* [PATCH v7 01/26] x86/fpu/xstate: Modify the initialization helper to handle both static and dynamic buffers
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 02/26] x86/fpu/xstate: Modify state copy helpers " Chang S. Bae
` (24 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, kvm
Have the function initializing the XSTATE buffer take a struct fpu *
pointer in preparation for dynamic state buffer support.
init_fpstate is a special case, which is indicated by a null pointer
parameter to fpstate_init().
Also, fpstate_init_xstate() now accepts the state component bitmap to
customize the compacted format.
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
---
Changes from v5:
* Moved fpstate_init_xstate() back to the header (again).
* Massaged the changelog.
Changes from v4:
* Added a proper function description. (Borislav Petkov)
* Added the likely() statement as a null pointer is a special case.
Changes from v3:
* Updated the changelog. (Borislav Petkov)
* Updated the function comment to use kernel-doc style. (Borislav Petkov)
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
---
arch/x86/include/asm/fpu/internal.h | 11 ++++++++++-
arch/x86/kernel/fpu/core.c | 28 +++++++++++++++++-----------
arch/x86/kernel/fpu/init.c | 2 +-
arch/x86/kernel/fpu/xstate.c | 3 +--
arch/x86/kvm/x86.c | 2 +-
5 files changed, 30 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 5a18694a89b2..c7a64e2806a9 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -80,7 +80,7 @@ static __always_inline __pure bool use_fxsr(void)
extern union fpregs_state init_fpstate;
-extern void fpstate_init(union fpregs_state *state);
+extern void fpstate_init(struct fpu *fpu);
#ifdef CONFIG_MATH_EMULATION
extern void fpstate_init_soft(struct swregs_state *soft);
#else
@@ -88,6 +88,15 @@ static inline void fpstate_init_soft(struct swregs_state *soft) {}
#endif
extern void save_fpregs_to_fpstate(struct fpu *fpu);
+static inline void fpstate_init_xstate(struct xregs_state *xsave, u64 mask)
+{
+ /*
+ * XRSTORS requires these bits set in xcomp_bv, or it will
+ * trigger #GP:
+ */
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | mask;
+}
+
/* Returns 0 or the negated trap number, which results in -EFAULT for #PF */
#define user_insn(insn, output, input...) \
({ \
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 7ada7bd03a32..6bc8ad4a3bd7 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -203,15 +203,6 @@ void fpu_sync_fpstate(struct fpu *fpu)
fpregs_unlock();
}
-static inline void fpstate_init_xstate(struct xregs_state *xsave)
-{
- /*
- * XRSTORS requires these bits set in xcomp_bv, or it will
- * trigger #GP:
- */
- xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
-}
-
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
{
fx->cwd = 0x37f;
@@ -229,8 +220,23 @@ static inline void fpstate_init_fstate(struct fregs_state *fp)
fp->fos = 0xffff0000u;
}
-void fpstate_init(union fpregs_state *state)
+/**
+ *
+ * fpstate_init() - initialize the xstate buffer
+ *
+ * If @fpu is NULL, initialize init_fpstate.
+ *
+ * @fpu: A struct fpu * pointer
+ */
+void fpstate_init(struct fpu *fpu)
{
+ union fpregs_state *state;
+
+ if (likely(fpu))
+ state = &fpu->state;
+ else
+ state = &init_fpstate;
+
if (!static_cpu_has(X86_FEATURE_FPU)) {
fpstate_init_soft(&state->soft);
return;
@@ -239,7 +245,7 @@ void fpstate_init(union fpregs_state *state)
memset(state, 0, fpu_kernel_xstate_size);
if (static_cpu_has(X86_FEATURE_XSAVES))
- fpstate_init_xstate(&state->xsave);
+ fpstate_init_xstate(&state->xsave, xfeatures_mask_all);
if (static_cpu_has(X86_FEATURE_FXSR))
fpstate_init_fxstate(&state->fxsave);
else
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 64e29927cc32..e14c72bc8706 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -124,7 +124,7 @@ static void __init fpu__init_system_generic(void)
* Set up the legacy init FPU context. (xstate init might overwrite this
* with a more modern format, if the CPU supports it.)
*/
- fpstate_init(&init_fpstate);
+ fpstate_init(NULL);
fpu__init_system_mxcsr();
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8def1b7f8fb..d4fdceb9a309 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -395,8 +395,7 @@ static void __init setup_init_fpu_buf(void)
print_xstate_features();
if (boot_cpu_has(X86_FEATURE_XSAVES))
- init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
- xfeatures_mask_all;
+ fpstate_init_xstate(&init_fpstate.xsave, xfeatures_mask_all);
/*
* Init all the features state with header.xfeatures being 0x0
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c6dc1b445231..606b66c9b44a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10597,7 +10597,7 @@ static void fx_init(struct kvm_vcpu *vcpu)
if (!vcpu->arch.guest_fpu)
return;
- fpstate_init(&vcpu->arch.guest_fpu->state);
+ fpstate_init(vcpu->arch.guest_fpu);
if (boot_cpu_has(X86_FEATURE_XSAVES))
vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
host_xcr0 | XSTATE_COMPACTION_ENABLED;
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 02/26] x86/fpu/xstate: Modify state copy helpers to handle both static and dynamic buffers
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 01/26] x86/fpu/xstate: Modify the initialization helper to handle both static and dynamic buffers Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 03/26] x86/fpu/xstate: Modify address finders " Chang S. Bae
` (23 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Have all the functions copying XSTATE take a struct fpu * pointer in
preparation for dynamic state buffer support.
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
---
Changes from v5:
* Adjusted function prototype changes to the recent renamed on the new
base.
Changes from v3:
* Updated the changelog. (Borislav Petkov)
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
---
arch/x86/include/asm/fpu/xstate.h | 4 ++--
arch/x86/kernel/fpu/regset.c | 2 +-
arch/x86/kernel/fpu/signal.c | 2 +-
arch/x86/kernel/fpu/xstate.c | 12 ++++++------
4 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 109dfcc75299..ede166e9d3f2 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -136,8 +136,8 @@ extern void __init update_regset_xstate_info(unsigned int size,
void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
int xfeature_size(int xfeature_nr);
-int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
-int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+int copy_uabi_from_kernel_to_xstate(struct fpu *fpu, const void *kbuf);
+int copy_sigframe_from_user_to_xstate(struct fpu *fpu, const void __user *ubuf);
void xsaves(struct xregs_state *xsave, u64 mask);
void xrstors(struct xregs_state *xsave, u64 mask);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 66ed317ebc0d..49dd307003ec 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -164,7 +164,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
}
fpu_force_restore(fpu);
- ret = copy_uabi_from_kernel_to_xstate(&fpu->state.xsave, kbuf ?: tmpbuf);
+ ret = copy_uabi_from_kernel_to_xstate(fpu, kbuf ?: tmpbuf);
out:
vfree(tmpbuf);
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 445c57c9c539..bec8c8046888 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -371,7 +371,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
fpregs_unlock();
if (use_xsave() && !fx_only) {
- ret = copy_sigframe_from_user_to_xstate(&fpu->state.xsave, buf_fx);
+ ret = copy_sigframe_from_user_to_xstate(fpu, buf_fx);
if (ret)
return ret;
} else {
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d4fdceb9a309..59f08953201c 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1089,10 +1089,10 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
return 0;
}
-
-static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf,
+static int copy_uabi_to_xstate(struct fpu *fpu, const void *kbuf,
const void __user *ubuf)
{
+ struct xregs_state *xsave = &fpu->state.xsave;
unsigned int offset, size;
struct xstate_header hdr;
u64 mask;
@@ -1158,9 +1158,9 @@ static int copy_uabi_to_xstate(struct xregs_state *xsave, const void *kbuf,
* format and copy to the target thread. This is called from
* xstateregs_set().
*/
-int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
+int copy_uabi_from_kernel_to_xstate(struct fpu *fpu, const void *kbuf)
{
- return copy_uabi_to_xstate(xsave, kbuf, NULL);
+ return copy_uabi_to_xstate(fpu, kbuf, NULL);
}
/*
@@ -1168,10 +1168,10 @@ int copy_uabi_from_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
* XSAVE[S] format and copy to the target thread. This is called from the
* sigreturn() and rt_sigreturn() system calls.
*/
-int copy_sigframe_from_user_to_xstate(struct xregs_state *xsave,
+int copy_sigframe_from_user_to_xstate(struct fpu *fpu,
const void __user *ubuf)
{
- return copy_uabi_to_xstate(xsave, NULL, ubuf);
+ return copy_uabi_to_xstate(fpu, NULL, ubuf);
}
static bool validate_xsaves_xrstors(u64 mask)
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 03/26] x86/fpu/xstate: Modify address finders to handle both static and dynamic buffers
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 01/26] x86/fpu/xstate: Modify the initialization helper to handle both static and dynamic buffers Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 02/26] x86/fpu/xstate: Modify state copy helpers " Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 04/26] x86/fpu/xstate: Add a new variable to indicate dynamic user states Chang S. Bae
` (22 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, kvm
Have all the functions finding XSTATE address take a struct fpu * pointer
in preparation for dynamic state buffer support.
init_fpstate is a special case, which is indicated by a null pointer
parameter to 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
---
Changes from v5:
* Adjusted some call sites for the new base.
Changes from v3:
* Updated the changelog. (Borislav Petkov)
* Updated the function comment to use kernel-doc style. (Borislav Petkov)
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
Changes from v1:
* Rebased on the upstream kernel (5.10)
---
arch/x86/include/asm/fpu/xstate.h | 2 +-
arch/x86/kernel/fpu/xstate.c | 42 ++++++++++++++++++++++++-------
arch/x86/kvm/x86.c | 10 +++-----
3 files changed, 38 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index ede166e9d3f2..2451bccc6cac 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -134,7 +134,7 @@ 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);
int xfeature_size(int xfeature_nr);
int copy_uabi_from_kernel_to_xstate(struct fpu *fpu, const void *kbuf);
int copy_sigframe_from_user_to_xstate(struct fpu *fpu, const void __user *ubuf);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 59f08953201c..af2adc954578 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -841,19 +841,34 @@ void fpu__resume_cpu(void)
}
}
-/*
+/**
+ * __raw_xsave_addr() - Find the address where the feature state is saved.
+ *
* Given an xstate feature nr, calculate where in the xsave
* buffer the state is. Callers should ensure that the buffer
* is valid.
+ *
+ * If @fpu is NULL, use init_fpstate.
+ *
+ * @fpu: A struct fpu * pointer
+ *
+ * Return: An address of the feature state in the buffer
*/
-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
@@ -866,15 +881,18 @@ 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 reference xstate buffer(s).
+ * (A null pointer parameter indicates 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?
*/
@@ -887,6 +905,12 @@ 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.
@@ -901,7 +925,7 @@ 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);
@@ -1061,8 +1085,8 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
membuf_write(&to, &pkru, sizeof(pkru));
} else {
copy_feature(header.xfeatures & BIT_ULL(i), &to,
- __raw_xsave_addr(xsave, i),
- __raw_xsave_addr(xinit, i),
+ __raw_xsave_addr(&tsk->thread.fpu, i),
+ __raw_xsave_addr(NULL, i),
xstate_sizes[i]);
}
/*
@@ -1129,7 +1153,7 @@ static int copy_uabi_to_xstate(struct fpu *fpu, const void *kbuf,
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];
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 606b66c9b44a..bd1e655dda9a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4717,7 +4717,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
memcpy(dest + offset, &vcpu->arch.pkru,
sizeof(vcpu->arch.pkru));
} else {
- src = get_xsave_addr(xsave, xfeature_nr);
+ src = get_xsave_addr(vcpu->arch.guest_fpu, xfeature_nr);
if (src)
memcpy(dest + offset, src, size);
}
@@ -4760,7 +4760,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
memcpy(&vcpu->arch.pkru, src + offset,
sizeof(vcpu->arch.pkru));
} else {
- void *dest = get_xsave_addr(xsave, xfeature_nr);
+ void *dest = get_xsave_addr(vcpu->arch.guest_fpu, xfeature_nr);
if (dest)
memcpy(dest, src + offset, size);
@@ -10829,12 +10829,10 @@ 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(vcpu->arch.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(vcpu->arch.guest_fpu, XFEATURE_BNDCSR);
if (mpx_state_buffer)
memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
if (init_event)
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 04/26] x86/fpu/xstate: Add a new variable to indicate dynamic user states
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (2 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 03/26] x86/fpu/xstate: Modify address finders " Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 05/26] x86/fpu/xstate: Add new variables to indicate dynamic XSTATE buffer size Chang S. Bae
` (21 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
The XSTATE per-task buffer is in preparation to be dynamic for user states.
Introduce a new mask variable to indicate the 'dynamic' user states. The
value is determined at boot-time.
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
---
Changes from v5:
* Made the variable __ro_after_init.
* Dropped the perf's xstate buffer renaming, as renamed already.
Changes from v3:
* Updated the changelog. (Borislav Petkov)
* Updated the code comment. (Borislav Petkov)
Changes from v2:
* Updated the changelog for clarification.
---
arch/x86/include/asm/fpu/xstate.h | 2 ++
arch/x86/kernel/fpu/xstate.c | 9 +++++++++
2 files changed, 11 insertions(+)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 2451bccc6cac..bc4cba62906b 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -129,6 +129,8 @@ static inline u64 xfeatures_mask_independent(void)
return XFEATURE_MASK_INDEPENDENT;
}
+extern u64 xfeatures_mask_user_dynamic;
+
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index af2adc954578..1d76afc29f19 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -62,6 +62,12 @@ static short xsave_cpuid_features[] __initdata = {
u64 xfeatures_mask_all __ro_after_init;
EXPORT_SYMBOL_GPL(xfeatures_mask_all);
+/*
+ * This represents user xstates, a subset of xfeatures_mask_all, saved in a
+ * dynamic kernel XSAVE buffer.
+ */
+u64 xfeatures_mask_user_dynamic __ro_after_init;
+
static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
@@ -709,6 +715,7 @@ static int __init init_xstate_size(void)
static void fpu__init_disable_system_xstate(void)
{
xfeatures_mask_all = 0;
+ xfeatures_mask_user_dynamic = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
}
@@ -780,6 +787,8 @@ void __init fpu__init_system_xstate(void)
/* Store it for paranoia check at the end */
xfeatures = xfeatures_mask_all;
+ /* Do not support the dynamically allocated buffer yet. */
+ xfeatures_mask_user_dynamic = 0;
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 05/26] x86/fpu/xstate: Add new variables to indicate dynamic XSTATE buffer size
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (3 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 04/26] x86/fpu/xstate: Add a new variable to indicate dynamic user states Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 06/26] x86/fpu/xstate: Calculate and remember dynamic XSTATE buffer sizes Chang S. Bae
` (20 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, kvm
The XSTATE per-task buffer is in preparation to be dynamic for user states.
Introduce new size variables to indicate the minimum and maximum size of
the buffer. The value is determined at boot-time.
Instead of adding them as newly exported, introduce helper functions to
access them as well as the user buffer size.
No functional change. Those sizes have no difference, as the buffer is not
dynamic yet.
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
---
Changes from v6:
* Massage the code comment.
Changes from v5:
* Made the new variables __ro_after_init for the new base code.
* Fixed the init_fpstate size for memset().
Changes from v3:
* Added as a new patch to add the variables along with new helpers.
(Borislav Petkov)
---
arch/x86/include/asm/fpu/xstate.h | 9 ++++
arch/x86/include/asm/processor.h | 10 +---
arch/x86/kernel/fpu/core.c | 26 +++++++---
arch/x86/kernel/fpu/init.c | 26 ++++------
arch/x86/kernel/fpu/regset.c | 2 +-
arch/x86/kernel/fpu/signal.c | 26 ++++++----
arch/x86/kernel/fpu/xstate.c | 83 +++++++++++++++++++++++++------
arch/x86/kernel/process.c | 7 +++
arch/x86/kvm/x86.c | 5 +-
9 files changed, 133 insertions(+), 61 deletions(-)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index bc4cba62906b..d722e774a9f9 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -136,6 +136,15 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
u64 xstate_mask);
+enum xstate_config {
+ XSTATE_MIN_SIZE,
+ XSTATE_MAX_SIZE,
+ XSTATE_USER_SIZE
+};
+
+extern unsigned int get_xstate_config(enum xstate_config cfg);
+void set_xstate_config(enum xstate_config cfg, unsigned int value);
+
void *get_xsave_addr(struct fpu *fpu, int xfeature_nr);
int xfeature_size(int xfeature_nr);
int copy_uabi_from_kernel_to_xstate(struct fpu *fpu, const void *kbuf);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f3020c54e2cb..505f596d1046 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -459,9 +459,6 @@ DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
#endif /* !X86_64 */
-extern unsigned int fpu_kernel_xstate_size;
-extern unsigned int fpu_user_xstate_size;
-
struct perf_event;
struct thread_struct {
@@ -536,12 +533,7 @@ struct thread_struct {
};
/* Whitelist the FPU state from the task_struct for hardened usercopy. */
-static inline void arch_thread_struct_whitelist(unsigned long *offset,
- unsigned long *size)
-{
- *offset = offsetof(struct thread_struct, fpu.state);
- *size = fpu_kernel_xstate_size;
-}
+extern void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size);
static inline void
native_load_sp0(unsigned long sp0)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 6bc8ad4a3bd7..fc01aa6f967e 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -231,21 +231,30 @@ static inline void fpstate_init_fstate(struct fregs_state *fp)
void fpstate_init(struct fpu *fpu)
{
union fpregs_state *state;
+ unsigned int size;
+ u64 mask;
- if (likely(fpu))
+ if (likely(fpu)) {
state = &fpu->state;
- else
+ /* The dynamic user states are not prepared yet. */
+ mask = xfeatures_mask_all & ~xfeatures_mask_user_dynamic;
+ size = get_xstate_config(XSTATE_MIN_SIZE);
+ } else {
state = &init_fpstate;
+ mask = xfeatures_mask_all;
+ size = sizeof(init_fpstate);
+ }
if (!static_cpu_has(X86_FEATURE_FPU)) {
fpstate_init_soft(&state->soft);
return;
}
- memset(state, 0, fpu_kernel_xstate_size);
+ memset(state, 0, size);
if (static_cpu_has(X86_FEATURE_XSAVES))
- fpstate_init_xstate(&state->xsave, xfeatures_mask_all);
+ fpstate_init_xstate(&state->xsave, mask);
+
if (static_cpu_has(X86_FEATURE_FXSR))
fpstate_init_fxstate(&state->fxsave);
else
@@ -268,8 +277,11 @@ int fpu_clone(struct task_struct *dst)
/*
* Don't let 'init optimized' areas of the XSAVE area
* leak into the child task:
+ *
+ * The child does not inherit the dynamic states. So,
+ * the xstate buffer has the minimum size.
*/
- memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size);
+ memset(&dst_fpu->state.xsave, 0, get_xstate_config(XSTATE_MIN_SIZE));
/*
* If the FPU registers are not owned by current just memcpy() the
@@ -278,7 +290,7 @@ int fpu_clone(struct task_struct *dst)
*/
fpregs_lock();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
- memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size);
+ memcpy(&dst_fpu->state, &src_fpu->state, get_xstate_config(XSTATE_MIN_SIZE));
else
save_fpregs_to_fpstate(dst_fpu);
@@ -337,7 +349,7 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
static inline unsigned int init_fpstate_copy_size(void)
{
if (!use_xsave())
- return fpu_kernel_xstate_size;
+ return get_xstate_config(XSTATE_MIN_SIZE);
/* XSAVE(S) just needs the legacy and the xstate header part */
return sizeof(init_fpstate.xsave);
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index e14c72bc8706..10e2a95916aa 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -129,15 +129,6 @@ static void __init fpu__init_system_generic(void)
fpu__init_system_mxcsr();
}
-/*
- * Size of the FPU context state. All tasks in the system use the
- * same context size, regardless of what portion they use.
- * This is inherent to the XSAVE architecture which puts all state
- * components into a single, continuous memory block:
- */
-unsigned int fpu_kernel_xstate_size __ro_after_init;
-EXPORT_SYMBOL_GPL(fpu_kernel_xstate_size);
-
/* Get alignment of the TYPE. */
#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)
@@ -167,8 +158,10 @@ static void __init fpu__init_task_struct_size(void)
/*
* Add back the dynamically-calculated register state
* size.
+ *
+ * Use the minimum size as embedded to task_struct.
*/
- task_size += fpu_kernel_xstate_size;
+ task_size += get_xstate_config(XSTATE_MIN_SIZE);
/*
* We dynamically size 'struct fpu', so we require that
@@ -193,6 +186,7 @@ static void __init fpu__init_task_struct_size(void)
static void __init fpu__init_system_xstate_size_legacy(void)
{
static int on_boot_cpu __initdata = 1;
+ unsigned int xstate_size;
WARN_ON_FPU(!on_boot_cpu);
on_boot_cpu = 0;
@@ -203,17 +197,17 @@ static void __init fpu__init_system_xstate_size_legacy(void)
*/
if (!boot_cpu_has(X86_FEATURE_FPU)) {
- fpu_kernel_xstate_size = sizeof(struct swregs_state);
+ xstate_size = sizeof(struct swregs_state);
} else {
if (boot_cpu_has(X86_FEATURE_FXSR))
- fpu_kernel_xstate_size =
- sizeof(struct fxregs_state);
+ xstate_size = sizeof(struct fxregs_state);
else
- fpu_kernel_xstate_size =
- sizeof(struct fregs_state);
+ xstate_size = sizeof(struct fregs_state);
}
- fpu_user_xstate_size = fpu_kernel_xstate_size;
+ set_xstate_config(XSTATE_MIN_SIZE, xstate_size);
+ set_xstate_config(XSTATE_MAX_SIZE, xstate_size);
+ set_xstate_config(XSTATE_USER_SIZE, xstate_size);
}
/* Legacy code to initialize eager fpu mode. */
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 49dd307003ec..8dea3730620e 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -149,7 +149,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
/*
* A whole standard-format XSAVE buffer is needed:
*/
- if (pos != 0 || count != fpu_user_xstate_size)
+ if (pos != 0 || count != get_xstate_config(XSTATE_USER_SIZE))
return -EFAULT;
if (!kbuf) {
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index bec8c8046888..63f000988fa6 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -36,7 +36,7 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
/* Check for the first magic field and other error scenarios. */
if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
fx_sw->xstate_size < min_xstate_size ||
- fx_sw->xstate_size > fpu_user_xstate_size ||
+ fx_sw->xstate_size > get_xstate_config(XSTATE_USER_SIZE) ||
fx_sw->xstate_size > fx_sw->extended_size)
goto setfx;
@@ -107,7 +107,7 @@ static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
return err;
err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *)(buf + fpu_user_xstate_size));
+ (__u32 __user *)(buf + get_xstate_config(XSTATE_USER_SIZE)));
/*
* Read the xfeatures which we copied (directly from the cpu or
@@ -144,7 +144,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
else
err = fnsave_to_user_sigframe((struct fregs_state __user *) buf);
- if (unlikely(err) && __clear_user(buf, fpu_user_xstate_size))
+ if (unlikely(err) && __clear_user(buf, get_xstate_config(XSTATE_USER_SIZE)))
err = -EFAULT;
return err;
}
@@ -205,7 +205,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
fpregs_unlock();
if (ret) {
- if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size))
+ if (!fault_in_pages_writeable(buf_fx, get_xstate_config(XSTATE_USER_SIZE)))
goto retry;
return -EFAULT;
}
@@ -304,12 +304,12 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore,
static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
bool ia32_fxstate)
{
- int state_size = fpu_kernel_xstate_size;
struct task_struct *tsk = current;
struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
u64 user_xfeatures = 0;
bool fx_only = false;
+ int state_size;
int ret;
if (use_xsave()) {
@@ -323,6 +323,8 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
state_size = fx_sw_user.xstate_size;
user_xfeatures = fx_sw_user.xfeatures;
} else {
+ /* The buffer cannot be dynamic without using XSAVE. */
+ state_size = get_xstate_config(XSTATE_MIN_SIZE);
user_xfeatures = XFEATURE_MASK_FPSSE;
}
@@ -418,8 +420,9 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
}
static inline int xstate_sigframe_size(void)
{
- return use_xsave() ? fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE :
- fpu_user_xstate_size;
+ int xstate_size = get_xstate_config(XSTATE_USER_SIZE);
+
+ return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
}
/*
@@ -514,19 +517,20 @@ unsigned long fpu__get_fpstate_size(void)
*/
void fpu__init_prepare_fx_sw_frame(void)
{
- int size = fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE;
+ int xstate_size = get_xstate_config(XSTATE_USER_SIZE);
+ int ext_size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
- fx_sw_reserved.extended_size = size;
+ fx_sw_reserved.extended_size = ext_size;
fx_sw_reserved.xfeatures = xfeatures_mask_uabi();
- fx_sw_reserved.xstate_size = fpu_user_xstate_size;
+ fx_sw_reserved.xstate_size = xstate_size;
if (IS_ENABLED(CONFIG_IA32_EMULATION) ||
IS_ENABLED(CONFIG_X86_32)) {
int fsave_header_size = sizeof(struct fregs_state);
fx_sw_reserved_ia32 = fx_sw_reserved;
- fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
+ fx_sw_reserved_ia32.extended_size = ext_size + fsave_header_size;
}
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 1d76afc29f19..cfcb0c29e5e4 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -77,12 +77,51 @@ static unsigned int xstate_comp_offsets[XFEATURE_MAX] __ro_after_init =
static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
-/*
- * The XSAVE area of kernel can be in standard or compacted format;
- * it is always in standard format for user mode. This is the user
- * mode standard format size used for signal and ptrace frames.
+/**
+ * struct fpu_xstate_buffer_config - xstate buffer configuration
+ * @max_size: The CPUID-enumerated all-feature "maximum" size
+ * for xstate per-task buffer.
+ * @min_size: The size to fit into the statically-allocated
+ * buffer. With dynamic states, this buffer no longer
+ * contains all the enabled state components.
+ * @user_size: The size of user-space buffer for signal and
+ * ptrace frames, in the non-compacted format.
*/
-unsigned int fpu_user_xstate_size __ro_after_init;
+struct fpu_xstate_buffer_config {
+ unsigned int min_size, max_size;
+ unsigned int user_size;
+};
+
+static struct fpu_xstate_buffer_config buffer_config __ro_after_init;
+
+unsigned int get_xstate_config(enum xstate_config cfg)
+{
+ switch (cfg) {
+ case XSTATE_MIN_SIZE:
+ return buffer_config.min_size;
+ case XSTATE_MAX_SIZE:
+ return buffer_config.max_size;
+ case XSTATE_USER_SIZE:
+ return buffer_config.user_size;
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL_GPL(get_xstate_config);
+
+void set_xstate_config(enum xstate_config cfg, unsigned int value)
+{
+ switch (cfg) {
+ case XSTATE_MIN_SIZE:
+ buffer_config.min_size = value;
+ break;
+ case XSTATE_MAX_SIZE:
+ buffer_config.max_size = value;
+ break;
+ case XSTATE_USER_SIZE:
+ buffer_config.user_size = value;
+ }
+}
/*
* Return whether the system supports a given xfeature.
@@ -595,7 +634,11 @@ static void do_extra_xstate_size_checks(void)
*/
paranoid_xstate_size += xfeature_size(i);
}
- XSTATE_WARN_ON(paranoid_xstate_size != fpu_kernel_xstate_size);
+ /*
+ * The size accounts for all the possible states reserved in the
+ * per-task buffer. Check against the maximum size.
+ */
+ XSTATE_WARN_ON(paranoid_xstate_size != get_xstate_config(XSTATE_MAX_SIZE));
}
@@ -690,21 +733,29 @@ static int __init init_xstate_size(void)
else
possible_xstate_size = xsave_size;
- /* Ensure we have the space to store all enabled: */
- if (!is_supported_xstate_size(possible_xstate_size))
- return -EINVAL;
-
/*
- * The size is OK, we are definitely going to use xsave,
- * make it known to the world that we need more space.
+ * The size accounts for all the possible states reserved in the
+ * per-task buffer. Set the maximum with this value.
*/
- fpu_kernel_xstate_size = possible_xstate_size;
+ set_xstate_config(XSTATE_MAX_SIZE, possible_xstate_size);
+
+ /* Perform an extra check for the maximum size. */
do_extra_xstate_size_checks();
+ /*
+ * Set the minimum to be the same as the maximum. The dynamic
+ * user states are not supported yet.
+ */
+ set_xstate_config(XSTATE_MIN_SIZE, possible_xstate_size);
+
+ /* Ensure the minimum size fits in the statically-allocated buffer: */
+ if (!is_supported_xstate_size(get_xstate_config(XSTATE_MIN_SIZE)))
+ return -EINVAL;
+
/*
* User space is always in standard format.
*/
- fpu_user_xstate_size = xsave_size;
+ set_xstate_config(XSTATE_USER_SIZE, xsave_size);
return 0;
}
@@ -800,7 +851,7 @@ void __init fpu__init_system_xstate(void)
* Update info used for ptrace frames; use standard-format size and no
* supervisor xstates:
*/
- update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_uabi());
+ update_regset_xstate_info(get_xstate_config(XSTATE_USER_SIZE), xfeatures_mask_uabi());
fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
@@ -820,7 +871,7 @@ void __init fpu__init_system_xstate(void)
print_xstate_offset_size();
pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
xfeatures_mask_all,
- fpu_kernel_xstate_size,
+ get_xstate_config(XSTATE_MAX_SIZE),
boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
return;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 1d9463e3096b..9ad39e807fcf 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -90,6 +90,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
return fpu_clone(dst);
}
+void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
+{
+ *offset = offsetof(struct thread_struct, fpu.state);
+ /* The buffer embedded in thread_struct has the minimum size. */
+ *size = get_xstate_config(XSTATE_MIN_SIZE);
+}
+
/*
* Free thread data structures etc..
*/
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd1e655dda9a..610a8c71e40e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9884,10 +9884,13 @@ static void kvm_save_current_fpu(struct fpu *fpu)
/*
* If the target FPU state is not resident in the CPU registers, just
* memcpy() from current, else save CPU state directly to the target.
+ *
+ * KVM does not support dynamic user states yet. Assume the buffer
+ * always has the minimum size.
*/
if (test_thread_flag(TIF_NEED_FPU_LOAD))
memcpy(&fpu->state, ¤t->thread.fpu.state,
- fpu_kernel_xstate_size);
+ get_xstate_config(XSTATE_MIN_SIZE));
else
save_fpregs_to_fpstate(fpu);
}
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 06/26] x86/fpu/xstate: Calculate and remember dynamic XSTATE buffer sizes
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (4 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 05/26] x86/fpu/xstate: Add new variables to indicate dynamic XSTATE buffer size Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 07/26] x86/fpu/xstate: Convert the struct fpu 'state' field to a pointer Chang S. Bae
` (19 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
The CPUID instruction separately enumerates sizes and alignments of
individual xfeatures. It independently enumerates the required size of an
entire XSAVE buffer to store all enabled features.
calculate_xstate_sizes() currently uses the individual feature
size/alignment enumeration to independently recalculate the required XSAVE
buffer size. This is compared against the CPUID-provided value.
Extend the function to accept an option to exclude dynamic states. With
that, calculate the maximum size that contains all the enabled states, and
the minimum size that fits in the statically-allocated buffer by excluding
dynamic states.
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
---
Changes from v6:
* Simplify xstate size calculation code. (Dave Hansen)
* Updated the changelog. (Dave Hansen)
* Fixed the v6 changes.
Changes from v5:
* Re-adjusted some local variable names.
Changes from v4:
* Massaged the function description, in preparation for the change
with a return value.
Changes from v3:
* Updated the changelog. (Borislav Petkov)
* Updated the code comment. (Borislav Petkov)
* Adjusted the calculation function naming.
* Moved out the new variable addition into a new patch.
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
* Renamed the in-line size variable.
* Updated some code comments.
---
arch/x86/kernel/fpu/xstate.c | 59 ++++++++++++++++++------------------
1 file changed, 30 insertions(+), 29 deletions(-)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index cfcb0c29e5e4..d1c256dbe8c5 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -591,24 +591,28 @@ static void check_xstate_against_struct(int nr)
}
}
-/*
- * This essentially double-checks what the cpu told us about
- * how large the XSAVE buffer needs to be. We are recalculating
- * it to be safe.
+/**
+ * calculate_xstate_size() - Calculate the xstate per-task buffer size.
+ *
+ * Independent XSAVE features allocate their own buffers and are always
+ * excluded. Only the size of the buffer for task->fpu is checked here.
*
- * Independent XSAVE features allocate their own buffers and are not
- * covered by these checks. Only the size of the buffer for task->fpu
- * is checked here.
+ * @include_dynamic_states: A knob to include dynamic states or not.
+ *
+ * Return: The calculated xstate size.
*/
-static void do_extra_xstate_size_checks(void)
+static unsigned int calculate_xstate_size(bool include_dynamic_states)
{
- int paranoid_xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ unsigned int xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
int i;
for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
if (!xfeature_enabled(i))
continue;
+ if (!include_dynamic_states && (xfeatures_mask_user_dynamic & BIT_ULL(i)))
+ continue;
+
check_xstate_against_struct(i);
/*
* Supervisor state components can be managed only by
@@ -619,7 +623,7 @@ static void do_extra_xstate_size_checks(void)
/* Align from the end of the previous feature */
if (xfeature_is_aligned(i))
- paranoid_xstate_size = ALIGN(paranoid_xstate_size, 64);
+ xstate_size = ALIGN(xstate_size, 64);
/*
* The offset of a given state in the non-compacted
* format is given to us in a CPUID leaf. We check
@@ -627,18 +631,15 @@ static void do_extra_xstate_size_checks(void)
* setup_xstate_features(). XSAVES uses compacted format.
*/
if (!cpu_feature_enabled(X86_FEATURE_XSAVES))
- paranoid_xstate_size = xfeature_uncompacted_offset(i);
+ xstate_size = xfeature_uncompacted_offset(i);
/*
* The compacted-format offset always depends on where
* the previous state ended.
*/
- paranoid_xstate_size += xfeature_size(i);
+ xstate_size += xfeature_size(i);
}
- /*
- * The size accounts for all the possible states reserved in the
- * per-task buffer. Check against the maximum size.
- */
- XSTATE_WARN_ON(paranoid_xstate_size != get_xstate_config(XSTATE_MAX_SIZE));
+
+ return xstate_size;
}
@@ -723,7 +724,7 @@ static bool is_supported_xstate_size(unsigned int test_xstate_size)
static int __init init_xstate_size(void)
{
/* Recompute the context size for enabled features: */
- unsigned int possible_xstate_size;
+ unsigned int possible_xstate_size, xstate_size;
unsigned int xsave_size;
xsave_size = get_xsave_size();
@@ -734,23 +735,23 @@ static int __init init_xstate_size(void)
possible_xstate_size = xsave_size;
/*
- * The size accounts for all the possible states reserved in the
- * per-task buffer. Set the maximum with this value.
+ * Calculate xstate size for all the possible states by setting
+ * 'true' to include dynamic states. Cross-check with the CPUID-
+ * provided size and record it.
*/
+ xstate_size = calculate_xstate_size(true);
+ XSTATE_WARN_ON(possible_xstate_size != xstate_size);
set_xstate_config(XSTATE_MAX_SIZE, possible_xstate_size);
- /* Perform an extra check for the maximum size. */
- do_extra_xstate_size_checks();
-
/*
- * Set the minimum to be the same as the maximum. The dynamic
- * user states are not supported yet.
+ * Calculate the xstate size without dynamic states by setting
+ * 'false' to exclude dynamic states. Ensure the size fits in
+ * the statically-allocated buffer and record it.
*/
- set_xstate_config(XSTATE_MIN_SIZE, possible_xstate_size);
-
- /* Ensure the minimum size fits in the statically-allocated buffer: */
- if (!is_supported_xstate_size(get_xstate_config(XSTATE_MIN_SIZE)))
+ xstate_size = calculate_xstate_size(false);
+ if (!is_supported_xstate_size(xstate_size))
return -EINVAL;
+ set_xstate_config(XSTATE_MIN_SIZE, xstate_size);
/*
* User space is always in standard format.
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 07/26] x86/fpu/xstate: Convert the struct fpu 'state' field to a pointer
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (5 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 06/26] x86/fpu/xstate: Calculate and remember dynamic XSTATE buffer sizes Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 08/26] x86/fpu/xstate: Introduce helpers to manage the XSTATE buffer dynamically Chang S. Bae
` (18 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, kvm
The XSTATE per-task buffer is embedded into struct fpu. The field 'state'
represents the buffer. When the dynamic user state is in use, the buffer
may be dynamically allocated.
Convert the 'state' field to point either to the embedded buffer or to the
dynamically-allocated buffer. Also, add a new field to represent the
embedded buffer.
The initial task sets it before dealing with soft FPU. Make sure that every
FPU state has a valid pointer value on its creation.
No functional change.
Suggested-by: Borislav Petkov <bp@suse.de>
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
---
Changes from v5:
* Tightened up task size calculation (previously, it could over-calculate)
* Adjusted the changelog.
Changes from v4:
* Fixed KVM's user_fpu and guest_fpu to initialize the 'state' field correctly.
* Massaged the changelog.
Changes from v3:
* Added as a new patch to simplify the buffer access. (Borislav Petkov)
---
arch/x86/include/asm/fpu/internal.h | 2 +-
arch/x86/include/asm/fpu/types.h | 29 ++++++++++++++++++++------
arch/x86/include/asm/trace/fpu.h | 4 ++--
arch/x86/kernel/fpu/core.c | 32 +++++++++++++++--------------
arch/x86/kernel/fpu/init.c | 8 +++++---
arch/x86/kernel/fpu/regset.c | 24 +++++++++++-----------
arch/x86/kernel/fpu/signal.c | 24 +++++++++++-----------
arch/x86/kernel/fpu/xstate.c | 8 ++++----
arch/x86/kernel/process.c | 2 +-
arch/x86/kvm/x86.c | 22 +++++++++++---------
arch/x86/math-emu/fpu_aux.c | 2 +-
arch/x86/math-emu/fpu_entry.c | 4 ++--
arch/x86/math-emu/fpu_system.h | 2 +-
13 files changed, 93 insertions(+), 70 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index c7a64e2806a9..d2fc19c0e457 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -484,7 +484,7 @@ static inline void fpregs_restore_userregs(void)
*/
mask = xfeatures_mask_restore_user() |
xfeatures_mask_supervisor();
- __restore_fpregs_from_fpstate(&fpu->state, mask);
+ __restore_fpregs_from_fpstate(fpu->state, mask);
fpregs_activate(fpu);
fpu->last_cpu = cpu;
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index f5a38a5f3ae1..c7826708f27f 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -339,13 +339,30 @@ struct fpu {
/*
* @state:
*
- * In-memory copy of all FPU registers that we save/restore
- * over context switches. If the task is using the FPU then
- * the registers in the FPU are more recent than this state
- * copy. If the task context-switches away then they get
- * saved here and represent the FPU state.
+ * A pointer to indicate the in-memory copy of all FPU registers
+ * that are saved/restored over context switches.
+ *
+ * Initially @state points to @__default_state. When dynamic states
+ * get used, a memory is allocated for the larger state copy and
+ * @state is updated to point to it. Then, the state in ->state
+ * supersedes and invalidates the state in @__default_state.
+ *
+ * In general, if the task is using the FPU then the registers in
+ * the FPU are more recent than the state copy. If the task
+ * context-switches away then they get saved in ->state and
+ * represent the FPU state.
+ */
+ union fpregs_state *state;
+
+ /*
+ * @__default_state:
+ *
+ * Initial in-memory copy of all FPU registers that saved/restored
+ * over context switches. When the task is switched to dynamic
+ * states, this copy is replaced with the new in-memory copy in
+ * ->state.
*/
- union fpregs_state state;
+ union fpregs_state __default_state;
/*
* WARNING: 'state' is dynamically-sized. Do not put
* anything after it here.
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 879b77792f94..ef82f4824ce7 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -22,8 +22,8 @@ DECLARE_EVENT_CLASS(x86_fpu,
__entry->fpu = fpu;
__entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD);
if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
- __entry->xfeatures = fpu->state.xsave.header.xfeatures;
- __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv;
+ __entry->xfeatures = fpu->state->xsave.header.xfeatures;
+ __entry->xcomp_bv = fpu->state->xsave.header.xcomp_bv;
}
),
TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx",
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index fc01aa6f967e..e12f18439fd4 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -99,19 +99,19 @@ EXPORT_SYMBOL(irq_fpu_usable);
void save_fpregs_to_fpstate(struct fpu *fpu)
{
if (likely(use_xsave())) {
- os_xsave(&fpu->state.xsave);
+ os_xsave(&fpu->state->xsave);
/*
* AVX512 state is tracked here because its use is
* known to slow the max clock speed of the core.
*/
- if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
+ if (fpu->state->xsave.header.xfeatures & XFEATURE_MASK_AVX512)
fpu->avx512_timestamp = jiffies;
return;
}
if (likely(use_fxsr())) {
- fxsave(&fpu->state.fxsave);
+ fxsave(&fpu->state->fxsave);
return;
}
@@ -119,8 +119,8 @@ void save_fpregs_to_fpstate(struct fpu *fpu)
* Legacy FPU register saving, FNSAVE always clears FPU registers,
* so we have to reload them from the memory state.
*/
- asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
- frstor(&fpu->state.fsave);
+ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state->fsave));
+ frstor(&fpu->state->fsave);
}
EXPORT_SYMBOL(save_fpregs_to_fpstate);
@@ -235,7 +235,7 @@ void fpstate_init(struct fpu *fpu)
u64 mask;
if (likely(fpu)) {
- state = &fpu->state;
+ state = fpu->state;
/* The dynamic user states are not prepared yet. */
mask = xfeatures_mask_all & ~xfeatures_mask_user_dynamic;
size = get_xstate_config(XSTATE_MIN_SIZE);
@@ -274,6 +274,8 @@ int fpu_clone(struct task_struct *dst)
if (!cpu_feature_enabled(X86_FEATURE_FPU))
return 0;
+ dst_fpu->state = &dst_fpu->__default_state;
+
/*
* Don't let 'init optimized' areas of the XSAVE area
* leak into the child task:
@@ -281,7 +283,7 @@ int fpu_clone(struct task_struct *dst)
* The child does not inherit the dynamic states. So,
* the xstate buffer has the minimum size.
*/
- memset(&dst_fpu->state.xsave, 0, get_xstate_config(XSTATE_MIN_SIZE));
+ memset(&dst_fpu->state->xsave, 0, get_xstate_config(XSTATE_MIN_SIZE));
/*
* If the FPU registers are not owned by current just memcpy() the
@@ -290,7 +292,7 @@ int fpu_clone(struct task_struct *dst)
*/
fpregs_lock();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
- memcpy(&dst_fpu->state, &src_fpu->state, get_xstate_config(XSTATE_MIN_SIZE));
+ memcpy(dst_fpu->state, src_fpu->state, get_xstate_config(XSTATE_MIN_SIZE));
else
save_fpregs_to_fpstate(dst_fpu);
@@ -377,7 +379,7 @@ static void fpu_reset_fpstate(void)
* user space as PKRU is eagerly written in switch_to() and
* flush_thread().
*/
- memcpy(&fpu->state, &init_fpstate, init_fpstate_copy_size());
+ memcpy(fpu->state, &init_fpstate, init_fpstate_copy_size());
set_thread_flag(TIF_NEED_FPU_LOAD);
fpregs_unlock();
}
@@ -404,7 +406,7 @@ void fpu__clear_user_states(struct fpu *fpu)
*/
if (xfeatures_mask_supervisor() &&
!fpregs_state_valid(fpu, smp_processor_id())) {
- os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor());
+ os_xrstor(&fpu->state->xsave, xfeatures_mask_supervisor());
}
/* Reset user states in registers. */
@@ -486,11 +488,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
* fully reproduce the context of the exception.
*/
if (boot_cpu_has(X86_FEATURE_FXSR)) {
- cwd = fpu->state.fxsave.cwd;
- swd = fpu->state.fxsave.swd;
+ cwd = fpu->state->fxsave.cwd;
+ swd = fpu->state->fxsave.swd;
} else {
- cwd = (unsigned short)fpu->state.fsave.cwd;
- swd = (unsigned short)fpu->state.fsave.swd;
+ cwd = (unsigned short)fpu->state->fsave.cwd;
+ swd = (unsigned short)fpu->state->fsave.swd;
}
err = swd & ~cwd;
@@ -504,7 +506,7 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
unsigned short mxcsr = MXCSR_DEFAULT;
if (boot_cpu_has(X86_FEATURE_XMM))
- mxcsr = fpu->state.fxsave.mxcsr;
+ mxcsr = fpu->state->fxsave.mxcsr;
err = ~(mxcsr >> 7) & mxcsr;
}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 10e2a95916aa..3e4e14ca723b 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -31,10 +31,12 @@ static void fpu__init_cpu_generic(void)
cr0 |= X86_CR0_EM;
write_cr0(cr0);
+ current->thread.fpu.state = ¤t->thread.fpu.__default_state;
+
/* Flush out any pending x87 state: */
#ifdef CONFIG_MATH_EMULATION
if (!boot_cpu_has(X86_FEATURE_FPU))
- fpstate_init_soft(¤t->thread.fpu.state.soft);
+ fpstate_init_soft(¤t->thread.fpu.state->soft);
else
#endif
asm volatile ("fninit");
@@ -153,7 +155,7 @@ static void __init fpu__init_task_struct_size(void)
* Subtract off the static size of the register state.
* It potentially has a bunch of padding.
*/
- task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state);
+ task_size -= sizeof(((struct task_struct *)0)->thread.fpu.__default_state);
/*
* Add back the dynamically-calculated register state
@@ -170,7 +172,7 @@ static void __init fpu__init_task_struct_size(void)
* you hit a compile error here, check the structure to
* see if something got added to the end.
*/
- CHECK_MEMBER_AT_END_OF(struct fpu, state);
+ CHECK_MEMBER_AT_END_OF(struct fpu, __default_state);
CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 8dea3730620e..73d7d7b489fe 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -74,8 +74,8 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
sync_fpstate(fpu);
if (!use_xsave()) {
- return membuf_write(&to, &fpu->state.fxsave,
- sizeof(fpu->state.fxsave));
+ return membuf_write(&to, &fpu->state->fxsave,
+ sizeof(fpu->state->fxsave));
}
copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_FX);
@@ -110,15 +110,15 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
fpu_force_restore(fpu);
/* Copy the state */
- memcpy(&fpu->state.fxsave, &newstate, sizeof(newstate));
+ memcpy(&fpu->state->fxsave, &newstate, sizeof(newstate));
/* Clear xmm8..15 */
- BUILD_BUG_ON(sizeof(fpu->state.fxsave.xmm_space) != 16 * 16);
- memset(&fpu->state.fxsave.xmm_space[8], 0, 8 * 16);
+ BUILD_BUG_ON(sizeof(fpu->state->fxsave.xmm_space) != 16 * 16);
+ memset(&fpu->state->fxsave.xmm_space[8], 0, 8 * 16);
/* Mark FP and SSE as in use when XSAVE is enabled */
if (use_xsave())
- fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
+ fpu->state->xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
return 0;
}
@@ -283,7 +283,7 @@ static void __convert_from_fxsr(struct user_i387_ia32_struct *env,
void
convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
{
- __convert_from_fxsr(env, tsk, &tsk->thread.fpu.state.fxsave);
+ __convert_from_fxsr(env, tsk, &tsk->thread.fpu.state->fxsave);
}
void convert_to_fxsr(struct fxregs_state *fxsave,
@@ -326,7 +326,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
return fpregs_soft_get(target, regset, to);
if (!cpu_feature_enabled(X86_FEATURE_FXSR)) {
- return membuf_write(&to, &fpu->state.fsave,
+ return membuf_write(&to, &fpu->state->fsave,
sizeof(struct fregs_state));
}
@@ -337,7 +337,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
copy_xstate_to_uabi_buf(mb, target, XSTATE_COPY_FP);
fx = &fxsave;
} else {
- fx = &fpu->state.fxsave;
+ fx = &fpu->state->fxsave;
}
__convert_from_fxsr(&env, target, fx);
@@ -366,16 +366,16 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
fpu_force_restore(fpu);
if (cpu_feature_enabled(X86_FEATURE_FXSR))
- convert_to_fxsr(&fpu->state.fxsave, &env);
+ convert_to_fxsr(&fpu->state->fxsave, &env);
else
- memcpy(&fpu->state.fsave, &env, sizeof(env));
+ memcpy(&fpu->state->fsave, &env, sizeof(env));
/*
* Update the header bit in the xsave header, indicating the
* presence of FP.
*/
if (cpu_feature_enabled(X86_FEATURE_XSAVE))
- fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP;
+ fpu->state->xsave.header.xfeatures |= XFEATURE_MASK_FP;
return 0;
}
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 63f000988fa6..2f35aada2007 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -67,13 +67,13 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
{
if (use_fxsr()) {
- struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct xregs_state *xsave = &tsk->thread.fpu.state->xsave;
struct user_i387_ia32_struct env;
struct _fpstate_32 __user *fp = buf;
fpregs_lock();
if (!test_thread_flag(TIF_NEED_FPU_LOAD))
- fxsave(&tsk->thread.fpu.state.fxsave);
+ fxsave(&tsk->thread.fpu.state->fxsave);
fpregs_unlock();
convert_from_fxsr(&env, tsk);
@@ -294,7 +294,7 @@ static int restore_fpregs_from_user(void __user *buf, u64 xrestore,
* been restored from a user buffer directly.
*/
if (test_thread_flag(TIF_NEED_FPU_LOAD) && xfeatures_mask_supervisor())
- os_xrstor(&fpu->state.xsave, xfeatures_mask_supervisor());
+ os_xrstor(&fpu->state->xsave, xfeatures_mask_supervisor());
fpregs_mark_activate();
fpregs_unlock();
@@ -365,7 +365,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
* the right place in memory. It's ia32 mode. Shrug.
*/
if (xfeatures_mask_supervisor())
- os_xsave(&fpu->state.xsave);
+ os_xsave(&fpu->state->xsave);
set_thread_flag(TIF_NEED_FPU_LOAD);
}
__fpu_invalidate_fpregs_state(fpu);
@@ -377,21 +377,21 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
if (ret)
return ret;
} else {
- if (__copy_from_user(&fpu->state.fxsave, buf_fx,
- sizeof(fpu->state.fxsave)))
+ if (__copy_from_user(&fpu->state->fxsave, buf_fx,
+ sizeof(fpu->state->fxsave)))
return -EFAULT;
/* Reject invalid MXCSR values. */
- if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
+ if (fpu->state->fxsave.mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
/* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */
if (use_xsave())
- fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
+ fpu->state->xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
}
/* Fold the legacy FP storage */
- convert_to_fxsr(&fpu->state.fxsave, &env);
+ convert_to_fxsr(&fpu->state->fxsave, &env);
fpregs_lock();
if (use_xsave()) {
@@ -406,10 +406,10 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
*/
u64 mask = user_xfeatures | xfeatures_mask_supervisor();
- fpu->state.xsave.header.xfeatures &= mask;
- ret = os_xrstor_safe(&fpu->state.xsave, xfeatures_mask_all);
+ fpu->state->xsave.header.xfeatures &= mask;
+ ret = os_xrstor_safe(&fpu->state->xsave, xfeatures_mask_all);
} else {
- ret = fxrstor_safe(&fpu->state.fxsave);
+ ret = fxrstor_safe(&fpu->state->fxsave);
}
if (likely(!ret))
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d1c256dbe8c5..b86aa7eb421b 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -925,7 +925,7 @@ static void *__raw_xsave_addr(struct fpu *fpu, int xfeature_nr)
}
if (fpu)
- xsave = &fpu->state.xsave;
+ xsave = &fpu->state->xsave;
else
xsave = &init_fpstate.xsave;
@@ -968,7 +968,7 @@ void *get_xsave_addr(struct fpu *fpu, int xfeature_nr)
"get of unsupported state");
if (fpu)
- xsave = &fpu->state.xsave;
+ xsave = &fpu->state->xsave;
else
xsave = &init_fpstate.xsave;
@@ -1060,7 +1060,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode copy_mode)
{
const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
- struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+ struct xregs_state *xsave = &tsk->thread.fpu.state->xsave;
struct xregs_state *xinit = &init_fpstate.xsave;
struct xstate_header header;
unsigned int zerofrom;
@@ -1177,7 +1177,7 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
static int copy_uabi_to_xstate(struct fpu *fpu, const void *kbuf,
const void __user *ubuf)
{
- struct xregs_state *xsave = &fpu->state.xsave;
+ struct xregs_state *xsave = &fpu->state->xsave;
unsigned int offset, size;
struct xstate_header hdr;
u64 mask;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9ad39e807fcf..534b9fb7e7ee 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -92,7 +92,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
{
- *offset = offsetof(struct thread_struct, fpu.state);
+ *offset = offsetof(struct thread_struct, fpu.__default_state);
/* The buffer embedded in thread_struct has the minimum size. */
*size = get_xstate_config(XSTATE_MIN_SIZE);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 610a8c71e40e..c7c273899eb0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4685,7 +4685,7 @@ 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;
+ struct xregs_state *xsave = &vcpu->arch.guest_fpu->state->xsave;
u64 xstate_bv = xsave->header.xfeatures;
u64 valid;
@@ -4728,7 +4728,7 @@ 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;
+ struct xregs_state *xsave = &vcpu->arch.guest_fpu->state->xsave;
u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
u64 valid;
@@ -4781,7 +4781,7 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
fill_xsave((u8 *) guest_xsave->region, vcpu);
} else {
memcpy(guest_xsave->region,
- &vcpu->arch.guest_fpu->state.fxsave,
+ &vcpu->arch.guest_fpu->state->fxsave,
sizeof(struct fxregs_state));
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
XFEATURE_MASK_FPSSE;
@@ -4815,7 +4815,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
- memcpy(&vcpu->arch.guest_fpu->state.fxsave,
+ memcpy(&vcpu->arch.guest_fpu->state->fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
}
return 0;
@@ -9889,7 +9889,7 @@ static void kvm_save_current_fpu(struct fpu *fpu)
* always has the minimum size.
*/
if (test_thread_flag(TIF_NEED_FPU_LOAD))
- memcpy(&fpu->state, ¤t->thread.fpu.state,
+ memcpy(fpu->state, current->thread.fpu.state,
get_xstate_config(XSTATE_MIN_SIZE));
else
save_fpregs_to_fpstate(fpu);
@@ -9908,7 +9908,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
*/
if (vcpu->arch.guest_fpu)
/* PKRU is separately restored in kvm_x86_ops.run. */
- __restore_fpregs_from_fpstate(&vcpu->arch.guest_fpu->state,
+ __restore_fpregs_from_fpstate(vcpu->arch.guest_fpu->state,
~XFEATURE_MASK_PKRU);
fpregs_mark_activate();
@@ -9929,7 +9929,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
if (vcpu->arch.guest_fpu)
kvm_save_current_fpu(vcpu->arch.guest_fpu);
- restore_fpregs_from_fpstate(&vcpu->arch.user_fpu->state);
+ restore_fpregs_from_fpstate(vcpu->arch.user_fpu->state);
fpregs_mark_activate();
fpregs_unlock();
@@ -10518,7 +10518,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
vcpu_load(vcpu);
- fxsave = &vcpu->arch.guest_fpu->state.fxsave;
+ fxsave = &vcpu->arch.guest_fpu->state->fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
fpu->fsw = fxsave->swd;
@@ -10541,7 +10541,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
vcpu_load(vcpu);
- fxsave = &vcpu->arch.guest_fpu->state.fxsave;
+ fxsave = &vcpu->arch.guest_fpu->state->fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
@@ -10602,7 +10602,7 @@ static void fx_init(struct kvm_vcpu *vcpu)
fpstate_init(vcpu->arch.guest_fpu);
if (boot_cpu_has(X86_FEATURE_XSAVES))
- vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
+ vcpu->arch.guest_fpu->state->xsave.header.xcomp_bv =
host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
@@ -10682,6 +10682,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
pr_err("kvm: failed to allocate userspace's fpu\n");
goto free_emulate_ctxt;
}
+ vcpu->arch.user_fpu->state = &vcpu->arch.user_fpu->__default_state;
vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
GFP_KERNEL_ACCOUNT);
@@ -10689,6 +10690,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
pr_err("kvm: failed to allocate vcpu's fpu\n");
goto free_user_fpu;
}
+ vcpu->arch.guest_fpu->state = &vcpu->arch.guest_fpu->__default_state;
fx_init(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index 034748459482..51432a73024c 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -53,7 +53,7 @@ void fpstate_init_soft(struct swregs_state *soft)
void finit(void)
{
- fpstate_init_soft(¤t->thread.fpu.state.soft);
+ fpstate_init_soft(¤t->thread.fpu.state->soft);
}
/*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 8679a9d6c47f..6ba56632170e 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -640,7 +640,7 @@ int fpregs_soft_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct swregs_state *s387 = &target->thread.fpu.state.soft;
+ struct swregs_state *s387 = &target->thread.fpu.state->soft;
void *space = s387->st_space;
int ret;
int offset, other, i, tags, regnr, tag, newtop;
@@ -691,7 +691,7 @@ int fpregs_soft_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
{
- struct swregs_state *s387 = &target->thread.fpu.state.soft;
+ struct swregs_state *s387 = &target->thread.fpu.state->soft;
const void *space = s387->st_space;
int offset = (S387->ftop & 7) * 10, other = 80 - offset;
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 9b41391867dc..a6291ddfdda6 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -73,7 +73,7 @@ static inline bool seg_writable(struct desc_struct *d)
return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE;
}
-#define I387 (¤t->thread.fpu.state)
+#define I387 (current->thread.fpu.state)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 08/26] x86/fpu/xstate: Introduce helpers to manage the XSTATE buffer dynamically
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (6 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 07/26] x86/fpu/xstate: Convert the struct fpu 'state' field to a pointer Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 09/26] x86/fpu/xstate: Update the XSTATE save function to support dynamic states Chang S. Bae
` (17 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
The static XSTATE per-task buffer contains the extended register states --
but it is not expandable at runtime. Introduce runtime methods and a new
fpu struct field to support the expansion.
fpu->state_mask indicates which state components are reserved to be
saved in the XSTATE buffer.
alloc_xstate_buffer() uses vzalloc(). If use of this mechanism grows to
allocate buffers larger than 64KB, a more sophisticated allocation scheme
that includes purpose-built reclaim capability might be justified.
Introduce a new helper -- get_xstate_size() to calculate the buffer size.
Also, use the new field and helper to initialize the buffer.
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
---
Changes from v5:
* Added to ensure XSAVES format with current in fpu_reset_fpstate() for new
base code.
Changes from v3:
* Updated code comments. (Borislav Petkov)
* Used vzalloc() instead of vmalloc() with memset(). (Borislav Petkov)
* Removed the max size check for >64KB. (Borislav Petkov)
* Removed the allocation size check in the helper. (Borislav Petkov)
* Switched the function description in the kernel-doc style.
* Used them for buffer initialization -- moved from the next patch.
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
* Replaced 'area' with 'buffer' in the comments and the changelog.
* Updated the code comments.
Changes from v1:
* Removed unneeded interrupt masking (Andy Lutomirski)
* Added vmalloc() error tracing (Dave Hansen, PeterZ, and Andy Lutomirski)
---
arch/x86/include/asm/fpu/types.h | 8 ++
arch/x86/include/asm/fpu/xstate.h | 3 +
arch/x86/include/asm/trace/fpu.h | 5 ++
arch/x86/kernel/fpu/core.c | 18 +++--
arch/x86/kernel/fpu/xstate.c | 127 ++++++++++++++++++++++++++++++
5 files changed, 154 insertions(+), 7 deletions(-)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index c7826708f27f..c0192e16cadb 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -336,6 +336,14 @@ struct fpu {
*/
unsigned long avx512_timestamp;
+ /*
+ * @state_mask:
+ *
+ * The bitmap represents state components reserved to be saved in
+ * ->state.
+ */
+ u64 state_mask;
+
/*
* @state:
*
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index d722e774a9f9..45735441fbe8 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -146,6 +146,9 @@ extern unsigned int get_xstate_config(enum xstate_config cfg);
void set_xstate_config(enum xstate_config cfg, unsigned int value);
void *get_xsave_addr(struct fpu *fpu, int xfeature_nr);
+unsigned int get_xstate_size(u64 mask);
+int alloc_xstate_buffer(struct fpu *fpu, u64 mask);
+void free_xstate_buffer(struct fpu *fpu);
int xfeature_size(int xfeature_nr);
int copy_uabi_from_kernel_to_xstate(struct fpu *fpu, const void *kbuf);
int copy_sigframe_from_user_to_xstate(struct fpu *fpu, const void __user *ubuf);
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index ef82f4824ce7..b691c2db47c7 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -89,6 +89,11 @@ DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed,
TP_ARGS(fpu)
);
+DEFINE_EVENT(x86_fpu, x86_fpu_xstate_alloc_failed,
+ TP_PROTO(struct fpu *fpu),
+ TP_ARGS(fpu)
+);
+
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH asm/trace/
#undef TRACE_INCLUDE_FILE
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e12f18439fd4..1f158e96c34f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -236,9 +236,8 @@ void fpstate_init(struct fpu *fpu)
if (likely(fpu)) {
state = fpu->state;
- /* The dynamic user states are not prepared yet. */
- mask = xfeatures_mask_all & ~xfeatures_mask_user_dynamic;
- size = get_xstate_config(XSTATE_MIN_SIZE);
+ mask = fpu->state_mask;
+ size = get_xstate_size(fpu->state_mask);
} else {
state = &init_fpstate;
mask = xfeatures_mask_all;
@@ -274,14 +273,16 @@ int fpu_clone(struct task_struct *dst)
if (!cpu_feature_enabled(X86_FEATURE_FPU))
return 0;
+ /*
+ * The child does not inherit the dynamic states. Thus, use the
+ * buffer embedded in struct task_struct, which has the minimum
+ * size.
+ */
+ dst_fpu->state_mask = (xfeatures_mask_all & ~xfeatures_mask_user_dynamic);
dst_fpu->state = &dst_fpu->__default_state;
-
/*
* Don't let 'init optimized' areas of the XSAVE area
* leak into the child task:
- *
- * The child does not inherit the dynamic states. So,
- * the xstate buffer has the minimum size.
*/
memset(&dst_fpu->state->xsave, 0, get_xstate_config(XSTATE_MIN_SIZE));
@@ -380,6 +381,9 @@ static void fpu_reset_fpstate(void)
* flush_thread().
*/
memcpy(fpu->state, &init_fpstate, init_fpstate_copy_size());
+ /* Adjust the xstate buffer format for current. */
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ fpstate_init_xstate(&fpu->state->xsave, fpu->state_mask);
set_thread_flag(TIF_NEED_FPU_LOAD);
fpregs_unlock();
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index b86aa7eb421b..597935ec5089 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -10,6 +10,7 @@
#include <linux/pkeys.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
#include <asm/fpu/api.h>
#include <asm/fpu/internal.h>
@@ -19,6 +20,7 @@
#include <asm/tlbflush.h>
#include <asm/cpufeature.h>
+#include <asm/trace/fpu.h>
/*
* Although we spell it out in here, the Processor Trace
@@ -76,6 +78,12 @@ static unsigned int xstate_comp_offsets[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
+/*
+ * True if the buffer of the corresponding XFEATURE is located on the next 64
+ * byte boundary. Otherwise, it follows the preceding component immediately.
+ */
+static bool xstate_aligns[XFEATURE_MAX] __ro_after_init =
+ { [ 0 ... XFEATURE_MAX - 1] = false};
/**
* struct fpu_xstate_buffer_config - xstate buffer configuration
@@ -174,6 +182,55 @@ static bool xfeature_is_supervisor(int xfeature_nr)
return ecx & 1;
}
+/**
+ * get_xstate_size() - Calculate an xstate buffer size
+ * @mask: This bitmap tells which components reserved in the buffer.
+ *
+ * Available once those arrays for the offset, size, and alignment info are
+ * set up, by setup_xstate_features().
+ *
+ * Returns: The buffer size
+ */
+unsigned int get_xstate_size(u64 mask)
+{
+ unsigned int size;
+ int i, nr;
+
+ if (!mask)
+ return 0;
+
+ /*
+ * The minimum buffer size excludes the dynamic user state. When a
+ * task uses the state, the buffer can grow up to the max size.
+ */
+ if (mask == (xfeatures_mask_all & ~xfeatures_mask_user_dynamic))
+ return get_xstate_config(XSTATE_MIN_SIZE);
+ else if (mask == xfeatures_mask_all)
+ return get_xstate_config(XSTATE_MAX_SIZE);
+
+ nr = fls64(mask) - 1;
+
+ if (!boot_cpu_has(X86_FEATURE_XSAVES))
+ return xstate_offsets[nr] + xstate_sizes[nr];
+
+ if ((xfeatures_mask_all & (BIT_ULL(nr + 1) - 1)) == mask)
+ return xstate_comp_offsets[nr] + xstate_sizes[nr];
+
+ /*
+ * With the given mask, no relevant size is found so far. So,
+ * calculate it by summing up each state size.
+ */
+ for (size = FXSAVE_SIZE + XSAVE_HDR_SIZE, i = FIRST_EXTENDED_XFEATURE; i <= nr; i++) {
+ if (!(mask & BIT_ULL(i)))
+ continue;
+
+ if (xstate_aligns[i])
+ size = ALIGN(size, 64);
+ size += xstate_sizes[i];
+ }
+ return size;
+}
+
/*
* Enable the extended processor state save/restore feature.
* Called once per CPU onlining.
@@ -224,10 +281,12 @@ static void __init setup_xstate_features(void)
xstate_offsets[XFEATURE_FP] = 0;
xstate_sizes[XFEATURE_FP] = offsetof(struct fxregs_state,
xmm_space);
+ xstate_aligns[XFEATURE_FP] = true;
xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP];
xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state,
xmm_space);
+ xstate_aligns[XFEATURE_SSE] = true;
for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
if (!xfeature_enabled(i))
@@ -245,6 +304,7 @@ static void __init setup_xstate_features(void)
continue;
xstate_offsets[i] = ebx;
+ xstate_aligns[i] = (ecx & 2) ? true : false;
/*
* In our xstate size checks, we assume that the highest-numbered
@@ -848,6 +908,9 @@ void __init fpu__init_system_xstate(void)
if (err)
goto out_disable;
+ /* Make sure init_task does not include the dynamic user states. */
+ current->thread.fpu.state_mask = (xfeatures_mask_all & ~xfeatures_mask_user_dynamic);
+
/*
* Update info used for ptrace frames; use standard-format size and no
* supervisor xstates:
@@ -1038,6 +1101,70 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
}
#endif /* ! CONFIG_ARCH_HAS_PKEYS */
+void free_xstate_buffer(struct fpu *fpu)
+{
+ /* Free up only the dynamically-allocated memory. */
+ if (fpu->state != &fpu->__default_state)
+ vfree(fpu->state);
+}
+
+/**
+ * alloc_xstate_buffer() - Allocate a buffer with the size calculated from
+ * @mask.
+ *
+ * @fpu: A struct fpu * pointer
+ * @mask: The bitmap tells which components to be reserved in the new
+ * buffer.
+ *
+ * Use vmalloc() simply here. If the task with a vmalloc()-allocated buffer
+ * tends to terminate quickly, vfree()-induced IPIs may be a concern.
+ * Caching may be helpful for this. But the task with large state is likely
+ * to live longer.
+ *
+ * Also, this method does not shrink or reclaim the buffer.
+ *
+ * Returns 0 on success, -ENOMEM on allocation error.
+ */
+int alloc_xstate_buffer(struct fpu *fpu, u64 mask)
+{
+ union fpregs_state *state;
+ unsigned int oldsz, newsz;
+ u64 state_mask;
+
+ state_mask = fpu->state_mask | mask;
+
+ oldsz = get_xstate_size(fpu->state_mask);
+ newsz = get_xstate_size(state_mask);
+
+ if (oldsz >= newsz)
+ return 0;
+
+ state = vzalloc(newsz);
+ if (!state) {
+ /*
+ * When allocation requested from #NM, the error code may
+ * not be populated well. Then, this tracepoint is useful
+ * for providing the failure context.
+ */
+ trace_x86_fpu_xstate_alloc_failed(fpu);
+ return -ENOMEM;
+ }
+
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ fpstate_init_xstate(&state->xsave, state_mask);
+
+ /*
+ * As long as the register state is intact, save the xstate in the
+ * new buffer at the next context copy/switch or potentially
+ * ptrace-driven xstate writing.
+ */
+
+ free_xstate_buffer(fpu);
+ fpu->state = state;
+ fpu->state_mask = state_mask;
+ return 0;
+}
+
static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
void *init_xstate, unsigned int size)
{
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 09/26] x86/fpu/xstate: Update the XSTATE save function to support dynamic states
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (7 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 08/26] x86/fpu/xstate: Introduce helpers to manage the XSTATE buffer dynamically Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 10/26] x86/fpu/xstate: Update the XSTATE buffer address finder " Chang S. Bae
` (16 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, kvm
Extend os_xsave() to receive a mask argument of which states to save, in
preparation for dynamic user state handling.
Update KVM to set a valid fpu->state_mask, so it can continue to share with
the core code.
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
---
Changes from v5:
* Adjusted the changelog and code for the new base code.
Changes from v3:
* Updated the changelog. (Borislav Petkov)
* Made the code change more reviewable.
Changes from v2:
* Updated the changelog to clarify the KVM code changes.
---
arch/x86/include/asm/fpu/internal.h | 3 +--
arch/x86/kernel/fpu/core.c | 2 +-
arch/x86/kernel/fpu/signal.c | 2 +-
arch/x86/kvm/x86.c | 9 +++++++--
4 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index d2fc19c0e457..263e349ff85a 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -298,9 +298,8 @@ static inline void os_xrstor_booting(struct xregs_state *xstate)
* Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features
* and command line options. The choice is permanent until the next reboot.
*/
-static inline void os_xsave(struct xregs_state *xstate)
+static inline void os_xsave(struct xregs_state *xstate, u64 mask)
{
- u64 mask = xfeatures_mask_all;
u32 lmask = mask;
u32 hmask = mask >> 32;
int err;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 1f158e96c34f..ed127c4d182b 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -99,7 +99,7 @@ EXPORT_SYMBOL(irq_fpu_usable);
void save_fpregs_to_fpstate(struct fpu *fpu)
{
if (likely(use_xsave())) {
- os_xsave(&fpu->state->xsave);
+ os_xsave(&fpu->state->xsave, fpu->state_mask);
/*
* AVX512 state is tracked here because its use is
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 2f35aada2007..f70f84d53442 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -365,7 +365,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
* the right place in memory. It's ia32 mode. Shrug.
*/
if (xfeatures_mask_supervisor())
- os_xsave(&fpu->state->xsave);
+ os_xsave(&fpu->state->xsave, fpu->state_mask);
set_thread_flag(TIF_NEED_FPU_LOAD);
}
__fpu_invalidate_fpregs_state(fpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c7c273899eb0..8c4ecc1628eb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9888,11 +9888,16 @@ static void kvm_save_current_fpu(struct fpu *fpu)
* KVM does not support dynamic user states yet. Assume the buffer
* always has the minimum size.
*/
- if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ if (test_thread_flag(TIF_NEED_FPU_LOAD)) {
memcpy(fpu->state, current->thread.fpu.state,
get_xstate_config(XSTATE_MIN_SIZE));
- else
+ } else {
+ struct fpu *src_fpu = ¤t->thread.fpu;
+
+ if (fpu->state_mask != src_fpu->state_mask)
+ fpu->state_mask = src_fpu->state_mask;
save_fpregs_to_fpstate(fpu);
+ }
}
/* Swap (qemu) user FPU context for the guest FPU context. */
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 10/26] x86/fpu/xstate: Update the XSTATE buffer address finder to support dynamic states
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (8 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 09/26] x86/fpu/xstate: Update the XSTATE save function to support dynamic states Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 11/26] x86/fpu/xstate: Update the XSTATE context copy function " Chang S. Bae
` (15 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
__raw_xsave_addr() returns the requested component's pointer in an XSTATE
buffer, by simply looking up the offset table. The offset used to be fixed,
but, with dynamic user states, it becomes variable.
get_xstate_size() has a routine to find an offset at runtime. Refactor to
use it for the address finder.
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
---
Changes from v5:
* Updated for future proofed __raw_xsave_addr().
Changes from v3:
* Added the function description in the kernel-doc style. (Borislav Petkov)
* Removed 'no functional change' in the changelog. (Borislav Petkov)
---
arch/x86/kernel/fpu/xstate.c | 78 ++++++++++++++++++++++++------------
1 file changed, 53 insertions(+), 25 deletions(-)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 597935ec5089..a6473a632e6e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -182,6 +182,38 @@ static bool xfeature_is_supervisor(int xfeature_nr)
return ecx & 1;
}
+/**
+ * get_xstate_comp_offset() - Find the feature's offset in the compacted
+ * format.
+ * @mask: This bitmap tells which components reserved in the format.
+ * @feature_nr: The feature number
+ *
+ * Returns: The offset value
+ */
+static unsigned int get_xstate_comp_offset(u64 mask, int feature_nr)
+{
+ u64 xmask = BIT_ULL(feature_nr + 1) - 1;
+ unsigned int next_offset, offset = 0;
+ int i;
+
+ if ((xfeatures_mask_all & xmask) == (mask & xmask))
+ return xstate_comp_offsets[feature_nr];
+
+ /*
+ * With the given mask, no relevant size is found. Calculate it by
+ * summing up each state size.
+ */
+ for (next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE, i = FIRST_EXTENDED_XFEATURE;
+ i <= feature_nr; i++) {
+ if (!(mask & BIT_ULL(i)))
+ continue;
+
+ offset = xstate_aligns[i] ? ALIGN(next_offset, 64) : next_offset;
+ next_offset += xstate_sizes[i];
+ }
+ return offset;
+}
+
/**
* get_xstate_size() - Calculate an xstate buffer size
* @mask: This bitmap tells which components reserved in the buffer.
@@ -193,8 +225,8 @@ static bool xfeature_is_supervisor(int xfeature_nr)
*/
unsigned int get_xstate_size(u64 mask)
{
- unsigned int size;
- int i, nr;
+ unsigned int offset;
+ int nr;
if (!mask)
return 0;
@@ -213,22 +245,8 @@ unsigned int get_xstate_size(u64 mask)
if (!boot_cpu_has(X86_FEATURE_XSAVES))
return xstate_offsets[nr] + xstate_sizes[nr];
- if ((xfeatures_mask_all & (BIT_ULL(nr + 1) - 1)) == mask)
- return xstate_comp_offsets[nr] + xstate_sizes[nr];
-
- /*
- * With the given mask, no relevant size is found so far. So,
- * calculate it by summing up each state size.
- */
- for (size = FXSAVE_SIZE + XSAVE_HDR_SIZE, i = FIRST_EXTENDED_XFEATURE; i <= nr; i++) {
- if (!(mask & BIT_ULL(i)))
- continue;
-
- if (xstate_aligns[i])
- size = ALIGN(size, 64);
- size += xstate_sizes[i];
- }
- return size;
+ offset = get_xstate_comp_offset(mask, nr);
+ return offset + xstate_sizes[nr];
}
/*
@@ -980,19 +998,29 @@ void fpu__resume_cpu(void)
*/
static void *__raw_xsave_addr(struct fpu *fpu, int xfeature_nr)
{
+ unsigned int offset;
void *xsave;
if (!xfeature_enabled(xfeature_nr)) {
- WARN_ON_FPU(1);
- return NULL;
- }
+ goto not_found;
+ } else if (!fpu) {
+ xsave = &init_fpstate.xsave;
- if (fpu)
+ offset = get_xstate_comp_offset(xfeatures_mask_all, xfeature_nr);
+ if (offset > sizeof(init_fpstate))
+ goto not_found;
+ } else if (!(fpu->state_mask & BIT_ULL(xfeature_nr))) {
+ goto not_found;
+ } else {
xsave = &fpu->state->xsave;
- else
- xsave = &init_fpstate.xsave;
+ offset = get_xstate_comp_offset(fpu->state_mask, xfeature_nr);
+ }
+
+ return xsave + offset;
- return xsave + xstate_comp_offsets[xfeature_nr];
+not_found:
+ WARN_ON_FPU(1);
+ return NULL;
}
/*
* Given the xsave area and a state inside, this function returns the
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 11/26] x86/fpu/xstate: Update the XSTATE context copy function to support dynamic states
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (9 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 10/26] x86/fpu/xstate: Update the XSTATE buffer address finder " Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-10 13:02 ` [PATCH v7 12/26] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state Chang S. Bae
` (14 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
ptrace() and signal return paths use XSTATE context copy functions. They
allow callers to read (or write) XSTATE values in the target's buffer. With
dynamic user states, a component's position in the buffer may vary and the
init fpstate is not always large enough to cover all the states.
Adjust the helpers to find a component's offset correctly. Also, update the
copy loop in the ptrace read path to support dynamic states.
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
---
Changes from v5:
* Updated to ensure xstate_bv aligned with the target.
* Rewrote the xstate copy loop, for the ptrace() read path, in an open
code.
* Adjusted the changelog.
Changes from v3:
* Cleaned up the code change with more comments.
* Removed 'no functional change' in the changelog. (Borislav Petkov)
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
---
arch/x86/kernel/fpu/xstate.c | 30 +++++++++++++++++++++++++-----
1 file changed, 25 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index a6473a632e6e..9e81b906fa78 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1273,6 +1273,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
zerofrom = offsetof(struct xregs_state, extended_state_area);
for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
+ u64 mask = BIT_ULL(i);
/*
* The ptrace buffer is in non-compacted XSAVE format.
* In non-compacted format disabled features still occupy
@@ -1280,7 +1281,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
* compacted init_fpstate. The gap tracking will zero this
* later.
*/
- if (!(xfeatures_mask_uabi() & BIT_ULL(i)))
+ if (!(xfeatures_mask_uabi() & mask))
continue;
/*
@@ -1300,10 +1301,24 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
pkru.pkru = tsk->thread.pkru;
membuf_write(&to, &pkru, sizeof(pkru));
} else {
- copy_feature(header.xfeatures & BIT_ULL(i), &to,
- __raw_xsave_addr(&tsk->thread.fpu, i),
- __raw_xsave_addr(NULL, i),
- xstate_sizes[i]);
+ unsigned int size = xstate_sizes[i];
+ void *from = NULL;
+
+ /*
+ * Copy the xstate if available. Otherwise, copy the
+ * non-zero init states for legacy states (FP and
+ * SSE) or fill zeros.
+ */
+
+ if (header.xfeatures & mask)
+ from = __raw_xsave_addr(&tsk->thread.fpu, i);
+ else if (XFEATURE_MASK_FPSSE & mask)
+ from = __raw_xsave_addr(NULL, i);
+
+ if (from)
+ membuf_write(&to, from, size);
+ else
+ membuf_zero(&to, size);
}
/*
* Keep track of the last copied state in the non-compacted
@@ -1345,6 +1360,8 @@ static int copy_uabi_to_xstate(struct fpu *fpu, const void *kbuf,
if (validate_user_xstate_header(&hdr))
return -EINVAL;
+ hdr.xfeatures &= fpu->state_mask;
+
/* Validate MXCSR when any of the related features is in use */
mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM;
if (hdr.xfeatures & mask) {
@@ -1371,6 +1388,9 @@ static int copy_uabi_to_xstate(struct fpu *fpu, const void *kbuf,
if (hdr.xfeatures & mask) {
void *dst = __raw_xsave_addr(fpu, i);
+ if (!dst)
+ continue;
+
offset = xstate_offsets[i];
size = xstate_sizes[i];
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 12/26] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (10 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 11/26] x86/fpu/xstate: Update the XSTATE context copy function " Chang S. Bae
@ 2021-07-10 13:02 ` Chang S. Bae
2021-07-13 19:13 ` Thiago Macieira
2021-07-10 13:03 ` [PATCH v7 13/26] x86/fpu/xstate: Support ptracer-induced XSTATE buffer expansion Chang S. Bae
` (13 subsequent siblings)
25 siblings, 1 reply; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:02 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
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 defer allocating the large XSAVE buffer until tasks
need 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
xstate-component bitmap format, used by XCR0.
Use this hardware capability to find the right time to expand the XSTATE
buffer. The #NM handler induces the buffer expansion.
Introduce helper functions:
xfd_write() - write IA32_XFD MSR
xfd_read() - read IA32_XFD MSR
xfd_switch() - switch IA32_XFD MSR
xfd_capable() - indicate XFD-capable xfeatures
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
---
Changes from v6:
* Update the #NM handler a little bit.
* Clean up the code comment.
Changes from v5:
* Excluded the access request check here and included the buffer allocation
again in #NM handler. The access request will be dealt in next patch.
* Updated the title. (Dave Hansen)
* Updated the code comment.
Changes from v4:
* Changed to use XFD to support the access request policy. Updated #NM
handler to raise a signal instead of buffer allocation.
* Decoupled XFD from the use of XSAVE compacted format.
* Updated helper functions.
* Updated function descriptions in a proper format.
* Updated some code comments.
Changes from v3:
* Removed 'no functional change' in the changelog. (Borislav Petkov)
Changes from v2:
* Changed to enable XFD only when the compacted format is used.
* Updated the changelog with task->fpu removed. (Borislav Petkov)
Changes from v1:
* Inlined the XFD-induced #NM handling code (Andy Lutomirski)
---
arch/x86/include/asm/cpufeatures.h | 1 +
arch/x86/include/asm/fpu/internal.h | 45 +++++++++++++++++++++++++++--
arch/x86/include/asm/msr-index.h | 2 ++
arch/x86/kernel/cpu/cpuid-deps.c | 1 +
arch/x86/kernel/fpu/xstate.c | 44 ++++++++++++++++++++++++++--
arch/x86/kernel/process.c | 6 ++++
arch/x86/kernel/process_32.c | 2 +-
arch/x86/kernel/process_64.c | 2 +-
arch/x86/kernel/traps.c | 38 ++++++++++++++++++++++++
9 files changed, 135 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d0ce5cfd3ac1..37150b7a8e44 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -277,6 +277,7 @@
#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 263e349ff85a..c9c3d58912ec 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -535,14 +535,55 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
* Misc helper functions:
*/
+/* The Extended Feature Disable (XFD) helpers: */
+
+static inline void xfd_write(u64 value)
+{
+ wrmsrl_safe(MSR_IA32_XFD, value);
+}
+
+static inline u64 xfd_read(void)
+{
+ u64 value;
+
+ rdmsrl_safe(MSR_IA32_XFD, &value);
+ return value;
+}
+
+static inline u64 xfd_capable(void)
+{
+ return xfeatures_mask_user_dynamic;
+}
+
+/**
+ * xfd_switch() - Switches the MSR IA32_XFD context if needed.
+ * @prev: The previous task's struct fpu pointer
+ * @next: The next task's struct fpu pointer
+ */
+static inline void xfd_switch(struct fpu *prev, struct fpu *next)
+{
+ u64 prev_xfd_mask, next_xfd_mask;
+
+ if (!static_cpu_has(X86_FEATURE_XFD) || !xfd_capable())
+ return;
+
+ prev_xfd_mask = prev->state_mask & xfd_capable();
+ next_xfd_mask = next->state_mask & xfd_capable();
+
+ if (unlikely(prev_xfd_mask != next_xfd_mask))
+ xfd_write(xfd_capable() ^ next_xfd_mask);
+}
+
/*
* Delay loading of the complete FPU state until the return to userland.
* PKRU is handled separately.
*/
-static inline void switch_fpu_finish(struct fpu *new_fpu)
+static inline void switch_fpu_finish(struct fpu *old_fpu, struct fpu *new_fpu)
{
- if (cpu_feature_enabled(X86_FEATURE_FPU))
+ if (cpu_feature_enabled(X86_FEATURE_FPU)) {
set_thread_flag(TIF_NEED_FPU_LOAD);
+ xfd_switch(old_fpu, new_fpu);
+ }
}
#endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a7c413432b33..eac0cfd9210b 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -626,6 +626,8 @@
#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/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index defda61f372d..7f891d2eb52e 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -75,6 +75,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_SGX_LC, X86_FEATURE_SGX },
{ X86_FEATURE_SGX1, X86_FEATURE_SGX },
{ X86_FEATURE_SGX2, X86_FEATURE_SGX1 },
+ { X86_FEATURE_XFD, X86_FEATURE_XSAVE },
{}
};
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 9e81b906fa78..2fb08d1a96e6 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -182,6 +182,26 @@ static bool xfeature_is_supervisor(int xfeature_nr)
return ecx & 1;
}
+/**
+ * xfd_supported() - Check if the feature supports Extended Feature Disable (XFD).
+ * @feature_nr: The feature number.
+ *
+ * Returns: True if supported; otherwise, false.
+ */
+static bool xfd_supported(int feature_nr)
+{
+ u32 eax, ebx, ecx, edx;
+
+ if (!boot_cpu_has(X86_FEATURE_XFD))
+ return false;
+
+ /*
+ * If state component 'i' supports it, ECX[2] return 1; otherwise, 0.
+ */
+ cpuid_count(XSTATE_CPUID, feature_nr, &eax, &ebx, &ecx, &edx);
+ return ecx & 4;
+}
+
/**
* get_xstate_comp_offset() - Find the feature's offset in the compacted
* format.
@@ -274,6 +294,9 @@ void fpu__init_cpu_xstate(void)
wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
+
+ if (boot_cpu_has(X86_FEATURE_XFD))
+ xfd_write(xfd_capable());
}
static bool xfeature_enabled(enum xfeature xfeature)
@@ -473,8 +496,9 @@ 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)) ? "dynamic" : "default");
}
}
@@ -920,6 +944,16 @@ void __init fpu__init_system_xstate(void)
/* Do not support the dynamically allocated buffer yet. */
xfeatures_mask_user_dynamic = 0;
+ for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
+ u64 feature_mask = BIT_ULL(i);
+
+ if (!(xfeatures_mask_uabi() & feature_mask))
+ continue;
+
+ if (xfd_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();
@@ -981,6 +1015,12 @@ void fpu__resume_cpu(void)
wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
+
+ if (boot_cpu_has(X86_FEATURE_XFD)) {
+ u64 fpu_xfd_mask = current->thread.fpu.state_mask & xfd_capable();
+
+ xfd_write(xfd_capable() ^ fpu_xfd_mask);
+ }
}
/**
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 534b9fb7e7ee..b85fa499f195 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -97,6 +97,12 @@ void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
*size = get_xstate_config(XSTATE_MIN_SIZE);
}
+void arch_release_task_struct(struct task_struct *task)
+{
+ if (cpu_feature_enabled(X86_FEATURE_FPU))
+ free_xstate_buffer(&task->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 ec0d836a13b1..41c9855158d6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -620,7 +620,7 @@ __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 a58800973aed..f45b2cefd6cf 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1112,6 +1112,44 @@ DEFINE_IDTENTRY(exc_device_not_available)
{
unsigned long cr0 = read_cr0();
+ if (boot_cpu_has(X86_FEATURE_XFD)) {
+ u64 xfd_err;
+
+ rdmsrl_safe(MSR_IA32_XFD_ERR, &xfd_err);
+ wrmsrl_safe(MSR_IA32_XFD_ERR, 0);
+
+ if (xfd_err) {
+ u64 xfd_event = xfd_err & xfd_capable();
+
+ if (WARN_ON(!xfd_event)) {
+ /*
+ * Unexpected event is raised. But update XFD state to
+ * unblock the task.
+ */
+ xfd_write(xfd_read() & ~xfd_err);
+ } else {
+ struct fpu *fpu = ¤t->thread.fpu;
+ int err = -1;
+
+ /*
+ * Make sure not in interrupt context as handling a
+ * trap from userspace.
+ */
+ if (!WARN_ON(in_interrupt())) {
+ err = alloc_xstate_buffer(fpu, xfd_event);
+ if (!err)
+ xfd_write((fpu->state_mask & xfd_capable()) ^
+ xfd_capable());
+ }
+
+ /* Raise a signal when it failed to handle. */
+ if (err)
+ force_sig(SIGSEGV);
+ }
+ return;
+ }
+ }
+
#ifdef CONFIG_MATH_EMULATION
if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) {
struct math_emu_info info = { };
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* Re: [PATCH v7 12/26] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state
2021-07-10 13:02 ` [PATCH v7 12/26] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state Chang S. Bae
@ 2021-07-13 19:13 ` Thiago Macieira
2021-07-17 15:47 ` Bae, Chang Seok
0 siblings, 1 reply; 31+ messages in thread
From: Thiago Macieira @ 2021-07-13 19:13 UTC (permalink / raw)
To: Chang S. Bae
Cc: bp, luto, tglx, mingo, x86, len.brown, dave.hansen, jing2.liu,
ravi.v.shankar, linux-kernel
On Saturday, 10 July 2021 06:02:59 PDT Chang S. Bae wrote:
> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index a58800973aed..f45b2cefd6cf 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -1112,6 +1112,44 @@ DEFINE_IDTENTRY(exc_device_not_available)
[cut]
> + /* Raise a signal when it failed to handle.
> */ + if (err)
> + force_sig(SIGSEGV);
> + }
> + return;
Hello Chang
Can I make a suggestion that you send a different signal than SIGSEGV for the
failure of unauthorised instructions? I would recommend SIGILL. Additionally,
please consider a new ILL_* constant for the si_code field.
I have multiple reasons for that:
1) the XFD failure is not a memory issue, so SIGSEGV is not really
appropriate, despite coming from an #NM interrupt
2) SIGILL is sent for the AMX instructions in other circumstances, due to CPU
#UD, notably:
- running on a CPU without AMX support
- running under an OS that did not enable the AMX state in XCR0 (like Linux
before this patch series)
When a developer is debugging code and sees a SIGILL on a valid instruction
stream in disassembly, they know they've got to code they should never have
got to, bypassing CPU checks. Forgetting to ask for permission is now a
variant of that case.
3) the very first AMX instruction to cause the #NM is likely going to be an
LDTILECFG or TILELOADD, which are memory-related instructions, so may #GP for
using bad pointers (and LDTILECFG can #GP for bad tile configurations).
Knowing that the issue was the instruction itself instead of the pointer or
data being loaded is going to come in handy.
4) SIGSEGV will also be sent for another reason by the kernel. Your cover
message had:
> 4. Applications touching AMX without permission results in process exit.
>
> Armed XFD results in #NM, results in SIGSEGV, typically resulting in
> process exit.
> 6. NM handler allocation failure results in process exit.
>
> If the #NM handler can not allocate the 8KB buffer, the task will
> receive a SIGSEGV at the instruction that took the #NM fault, typically
> resulting in process exit.
Knowing that it was caused by reaching code that shouldn't have been reached,
instead of an OOM issue, is handy.
Do note that this SIGSEGV for allocation is unlikely to happen. If the kernel
is under memory pressure, the OOM killer will probably kick in and may kill
(SIGKILL) this process instead. But at least #6 is a legitimate memory issue.
On the same topic, is there a way to save this state in a core dump? The FS
and GS bases would also be very handy.
--
Thiago Macieira - thiago.macieira (AT) intel.com
Software Architect - Intel DPG Cloud Engineering
^ permalink raw reply [flat|nested] 31+ messages in thread
* Re: [PATCH v7 12/26] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state
2021-07-13 19:13 ` Thiago Macieira
@ 2021-07-17 15:47 ` Bae, Chang Seok
0 siblings, 0 replies; 31+ messages in thread
From: Bae, Chang Seok @ 2021-07-17 15:47 UTC (permalink / raw)
To: Macieira, Thiago
Cc: Borislav Petkov, Lutomirski, Andy, Thomas Gleixner, Ingo Molnar,
the arch/x86 maintainers, Brown, Len, Hansen, Dave, Liu, Jing2,
Shankar, Ravi V, linux-kernel
On Jul 13, 2021, at 12:13, Macieira, Thiago <thiago.macieira@intel.com> wrote:
> On Saturday, 10 July 2021 06:02:59 PDT Chang S. Bae wrote:
>>
>> + /* Raise a signal when it failed to handle.
>> */ + if (err)
>> + force_sig(SIGSEGV);
>> + }
>> + return;
>
> Can I make a suggestion that you send a different signal than SIGSEGV for the
> failure of unauthorised instructions? I would recommend SIGILL. Additionally,
> please consider a new ILL_* constant for the si_code field.
Applied on v8 [1].
> On the same topic, is there a way to save this state in a core dump? The FS
> and GS bases would also be very handy.
According to [2],
“Exporting the extended register state through ptrace and core-dump
(NT_X86_XSTATE note) interfaces will be same"
Also, AMX state was found as I retrieved from my core-dump image.
Thanks,
Chang
[1] https://lore.kernel.org/lkml/20210717152903.7651-13-chang.seok.bae@intel.com/
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/x86/include/asm/user.h#n26
^ permalink raw reply [flat|nested] 31+ messages in thread
* [PATCH v7 13/26] x86/fpu/xstate: Support ptracer-induced XSTATE buffer expansion
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (11 preceding siblings ...)
2021-07-10 13:02 ` [PATCH v7 12/26] x86/fpu/xstate: Use feature disable (XFD) to protect dynamic user state Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 14/26] x86/arch_prctl: Create ARCH_SET_XSTATE_ENABLE/ARCH_GET_XSTATE_ENABLE Chang S. Bae
` (12 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
ptrace() may update XSTATE data before the target task has taken an XFD
fault and expanded the XSTATE buffer. Detect this case and allocate a
sufficient buffer to support the request. Also, disable the (now
unnecessary) associated first-use fault.
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
---
Changes from v5:
* Adjusted to use 'tmpbuf' for the new base code.
Changes from v4:
* Improved the condition check for the expansion.
* Simplified the XSTATE_BV retrieval.
* Updated the code comment.
Changes from v3:
* Removed 'no functional changes' in the changelog. (Borislav Petkov)
Changes from v2:
* Updated the changelog with task->fpu removed. (Borislav Petkov)
* Updated the code comments.
---
arch/x86/kernel/fpu/regset.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 73d7d7b489fe..244e672c3e3d 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -163,6 +163,30 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
}
}
+ /*
+ * When a ptracer attempts to write any dynamic user state in the
+ * target buffer but not sufficiently allocated, it dynamically
+ * expands the buffer.
+ *
+ * Check if the expansion is possibly needed.
+ */
+ if (xfeatures_mask_user_dynamic &&
+ ((fpu->state_mask & xfeatures_mask_user_dynamic) != xfeatures_mask_user_dynamic)) {
+ u64 state_mask;
+
+ /* Retrieve XSTATE_BV. */
+ memcpy(&state_mask, (kbuf ?: tmpbuf) + offsetof(struct xregs_state, header),
+ sizeof(u64));
+
+ /* Expand the xstate buffer based on the XSTATE_BV. */
+ state_mask &= xfeatures_mask_user_dynamic;
+ if (state_mask) {
+ ret = alloc_xstate_buffer(fpu, state_mask);
+ if (ret)
+ goto out;
+ }
+ }
+
fpu_force_restore(fpu);
ret = copy_uabi_from_kernel_to_xstate(fpu, kbuf ?: tmpbuf);
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 14/26] x86/arch_prctl: Create ARCH_SET_XSTATE_ENABLE/ARCH_GET_XSTATE_ENABLE
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (12 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 13/26] x86/fpu/xstate: Support ptracer-induced XSTATE buffer expansion Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 15/26] x86/fpu/xstate: Support both legacy and expanded signal XSTATE size Chang S. Bae
` (11 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
arch_prctl(ARCH_SET_XSTATE_ENABLE)
Some XSTATE features, such as AMX, are unavailable to applications
until that process explicitly requests them via this call. Requests can
be made for any number of valid user XSTATEs in a single call. This
call is intended to be invoked very early in process initialization. A
forked child inherits access, but permission is reset upon exec. There
is no concept of un-requesting XSTATE access.
Return codes:
0: success (including repeated calls)
EINVAL: no hardware feature for the request
EBUSY: error in updating all threads in the process
arch_prctl(ARCH_GET_XSTATE_ENABLE)
Return the bitmask of permitted user XSTATE features.
The permission is checked at every XSTATE buffer expansion: e.g.
XFD-induced #NM event, and ptracer's XSTATE injection. When no permission
is found, inform userspace via SIGSEGV or with error code.
The notion of granted permission is broadcast to all threads in a process.
(This approach follows the PR_SET_FP_MODE prctl(2) implementation.)
Detect a fork race by aborting and returning -EBUSY if the number of
threads at the end of call changed.
[ An alternative implementation would not save the permission bitmap in
every task. But instead would extend the per-process signal data, and that
would not be subject to this race. ]
Rename the third argument for do_arch_prctl_common() to reflect its generic
use.
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
---
Changes from v6:
* Add state bitmap param to proposed syscall. (Thiago Macieira)
* Add companion syscall to return the current permission bitmap.
* Update the ptrace path to return EFAULT when no permission to write
XTILEDATA.
* Update do_arch_prctl_common().
Changes from v5:
* Switched to per-process permission. (Based on the discussion on LKML)
---
arch/x86/include/asm/fpu/types.h | 8 ++++
arch/x86/include/asm/fpu/xstate.h | 9 ++++
arch/x86/include/asm/proto.h | 2 +-
arch/x86/include/uapi/asm/prctl.h | 3 ++
arch/x86/kernel/fpu/regset.c | 17 +++++---
arch/x86/kernel/fpu/xstate.c | 68 +++++++++++++++++++++++++++++++
arch/x86/kernel/process.c | 8 +++-
arch/x86/kernel/process_64.c | 6 +++
arch/x86/kernel/traps.c | 8 ++--
9 files changed, 117 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index c0192e16cadb..03160a1a79ad 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -336,6 +336,14 @@ struct fpu {
*/
unsigned long avx512_timestamp;
+ /*
+ * @state_perm:
+ *
+ * The bitmap indicates the permission of using some state
+ * components which are dynamically stored in the per-task buffer.
+ */
+ u64 dynamic_state_perm;
+
/*
* @state_mask:
*
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 45735441fbe8..f33ad441e42f 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -149,6 +149,15 @@ void *get_xsave_addr(struct fpu *fpu, int xfeature_nr);
unsigned int get_xstate_size(u64 mask);
int alloc_xstate_buffer(struct fpu *fpu, u64 mask);
void free_xstate_buffer(struct fpu *fpu);
+
+long set_process_xstate_perm(struct task_struct *tsk, u64 state_perm);
+void reset_task_xstate_perm(struct task_struct *tsk);
+static inline long get_task_xstate_perm(struct task_struct *tsk)
+{
+ return (xfeatures_mask_uabi() & ~xfeatures_mask_user_dynamic) |
+ tsk->thread.fpu.dynamic_state_perm;
+}
+
int xfeature_size(int xfeature_nr);
int copy_uabi_from_kernel_to_xstate(struct fpu *fpu, const void *kbuf);
int copy_sigframe_from_user_to_xstate(struct fpu *fpu, const void __user *ubuf);
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 8c5d1910a848..feed36d44d04 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -40,6 +40,6 @@ void x86_report_nx(void);
extern int reboot_force;
long do_arch_prctl_common(struct task_struct *task, int option,
- unsigned long cpuid_enabled);
+ unsigned long arg2);
#endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 5a6aac9fa41f..5fb1393a289c 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -10,6 +10,9 @@
#define ARCH_GET_CPUID 0x1011
#define ARCH_SET_CPUID 0x1012
+#define ARCH_SET_XSTATE_ENABLE 0x1021
+#define ARCH_GET_XSTATE_ENABLE 0x1022
+
#define ARCH_MAP_VDSO_X32 0x2001
#define ARCH_MAP_VDSO_32 0x2002
#define ARCH_MAP_VDSO_64 0x2003
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 244e672c3e3d..ee71ffd7c221 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -166,22 +166,27 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
/*
* When a ptracer attempts to write any dynamic user state in the
* target buffer but not sufficiently allocated, it dynamically
- * expands the buffer.
+ * expands the buffer if permitted.
*
* Check if the expansion is possibly needed.
*/
if (xfeatures_mask_user_dynamic &&
((fpu->state_mask & xfeatures_mask_user_dynamic) != xfeatures_mask_user_dynamic)) {
- u64 state_mask;
+ u64 state_mask, dynstate_mask;
/* Retrieve XSTATE_BV. */
memcpy(&state_mask, (kbuf ?: tmpbuf) + offsetof(struct xregs_state, header),
sizeof(u64));
- /* Expand the xstate buffer based on the XSTATE_BV. */
- state_mask &= xfeatures_mask_user_dynamic;
- if (state_mask) {
- ret = alloc_xstate_buffer(fpu, state_mask);
+ /* Check the permission and expand the xstate buffer. */
+ dynstate_mask = state_mask & xfeatures_mask_user_dynamic;
+ if (dynstate_mask) {
+ if ((dynstate_mask & fpu->dynamic_state_perm) != dynstate_mask) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret = alloc_xstate_buffer(fpu, dynstate_mask);
if (ret)
goto out;
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 2fb08d1a96e6..cff0aa82ef53 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -961,6 +961,7 @@ void __init fpu__init_system_xstate(void)
goto out_disable;
/* Make sure init_task does not include the dynamic user states. */
+ current->thread.fpu.dynamic_state_perm = 0;
current->thread.fpu.state_mask = (xfeatures_mask_all & ~xfeatures_mask_user_dynamic);
/*
@@ -1233,6 +1234,73 @@ int alloc_xstate_buffer(struct fpu *fpu, u64 mask)
return 0;
}
+/**
+ * set_process_xstate_perm() - Set a per-process permission to use dynamic
+ * user xstates.
+ * @task: A struct task_struct * pointer
+ * @state_perm: A bitmap to indicate which state's permission to be set.
+ * Return: 0 if successful; otherwise, error code.
+ */
+long set_process_xstate_perm(struct task_struct *tsk, u64 state_perm)
+{
+ u64 req_dynstate_perm, old_dynstate_perm;
+ struct task_struct *t;
+ int nr_threads = 0;
+
+ if (!boot_cpu_has(X86_FEATURE_FPU))
+ return -EINVAL;
+
+ if (state_perm & ~xfeatures_mask_uabi())
+ return -EINVAL;
+
+ req_dynstate_perm = state_perm & xfeatures_mask_user_dynamic;
+ if (!req_dynstate_perm)
+ return 0;
+
+ old_dynstate_perm = tsk->thread.fpu.dynamic_state_perm;
+
+ for_each_thread(tsk, t) {
+ t->thread.fpu.dynamic_state_perm |= req_dynstate_perm;
+ nr_threads++;
+ }
+
+ if (nr_threads != tsk->signal->nr_threads) {
+ for_each_thread(tsk, t)
+ t->thread.fpu.dynamic_state_perm = old_dynstate_perm;
+ pr_err("x86/fpu: ARCH_XSTATE_PERM failed as thread number mismatched.\n");
+ return -EBUSY;
+ }
+ return 0;
+}
+
+/**
+ * reset_task_xstate_perm() - Reset a task's permission to use dynamic user
+ * xstates.
+ *
+ * It is expected to call at exec in which one task runs in a process.
+ *
+ * @task: A struct task_struct * pointer
+ */
+void reset_task_xstate_perm(struct task_struct *tsk)
+{
+ struct fpu *fpu = &tsk->thread.fpu;
+
+ if (!xfeatures_mask_user_dynamic)
+ return;
+
+ WARN_ON(tsk->signal->nr_threads > 1);
+
+ fpu->state_mask = (xfeatures_mask_all & ~xfeatures_mask_user_dynamic);
+ free_xstate_buffer(fpu);
+ fpu->state = &fpu->__default_state;
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
+ fpstate_init_xstate(&fpu->state->xsave, fpu->state_mask);
+
+ xfd_write(xfd_capable() ^ (fpu->state_mask & xfd_capable()));
+
+ fpu->dynamic_state_perm = 0;
+}
+
static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
void *init_xstate, unsigned int size)
{
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b85fa499f195..e39fbaca536a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -1012,13 +1012,17 @@ unsigned long get_wchan(struct task_struct *p)
}
long do_arch_prctl_common(struct task_struct *task, int option,
- unsigned long cpuid_enabled)
+ unsigned long arg2)
{
switch (option) {
case ARCH_GET_CPUID:
return get_cpuid_mode();
case ARCH_SET_CPUID:
- return set_cpuid_mode(task, cpuid_enabled);
+ return set_cpuid_mode(task, arg2);
+ case ARCH_SET_XSTATE_ENABLE:
+ return set_process_xstate_perm(task, arg2);
+ case ARCH_GET_XSTATE_ENABLE:
+ return get_task_xstate_perm(task);
}
return -EINVAL;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 41c9855158d6..065ea28328b9 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -678,6 +678,9 @@ void set_personality_64bit(void)
so it's not too bad. The main problem is just that
32bit children are affected again. */
current->personality &= ~READ_IMPLIES_EXEC;
+
+ /* Make sure to reset the dynamic state permission. */
+ reset_task_xstate_perm(current);
}
static void __set_personality_x32(void)
@@ -723,6 +726,9 @@ void set_personality_ia32(bool x32)
/* Make sure to be in 32bit mode */
set_thread_flag(TIF_ADDR32);
+ /* Make sure to reset the dynamic state permission. */
+ reset_task_xstate_perm(current);
+
if (x32)
__set_personality_x32();
else
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index f45b2cefd6cf..88ad28c79dc2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1132,10 +1132,12 @@ DEFINE_IDTENTRY(exc_device_not_available)
int err = -1;
/*
- * Make sure not in interrupt context as handling a
- * trap from userspace.
+ * Make sure that dynamic buffer expansion is permitted
+ * and not in interrupt context as handling a trap from
+ * userspace.
*/
- if (!WARN_ON(in_interrupt())) {
+ if (((xfd_event & fpu->dynamic_state_perm) == xfd_event) &&
+ !WARN_ON(in_interrupt())) {
err = alloc_xstate_buffer(fpu, xfd_event);
if (!err)
xfd_write((fpu->state_mask & xfd_capable()) ^
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 15/26] x86/fpu/xstate: Support both legacy and expanded signal XSTATE size
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (13 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 14/26] x86/arch_prctl: Create ARCH_SET_XSTATE_ENABLE/ARCH_GET_XSTATE_ENABLE Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 16/26] x86/fpu/xstate: Adjust the XSAVE feature table to address gaps in state component numbers Chang S. Bae
` (10 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Prepare to support two XSTATE sizes on the signal stack -- legacy and
expanded. Legacy programs have not requested access to AMX (or later
features), and the XSTATE on their signal stack can include up through
AVX-512.
Programs that request access to AVX (and/or later features) will have an
uncompressed XSTATE that includes those features. If such program that also
use the sigaltstack, they must assure that their sigaltstack is large
enough to handle that full XSTATE format. (This is most easily done by
using signal.h from glibc 2.34 or later)
Introduce a new XSTATE size variable for the legacy stack and some helpers.
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
---
Changes from v6:
* Massage the code comments.
Changes form v5:
* Added as a new patch.
---
arch/x86/include/asm/fpu/internal.h | 23 +++++++++--
arch/x86/include/asm/fpu/xstate.h | 3 +-
arch/x86/kernel/fpu/init.c | 1 +
arch/x86/kernel/fpu/signal.c | 63 ++++++++++++++++++++---------
arch/x86/kernel/fpu/xstate.c | 25 +++++++++++-
5 files changed, 89 insertions(+), 26 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index c9c3d58912ec..a1ccef6d4520 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -337,15 +337,30 @@ static inline void os_xrstor(struct xregs_state *xstate, u64 mask)
*/
static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
{
+ u32 lmask, hmask;
+ u64 mask;
+ int err;
+
/*
* Include the features which are not xsaved/rstored by the kernel
* internally, e.g. PKRU. That's user space ABI and also required
* to allow the signal handler to modify PKRU.
*/
- u64 mask = xfeatures_mask_uabi();
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
+ mask = xfeatures_mask_uabi();
+
+ /*
+ * Exclude dynamic user states for non-opt-in threads.
+ */
+ if (xfeatures_mask_user_dynamic) {
+ struct fpu *fpu = ¤t->thread.fpu;
+
+ mask &= fpu->dynamic_state_perm ?
+ fpu->state_mask :
+ ~xfeatures_mask_user_dynamic;
+ }
+
+ lmask = mask;
+ hmask = mask >> 32;
/*
* Clear the xsave header first, so that reserved fields are
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index f33ad441e42f..6051fd6a749f 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -139,7 +139,8 @@ extern void __init update_regset_xstate_info(unsigned int size,
enum xstate_config {
XSTATE_MIN_SIZE,
XSTATE_MAX_SIZE,
- XSTATE_USER_SIZE
+ XSTATE_USER_SIZE,
+ XSTATE_USER_MINSIG_SIZE,
};
extern unsigned int get_xstate_config(enum xstate_config cfg);
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 3e4e14ca723b..acbd3da0e022 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -210,6 +210,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
set_xstate_config(XSTATE_MIN_SIZE, xstate_size);
set_xstate_config(XSTATE_MAX_SIZE, xstate_size);
set_xstate_config(XSTATE_USER_SIZE, xstate_size);
+ set_xstate_config(XSTATE_USER_MINSIG_SIZE, xstate_size);
}
/* Legacy code to initialize eager fpu mode. */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index f70f84d53442..78696b412b56 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -15,9 +15,26 @@
#include <asm/sigframe.h>
#include <asm/trace/fpu.h>
+/*
+ * Record the signal xstate size and feature bits. Exclude dynamic user
+ * states. See fpu__init_prepare_fx_sw_frame(). The opt-in tasks will
+ * dynamically adjust the data.
+ */
static struct _fpx_sw_bytes fx_sw_reserved __ro_after_init;
static struct _fpx_sw_bytes fx_sw_reserved_ia32 __ro_after_init;
+static unsigned int current_sig_xstate_size(void)
+{
+ return current->thread.fpu.dynamic_state_perm ?
+ get_xstate_config(XSTATE_USER_SIZE) :
+ get_xstate_config(XSTATE_USER_MINSIG_SIZE);
+}
+
+static inline int extend_sig_xstate_size(unsigned int size)
+{
+ return use_xsave() ? size + FP_XSTATE_MAGIC2_SIZE : size;
+}
+
/*
* Check for the presence of extended state information in the
* user fpstate pointer in the sigcontext.
@@ -36,7 +53,7 @@ static inline int check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
/* Check for the first magic field and other error scenarios. */
if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
fx_sw->xstate_size < min_xstate_size ||
- fx_sw->xstate_size > get_xstate_config(XSTATE_USER_SIZE) ||
+ fx_sw->xstate_size > current_sig_xstate_size() ||
fx_sw->xstate_size > fx_sw->extended_size)
goto setfx;
@@ -94,20 +111,32 @@ static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
{
+ unsigned int current_xstate_size = current_sig_xstate_size();
struct xregs_state __user *x = buf;
- struct _fpx_sw_bytes *sw_bytes;
+ struct _fpx_sw_bytes sw_bytes;
u32 xfeatures;
int err;
- /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
- sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
- err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
+ /*
+ * Setup the bytes not touched by the [f]xsave and reserved for SW.
+ *
+ * Use the recorded values if it matches with the current task. Otherwise,
+ * adjust it.
+ */
+ sw_bytes = ia32_frame ? fx_sw_reserved_ia32 : fx_sw_reserved;
+ if (sw_bytes.xstate_size != current_xstate_size) {
+ unsigned int default_xstate_size = sw_bytes.xstate_size;
+
+ sw_bytes.xfeatures = xfeatures_mask_uabi();
+ sw_bytes.xstate_size = current_xstate_size;
+ sw_bytes.extended_size += (current_xstate_size - default_xstate_size);
+ }
+ err = __copy_to_user(&x->i387.sw_reserved, &sw_bytes, sizeof(sw_bytes));
if (!use_xsave())
return err;
- err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *)(buf + get_xstate_config(XSTATE_USER_SIZE)));
+ err |= __put_user(FP_XSTATE_MAGIC2, (__u32 __user *)(buf + current_xstate_size));
/*
* Read the xfeatures which we copied (directly from the cpu or
@@ -144,7 +173,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
else
err = fnsave_to_user_sigframe((struct fregs_state __user *) buf);
- if (unlikely(err) && __clear_user(buf, get_xstate_config(XSTATE_USER_SIZE)))
+ if (unlikely(err) && __clear_user(buf, current_sig_xstate_size()))
err = -EFAULT;
return err;
}
@@ -205,7 +234,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
fpregs_unlock();
if (ret) {
- if (!fault_in_pages_writeable(buf_fx, get_xstate_config(XSTATE_USER_SIZE)))
+ if (!fault_in_pages_writeable(buf_fx, current_sig_xstate_size()))
goto retry;
return -EFAULT;
}
@@ -418,19 +447,13 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
fpregs_unlock();
return ret;
}
-static inline int xstate_sigframe_size(void)
-{
- int xstate_size = get_xstate_config(XSTATE_USER_SIZE);
-
- return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
-}
/*
* Restore FPU state from a sigframe:
*/
int fpu__restore_sig(void __user *buf, int ia32_frame)
{
- unsigned int size = xstate_sigframe_size();
+ unsigned int size = extend_sig_xstate_size(current_sig_xstate_size());
struct fpu *fpu = ¤t->thread.fpu;
void __user *buf_fx = buf;
bool ia32_fxstate = false;
@@ -477,7 +500,7 @@ unsigned long
fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
unsigned long *buf_fx, unsigned long *size)
{
- unsigned long frame_size = xstate_sigframe_size();
+ unsigned long frame_size = extend_sig_xstate_size(current_sig_xstate_size());
*buf_fx = sp = round_down(sp - frame_size, 64);
if (ia32_frame && use_fxsr()) {
@@ -492,7 +515,7 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
unsigned long fpu__get_fpstate_size(void)
{
- unsigned long ret = xstate_sigframe_size();
+ unsigned long ret = extend_sig_xstate_size(get_xstate_config(XSTATE_USER_SIZE));
/*
* This space is needed on (most) 32-bit kernels, or when a 32-bit
@@ -517,12 +540,12 @@ unsigned long fpu__get_fpstate_size(void)
*/
void fpu__init_prepare_fx_sw_frame(void)
{
- int xstate_size = get_xstate_config(XSTATE_USER_SIZE);
+ int xstate_size = get_xstate_config(XSTATE_USER_MINSIG_SIZE);
int ext_size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
fx_sw_reserved.extended_size = ext_size;
- fx_sw_reserved.xfeatures = xfeatures_mask_uabi();
+ fx_sw_reserved.xfeatures = xfeatures_mask_uabi() & ~xfeatures_mask_user_dynamic;
fx_sw_reserved.xstate_size = xstate_size;
if (IS_ENABLED(CONFIG_IA32_EMULATION) ||
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index cff0aa82ef53..b8a8e8e38dad 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -94,10 +94,13 @@ static bool xstate_aligns[XFEATURE_MAX] __ro_after_init =
* contains all the enabled state components.
* @user_size: The size of user-space buffer for signal and
* ptrace frames, in the non-compacted format.
+ * @user_minsig_size: The non-compacted legacy xstate size for signal.
+ * Legacy programs do not request to access dynamic
+ * states.
*/
struct fpu_xstate_buffer_config {
unsigned int min_size, max_size;
- unsigned int user_size;
+ unsigned int user_size, user_minsig_size;
};
static struct fpu_xstate_buffer_config buffer_config __ro_after_init;
@@ -111,6 +114,8 @@ unsigned int get_xstate_config(enum xstate_config cfg)
return buffer_config.max_size;
case XSTATE_USER_SIZE:
return buffer_config.user_size;
+ case XSTATE_USER_MINSIG_SIZE:
+ return buffer_config.user_minsig_size;
default:
return 0;
}
@@ -128,6 +133,9 @@ void set_xstate_config(enum xstate_config cfg, unsigned int value)
break;
case XSTATE_USER_SIZE:
buffer_config.user_size = value;
+ break;
+ case XSTATE_USER_MINSIG_SIZE:
+ buffer_config.user_minsig_size = value;
}
}
@@ -859,6 +867,21 @@ static int __init init_xstate_size(void)
* User space is always in standard format.
*/
set_xstate_config(XSTATE_USER_SIZE, xsave_size);
+
+ /*
+ * The minimum signal xstate size is for non-opt-in user threads
+ * that do not access dynamic states.
+ */
+ if (xfeatures_mask_user_dynamic) {
+ int nr = fls64(xfeatures_mask_uabi() & ~xfeatures_mask_user_dynamic) - 1;
+ unsigned int size, offset, ecx, edx;
+
+ cpuid_count(XSTATE_CPUID, nr, &size, &offset, &ecx, &edx);
+ set_xstate_config(XSTATE_USER_MINSIG_SIZE, offset + size);
+ } else {
+ set_xstate_config(XSTATE_USER_MINSIG_SIZE, xsave_size);
+ }
+
return 0;
}
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 16/26] x86/fpu/xstate: Adjust the XSAVE feature table to address gaps in state component numbers
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (14 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 15/26] x86/fpu/xstate: Support both legacy and expanded signal XSTATE size Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 17/26] x86/fpu/xstate: Disable XSTATE support if an inconsistent state is detected Chang S. Bae
` (9 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
At compile-time xfeatures_mask_all includes all possible XCR0 features. At
run-time fpu__init_system_xstate() clears features in xfeatures_mask_all
that are not enabled in CPUID. It does this by looping through all possible
XCR0 features.
Update the code to handle the possibility that there will be gaps in the
XCR0 feature bit numbers.
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
---
Changes from v5:
* Folded a few lines.
Changes from v4:
* Simplified the implementation. (Thomas Gleixner)
* Updated the patch title accordingly.
Changes from v1:
* Rebased on the upstream kernel (5.10)
---
arch/x86/kernel/fpu/xstate.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index b8a8e8e38dad..353125a18274 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -43,18 +43,17 @@ static const char *xfeature_names[] =
"unknown xstate feature" ,
};
-static short xsave_cpuid_features[] __initdata = {
- X86_FEATURE_FPU,
- X86_FEATURE_XMM,
- X86_FEATURE_AVX,
- X86_FEATURE_MPX,
- X86_FEATURE_MPX,
- X86_FEATURE_AVX512F,
- X86_FEATURE_AVX512F,
- X86_FEATURE_AVX512F,
- X86_FEATURE_INTEL_PT,
- X86_FEATURE_PKU,
- X86_FEATURE_ENQCMD,
+static unsigned short xsave_cpuid_features[] __initdata = {
+ [XFEATURE_SSE] = X86_FEATURE_XMM,
+ [XFEATURE_YMM] = X86_FEATURE_AVX,
+ [XFEATURE_BNDREGS] = X86_FEATURE_MPX,
+ [XFEATURE_BNDCSR] = X86_FEATURE_MPX,
+ [XFEATURE_OPMASK] = X86_FEATURE_AVX512F,
+ [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F,
+ [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F,
+ [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT,
+ [XFEATURE_PKRU] = X86_FEATURE_PKU,
+ [XFEATURE_PASID] = X86_FEATURE_ENQCMD,
};
/*
@@ -955,7 +954,8 @@ void __init fpu__init_system_xstate(void)
* Clear XSAVE features that are disabled in the normal CPUID.
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
- if (!boot_cpu_has(xsave_cpuid_features[i]))
+ if (((i == 0) || xsave_cpuid_features[i]) &&
+ !boot_cpu_has(xsave_cpuid_features[i]))
xfeatures_mask_all &= ~BIT_ULL(i);
}
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 17/26] x86/fpu/xstate: Disable XSTATE support if an inconsistent state is detected
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (15 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 16/26] x86/fpu/xstate: Adjust the XSAVE feature table to address gaps in state component numbers Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 18/26] x86/cpufeatures/amx: Enumerate Advanced Matrix Extension (AMX) feature bits Chang S. Bae
` (8 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
The kernel has a sanity check between two methods to calculate XSTATE size.
In the unlikely event that they disagree, disable the use of XSTATE.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
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
---
Changes from v4:
* Added as a new patch. (Thomas Gleixner)
---
arch/x86/kernel/fpu/xstate.c | 40 ++++++++++++++++++++++++------------
1 file changed, 27 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 353125a18274..eda70bdca45c 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -654,11 +654,11 @@ static void __xstate_dump_leaves(void)
} while (0)
#define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \
- if ((nr == nr_macro) && \
- WARN_ONCE(sz != sizeof(__struct), \
- "%s: struct is %zu bytes, cpu state %d bytes\n", \
- __stringify(nr_macro), sizeof(__struct), sz)) { \
+ if ((nr == nr_macro) && (sz != sizeof(__struct))) { \
+ pr_err("%s: struct is %zu bytes, cpu state %d bytes\n", \
+ __stringify(nr_macro), sizeof(__struct), sz); \
__xstate_dump_leaves(); \
+ return -EINVAL; \
} \
} while (0)
@@ -667,7 +667,7 @@ static void __xstate_dump_leaves(void)
* that our software representation matches what the CPU
* tells us about the state's size.
*/
-static void check_xstate_against_struct(int nr)
+static int check_xstate_against_struct(int nr)
{
/*
* Ask the CPU for the size of the state.
@@ -695,9 +695,12 @@ static void check_xstate_against_struct(int nr)
(nr >= XFEATURE_MAX) ||
(nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) {
- WARN_ONCE(1, "no structure for xstate: %d\n", nr);
+ pr_err("no structure for xstate: %d\n", nr);
XSTATE_WARN_ON(1);
+ return -EINVAL;
}
+
+ return 0;
}
/**
@@ -707,13 +710,14 @@ static void check_xstate_against_struct(int nr)
* excluded. Only the size of the buffer for task->fpu is checked here.
*
* @include_dynamic_states: A knob to include dynamic states or not.
+ * @size: A pointer to record the size.
*
- * Return: The calculated xstate size.
+ * Return: 0 if successful; otherwise, error code.
*/
-static unsigned int calculate_xstate_size(bool include_dynamic_states)
+static int calculate_xstate_size(bool include_dynamic_states, unsigned int *size)
{
unsigned int xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
- int i;
+ int i, err;
for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
if (!xfeature_enabled(i))
@@ -722,7 +726,10 @@ static unsigned int calculate_xstate_size(bool include_dynamic_states)
if (!include_dynamic_states && (xfeatures_mask_user_dynamic & BIT_ULL(i)))
continue;
- check_xstate_against_struct(i);
+ err = check_xstate_against_struct(i);
+ if (err)
+ return err;
+
/*
* Supervisor state components can be managed only by
* XSAVES.
@@ -748,7 +755,9 @@ static unsigned int calculate_xstate_size(bool include_dynamic_states)
xstate_size += xfeature_size(i);
}
- return xstate_size;
+ if (size)
+ *size = xstate_size;
+ return 0;
}
@@ -835,6 +844,7 @@ static int __init init_xstate_size(void)
/* Recompute the context size for enabled features: */
unsigned int possible_xstate_size, xstate_size;
unsigned int xsave_size;
+ int err;
xsave_size = get_xsave_size();
@@ -848,7 +858,9 @@ static int __init init_xstate_size(void)
* 'true' to include dynamic states. Cross-check with the CPUID-
* provided size and record it.
*/
- xstate_size = calculate_xstate_size(true);
+ err = calculate_xstate_size(true, &xstate_size);
+ if (err)
+ return err;
XSTATE_WARN_ON(possible_xstate_size != xstate_size);
set_xstate_config(XSTATE_MAX_SIZE, possible_xstate_size);
@@ -857,7 +869,9 @@ static int __init init_xstate_size(void)
* 'false' to exclude dynamic states. Ensure the size fits in
* the statically-allocated buffer and record it.
*/
- xstate_size = calculate_xstate_size(false);
+ err = calculate_xstate_size(false, &xstate_size);
+ if (err)
+ return err;
if (!is_supported_xstate_size(xstate_size))
return -EINVAL;
set_xstate_config(XSTATE_MIN_SIZE, xstate_size);
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 18/26] x86/cpufeatures/amx: Enumerate Advanced Matrix Extension (AMX) feature bits
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (16 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 17/26] x86/fpu/xstate: Disable XSTATE support if an inconsistent state is detected Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 19/26] x86/fpu/amx: Define AMX state components and have it used for boot-time checks Chang S. Bae
` (7 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Intel's Advanced Matrix Extension (AMX) is a new 64-bit extended feature
consisting of two-dimensional registers and an accelerator unit. The first
implementation of the latter is the tile matrix multiply unit (TMUL). TMUL
performs SIMD dot-products on four bytes (INT8) or two bfloat16
floating-point (BF16) elements.
Here enumerate this hardware capability to be shown as 'amx_tile',
'amx_bf16', and 'amx_int8' in /proc/cpuinfo.
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
---
Changes from v4:
* Massaged the changelog a bit.
---
arch/x86/include/asm/cpufeatures.h | 3 +++
arch/x86/kernel/cpu/cpuid-deps.c | 3 +++
2 files changed, 6 insertions(+)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 37150b7a8e44..9e9763ec7713 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -386,7 +386,10 @@
#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */
+#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX BF16 Support */
#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */
+#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
+#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX INT8 Support */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 7f891d2eb52e..9a520ab259ac 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -76,6 +76,9 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_SGX1, X86_FEATURE_SGX },
{ X86_FEATURE_SGX2, X86_FEATURE_SGX1 },
{ X86_FEATURE_XFD, X86_FEATURE_XSAVE },
+ { X86_FEATURE_AMX_TILE, X86_FEATURE_XSAVE },
+ { X86_FEATURE_AMX_INT8, X86_FEATURE_AMX_TILE },
+ { X86_FEATURE_AMX_BF16, X86_FEATURE_AMX_TILE },
{}
};
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 19/26] x86/fpu/amx: Define AMX state components and have it used for boot-time checks
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (17 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 18/26] x86/cpufeatures/amx: Enumerate Advanced Matrix Extension (AMX) feature bits Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 20/26] x86/fpu/amx: Initialize child's AMX state Chang S. Bae
` (6 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Linux uses check_xstate_against_struct() to sanity check the size of
XSTATE-enabled features. AMX is the XSAVE-enabled feature, and its size is
not hard-coded but discoverable at run-time via CPUID.
The AMX state is composed of state components 17 and 18, which are all user
state components. The first component is the XTILECFG state of a 64-byte
tile-related control register. The state component 18, called XTILEDATA,
contains the actual tile data, and the state size varies on
implementations. The architectural maximum, as defined in the CPUID(0x1d,
1): EAX[15:0], is a byte less than 64KB. The first implementation supports
8KB.
Check the XTILEDATA state size dynamically. The feature introduces the new
tile register, TMM. Define one register struct only and read the number of
registers from CPUID. Cross-check the overall size with CPUID again.
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
---
Changes from v4:
* Changed to return an error when tile data size mismatches. (Thomas Gleixner)
* Updated the function description and code comments.
Changes from v2:
* Updated the code comments.
Changes from v1:
* Rebased on the upstream kernel (5.10)
---
arch/x86/include/asm/fpu/types.h | 27 +++++++++++
arch/x86/include/asm/fpu/xstate.h | 2 +
arch/x86/kernel/fpu/xstate.c | 78 +++++++++++++++++++++++++++++++
3 files changed, 107 insertions(+)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 03160a1a79ad..f24b58b606dc 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -120,6 +120,9 @@ enum xfeature {
XFEATURE_RSRVD_COMP_13,
XFEATURE_RSRVD_COMP_14,
XFEATURE_LBR,
+ XFEATURE_RSRVD_COMP_16,
+ XFEATURE_XTILE_CFG,
+ XFEATURE_XTILE_DATA,
XFEATURE_MAX,
};
@@ -136,11 +139,15 @@ enum xfeature {
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID)
#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR)
+#define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG)
+#define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA)
#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \
| XFEATURE_MASK_ZMM_Hi256 \
| XFEATURE_MASK_Hi16_ZMM)
+#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA \
+ | XFEATURE_MASK_XTILE_CFG)
#define FIRST_EXTENDED_XFEATURE XFEATURE_YMM
@@ -153,6 +160,9 @@ struct reg_256_bit {
struct reg_512_bit {
u8 regbytes[512/8];
};
+struct reg_1024_byte {
+ u8 regbytes[1024];
+};
/*
* State component 2:
@@ -255,6 +265,23 @@ struct arch_lbr_state {
u64 ler_to;
u64 ler_info;
struct lbr_entry entries[];
+};
+
+/*
+ * State component 17: 64-byte tile configuration register.
+ */
+struct xtile_cfg {
+ u64 tcfg[8];
+} __packed;
+
+/*
+ * State component 18: 1KB tile data register.
+ * Each register represents 16 64-byte rows of the matrix
+ * data. But the number of registers depends on the actual
+ * implementation.
+ */
+struct xtile_data {
+ struct reg_1024_byte tmm;
} __packed;
/*
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 6051fd6a749f..dbf0db1df9bf 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -14,6 +14,8 @@
#define XSTATE_CPUID 0x0000000d
+#define TILE_CPUID 0x0000001d
+
#define FXSAVE_SIZE 512
#define XSAVE_HDR_SIZE 64
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index eda70bdca45c..e148f1202410 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -41,6 +41,14 @@ static const char *xfeature_names[] =
"Protection Keys User registers",
"PASID state",
"unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "AMX Tile config" ,
+ "AMX Tile data" ,
+ "unknown xstate feature" ,
};
static unsigned short xsave_cpuid_features[] __initdata = {
@@ -54,6 +62,8 @@ static unsigned short xsave_cpuid_features[] __initdata = {
[XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT,
[XFEATURE_PKRU] = X86_FEATURE_PKU,
[XFEATURE_PASID] = X86_FEATURE_ENQCMD,
+ [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE,
+ [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE,
};
/*
@@ -389,6 +399,8 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
print_xstate_feature(XFEATURE_MASK_PKRU);
print_xstate_feature(XFEATURE_MASK_PASID);
+ print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
+ print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
}
/*
@@ -662,6 +674,67 @@ static void __xstate_dump_leaves(void)
} \
} while (0)
+/**
+ * check_xtile_data_against_struct() - Check tile data state size.
+ *
+ * Calculate the state size by multiplying the single tile size which is
+ * recorded in a C struct, and the number of tiles that the CPU informs.
+ * Compare the provided size with the calculation.
+ *
+ * @size: The tile data state size
+ *
+ * Returns: 0 on success, -EINVAL on mismatch.
+ */
+static int check_xtile_data_against_struct(int size)
+{
+ u32 max_palid, palid, state_size;
+ u32 eax, ebx, ecx, edx;
+ u16 max_tile;
+
+ /*
+ * Check the maximum palette id:
+ * eax: the highest numbered palette subleaf.
+ */
+ cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx);
+
+ /*
+ * Cross-check each tile size and find the maximum number of
+ * supported tiles.
+ */
+ for (palid = 1, max_tile = 0; palid <= max_palid; palid++) {
+ u16 tile_size, max;
+
+ /*
+ * Check the tile size info:
+ * eax[31:16]: bytes per title
+ * ebx[31:16]: the max names (or max number of tiles)
+ */
+ cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx);
+ tile_size = eax >> 16;
+ max = ebx >> 16;
+
+ if (tile_size != sizeof(struct xtile_data)) {
+ pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n",
+ __stringify(XFEATURE_XTILE_DATA),
+ sizeof(struct xtile_data), tile_size);
+ __xstate_dump_leaves();
+ return -EINVAL;
+ }
+
+ if (max > max_tile)
+ max_tile = max;
+ }
+
+ state_size = sizeof(struct xtile_data) * max_tile;
+ if (size != state_size) {
+ pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n",
+ __stringify(XFEATURE_XTILE_DATA), state_size, size);
+ __xstate_dump_leaves();
+ return -EINVAL;
+ }
+ return 0;
+}
+
/*
* We have a C struct for each 'xstate'. We need to ensure
* that our software representation matches what the CPU
@@ -685,6 +758,11 @@ static int check_xstate_against_struct(int nr)
XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state);
+ XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg);
+
+ /* The tile data size varies between implementations. */
+ if (nr == XFEATURE_XTILE_DATA)
+ check_xtile_data_against_struct(sz);
/*
* Make *SURE* to add any feature numbers in below if
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 20/26] x86/fpu/amx: Initialize child's AMX state
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (18 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 19/26] x86/fpu/amx: Define AMX state components and have it used for boot-time checks Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 21/26] x86/fpu/amx: Enable the AMX feature in 64-bit mode Chang S. Bae
` (5 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Assure that a forked child starts AMX registers in the INIT-state.
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
---
Changes from v5:
* Introduced a new define. (Andy Lutomirski)
Changes from v4:
* Added as a new patch. This was missing on previous versions.
---
arch/x86/include/asm/fpu/xstate.h | 3 +++
arch/x86/kernel/fpu/core.c | 3 +++
2 files changed, 6 insertions(+)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index dbf0db1df9bf..bd7df0e7fc2b 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -80,6 +80,9 @@
XFEATURE_MASK_INDEPENDENT | \
XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
+/* Volatile states that a child does not inherit. */
+#define XFEATURE_MASK_CLEARED_ON_CLONE XFEATURE_MASK_XTILE
+
#ifdef CONFIG_X86_64
#define REX_PREFIX "0x48, "
#else
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index ed127c4d182b..e8912b5b9369 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -299,6 +299,9 @@ int fpu_clone(struct task_struct *dst)
save_fpregs_to_fpstate(dst_fpu);
fpregs_unlock();
+ if (xfeatures_mask_all & XFEATURE_MASK_CLEARED_ON_CLONE)
+ dst_fpu->state->xsave.header.xfeatures &= ~XFEATURE_MASK_CLEARED_ON_CLONE;
+
set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
trace_x86_fpu_copy_src(src_fpu);
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 21/26] x86/fpu/amx: Enable the AMX feature in 64-bit mode
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (19 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 20/26] x86/fpu/amx: Initialize child's AMX state Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 22/26] x86/fpu/xstate: Skip writing zeros to signal frame for dynamic user states if in INIT-state Chang S. Bae
` (4 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
In 64-bit mode, include the AMX state components in
XFEATURE_MASK_USER_SUPPORTED.
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
---
Changes from v5:
* Adjusted macro changes and moved the disabling code for non-64-bit mode
for the new base changes.
Changes from v4:
* Removed the irrelevant line from the changelog. (Thomas Gleixner)
---
arch/x86/include/asm/fpu/xstate.h | 3 ++-
arch/x86/kernel/fpu/xstate.c | 6 +++++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index bd7df0e7fc2b..bf0c6f981f34 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -35,7 +35,8 @@
XFEATURE_MASK_Hi16_ZMM | \
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
- XFEATURE_MASK_BNDCSR)
+ XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_XTILE)
/*
* Features which are restored when returning to user space.
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index e148f1202410..4e4f95065c4e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -538,7 +538,8 @@ static void __init print_xstate_offset_size(void)
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
XFEATURE_MASK_BNDCSR | \
- XFEATURE_MASK_PASID)
+ XFEATURE_MASK_PASID | \
+ XFEATURE_MASK_XTILE)
/*
* setup the xstate image representing the init state
@@ -1054,6 +1055,9 @@ void __init fpu__init_system_xstate(void)
xfeatures_mask_all &= XFEATURE_MASK_USER_SUPPORTED |
XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+ if (!IS_ENABLED(CONFIG_X86_64))
+ xfeatures_mask_all &= ~XFEATURE_MASK_XTILE;
+
/* Store it for paranoia check at the end */
xfeatures = xfeatures_mask_all;
/* Do not support the dynamically allocated buffer yet. */
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 22/26] x86/fpu/xstate: Skip writing zeros to signal frame for dynamic user states if in INIT-state
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (20 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 21/26] x86/fpu/amx: Enable the AMX feature in 64-bit mode Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 23/26] selftest/x86/amx: Test cases for the AMX state management Chang S. Bae
` (3 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
By default, for XSTATE features in the INIT-state, XSAVE writes zeros to
the uncompressed destination buffer.
E.g., if you are not using AVX-512, you will still get a bunch of zeros on
the signal stack where live AVX-512 data would go.
For 'dynamic user state' (currently only XTILEDATA), explicitly skip this
data transfer. The result is that the user buffer for the AMX region will
not be touched by XSAVE.
[ Reading XINUSE takes about 20-30 cycles, but writing zeros consumes about
5-times or more, e.g., for XTILEDATA. ]
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
---
Changes from v5:
* Mentioned the optimization trade-offs in the changelog. (Dave Hansen)
* Added code comment.
Changes from v4:
* Added as a new patch.
---
arch/x86/include/asm/fpu/internal.h | 38 +++++++++++++++++++++--------
1 file changed, 28 insertions(+), 10 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a1ccef6d4520..c9f1573f3ff8 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -337,8 +337,9 @@ static inline void os_xrstor(struct xregs_state *xstate, u64 mask)
*/
static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
{
+ struct fpu *fpu = ¤t->thread.fpu;
u32 lmask, hmask;
- u64 mask;
+ u64 state_mask;
int err;
/*
@@ -346,21 +347,38 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
* internally, e.g. PKRU. That's user space ABI and also required
* to allow the signal handler to modify PKRU.
*/
- mask = xfeatures_mask_uabi();
+ state_mask = xfeatures_mask_uabi();
+
+ if (!xfeatures_mask_user_dynamic)
+ goto mask_ready;
/*
* Exclude dynamic user states for non-opt-in threads.
*/
- if (xfeatures_mask_user_dynamic) {
- struct fpu *fpu = ¤t->thread.fpu;
-
- mask &= fpu->dynamic_state_perm ?
- fpu->state_mask :
- ~xfeatures_mask_user_dynamic;
+ if (!fpu->dynamic_state_perm) {
+ state_mask &= ~xfeatures_mask_user_dynamic;
+ } else {
+ u64 dynamic_state_mask;
+
+ state_mask &= fpu->state_mask;
+
+ dynamic_state_mask = state_mask & xfeatures_mask_user_dynamic;
+ if (dynamic_state_mask && boot_cpu_has(X86_FEATURE_XGETBV1)) {
+ u64 dynamic_xinuse, dynamic_init;
+ u64 xinuse = xgetbv(1);
+
+ dynamic_xinuse = xinuse & dynamic_state_mask;
+ dynamic_init = ~xinuse & dynamic_state_mask;
+ if (dynamic_init) {
+ state_mask &= ~xfeatures_mask_user_dynamic;
+ state_mask |= dynamic_xinuse;
+ }
+ }
}
- lmask = mask;
- hmask = mask >> 32;
+mask_ready:
+ lmask = state_mask;
+ hmask = state_mask >> 32;
/*
* Clear the xsave header first, so that reserved fields are
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 23/26] selftest/x86/amx: Test cases for the AMX state management
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (21 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 22/26] x86/fpu/xstate: Skip writing zeros to signal frame for dynamic user states if in INIT-state Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 24/26] x86/insn/amx: Add TILERELEASE instruction to the opcode map Chang S. Bae
` (2 subsequent siblings)
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, linux-kselftest
This selftest verifies that the XSTATE arch_prctl works for AMX state and
that a forked task has the AMX state in the INIT-state.
In addition, this test verifies that the kernel correctly context switches
unique AMX data, when multiple threads are using AMX. The test also
verifies that ptrace() can insert data into existing threads.
Finally, add a test case to verify that unused states are excluded, by
leaving a known pattern on the signal stack and verifying that it is still
intact after taking a subsequent signal.
These test cases do not depend on AMX compiler support, as they employ
userspace-XSAVE directly to access AMX state.
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
---
Changes from v6:
* Adjust for the syscall and ptrace path changes.
Changes from v5:
* Adjusted arch_prctl for the updated ABI.
* Added test for the dynamic signal xstate buffer.
* Fixed XSAVE buffer's header data.
Changes from v4:
* Added test for arch_prctl.
* Excluded tile config details to focus on testing the kernel's ability to
manage dynamic user state.
* Removed tile instructions.
* Simplified the fork() and ptrace() test routine.
* Massaged the changelog.
Changes from v2:
* Updated the test messages and the changelog as tile data is not inherited
to a child anymore.
* Removed bytecode for the instructions already supported by binutils.
* Changed to check the XSAVE availability in a reliable way.
Changes from v1:
* Removed signal testing code
---
tools/testing/selftests/x86/Makefile | 2 +-
tools/testing/selftests/x86/amx.c | 883 +++++++++++++++++++++++++++
2 files changed, 884 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/x86/amx.c
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index b4142cd1c5c2..8a1f62ab3c8e 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \
- corrupt_xstate_header
+ corrupt_xstate_header amx
# Some selftests require 32bit support enabled also on 64bit systems
TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c
new file mode 100644
index 000000000000..154dc750dae3
--- /dev/null
+++ b/tools/testing/selftests/x86/amx.c
@@ -0,0 +1,883 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <errno.h>
+#include <elf.h>
+#include <pthread.h>
+#include <setjmp.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <x86intrin.h>
+
+#include <linux/futex.h>
+
+#include <sys/ptrace.h>
+#include <sys/shm.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <sys/uio.h>
+
+
+#ifndef __x86_64__
+# error This test is 64-bit only
+#endif
+
+static inline uint64_t __xgetbv(uint32_t index)
+{
+ uint32_t eax, edx;
+
+ asm volatile("xgetbv;"
+ : "=a" (eax), "=d" (edx)
+ : "c" (index));
+ return eax + ((uint64_t)edx << 32);
+}
+
+static inline void __cpuid(uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx)
+{
+ asm volatile("cpuid;"
+ : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx)
+ : "0" (*eax), "2" (*ecx));
+}
+
+static inline void __xsave(void *buffer, uint32_t lo, uint32_t hi)
+{
+ asm volatile("xsave (%%rdi)"
+ : : "D" (buffer), "a" (lo), "d" (hi)
+ : "memory");
+}
+
+static inline void __xrstor(void *buffer, uint32_t lo, uint32_t hi)
+{
+ asm volatile("xrstor (%%rdi)"
+ : : "D" (buffer), "a" (lo), "d" (hi));
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_handler = SIG_DFL;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static jmp_buf jmpbuf;
+
+/* Hardware info check: */
+
+static bool xsave_disabled;
+
+static void handle_sigill(int sig, siginfo_t *si, void *ctx_void)
+{
+ xsave_disabled = true;
+ siglongjmp(jmpbuf, 1);
+}
+
+#define XFEATURE_XTILECFG 17
+#define XFEATURE_XTILEDATA 18
+#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
+#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
+#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
+
+static inline bool check_xsave_capability(void)
+{
+ sethandler(SIGILL, handle_sigill, 0);
+
+ if ((!sigsetjmp(jmpbuf, 1)) && (__xgetbv(0) & XFEATURE_MASK_XTILEDATA)) {
+ clearhandler(SIGILL);
+ return true;
+ }
+
+ clearhandler(SIGILL);
+ return false;
+}
+
+static uint32_t xsave_size;
+
+static uint32_t xsave_xtiledata_offset;
+static uint32_t xsave_xtiledata_size;
+
+static uint32_t xsave_xtilecfg_offset;
+static uint32_t xsave_xtilecfg_size;
+
+#define XSTATE_CPUID 0xd
+#define XSTATE_USER_STATE_SUBLEAVE 0x0
+
+static void check_cpuid(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ eax = XSTATE_CPUID;
+ ecx = XSTATE_USER_STATE_SUBLEAVE;
+
+ __cpuid(&eax, &ebx, &ecx, &edx);
+ if (!ebx)
+ err(1, "xstate cpuid: xsave size");
+
+ xsave_size = ebx;
+
+ eax = XSTATE_CPUID;
+ ecx = XFEATURE_XTILECFG;
+
+ __cpuid(&eax, &ebx, &ecx, &edx);
+ if (!eax || !ebx)
+ err(1, "xstate cpuid: tile config state");
+
+ xsave_xtilecfg_size = eax;
+ xsave_xtilecfg_offset = ebx;
+
+ eax = XSTATE_CPUID;
+ ecx = XFEATURE_XTILEDATA;
+
+ __cpuid(&eax, &ebx, &ecx, &edx);
+ if (!eax || !ebx)
+ err(1, "xstate cpuid: tile data state");
+
+ xsave_xtiledata_size = eax;
+ xsave_xtiledata_offset = ebx;
+}
+
+/* The helpers for managing XSAVE buffer and tile states: */
+
+#define XSAVE_HDR_OFFSET 512
+#define XSAVE_HDR_SIZE 64
+
+static inline void clr_xstatehdr(void *xsave)
+{
+ memset(xsave + XSAVE_HDR_OFFSET, 0, XSAVE_HDR_SIZE);
+}
+
+static inline uint64_t get_xstatebv(void *xsave)
+{
+ return *(uint64_t *)(xsave + XSAVE_HDR_OFFSET);
+}
+
+static inline void set_xstatebv(void *xsave, uint64_t bv)
+{
+ *(uint64_t *)(xsave + XSAVE_HDR_OFFSET) = bv;
+}
+
+static void set_rand_tiledata(void *tiledata)
+{
+ int *ptr = tiledata;
+ int data = rand();
+ int i;
+
+ for (i = 0; i < xsave_xtiledata_size / sizeof(int); i++, ptr++)
+ *ptr = data;
+}
+
+static void *xsave_buffer, *tiledata;
+static int nerrs, errs;
+
+/* See 'struct _fpx_sw_bytes' at sigcontext.h */
+#define SW_BYTES_OFFSET 464
+/* N.B. The struct's field name varies so read from the offset. */
+#define SW_BYTES_BV_OFFSET SW_BYTES_OFFSET + 8
+
+static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *xsave)
+{
+ return (struct _fpx_sw_bytes *)(xsave + SW_BYTES_OFFSET);
+}
+
+static inline uint64_t get_fpx_sw_bytes_xstatebv(void *xsave)
+{
+ return *(uint64_t *)(xsave + SW_BYTES_BV_OFFSET);
+}
+
+static volatile bool sigsegved;
+
+static void handle_sigsegv(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = (ucontext_t*)ctx_void;
+ void *xsave = ctx->uc_mcontext.fpregs;
+ struct _fpx_sw_bytes *sw_bytes;
+
+ printf("\tAt SIGSEGV handler,\n");
+
+ sw_bytes = get_fpx_sw_bytes(xsave);
+ if (!(sw_bytes->xstate_size < xsave_xtiledata_offset) &&
+ !(get_fpx_sw_bytes_xstatebv(xsave) & XFEATURE_MASK_XTILEDATA)) {
+ printf("[OK]\tValid xstate size and mask in the SW data of xstate buffer.\n");
+ } else {
+ errs++;
+ printf("[FAIL]\tInvalid xstate size and/or mask in the SW data of xstate buf.\n");
+ }
+
+ sigsegved = true;
+ ctx->uc_mcontext.gregs[REG_RIP] += 3; /* Skip the faulting XRSTOR */
+}
+
+/* Return true if XRSTOR is successful; otherwise, false. */
+static bool inline xrstor(void *buffer, uint32_t lo, uint32_t hi)
+{
+ sigsegved = false;
+ __xrstor(buffer, lo, hi);
+ return !sigsegved;
+}
+
+/* arch_prctl test */
+
+#define ARCH_SET_XSTATE_ENABLE 0x1021
+#define ARCH_GET_XSTATE_ENABLE 0x1022
+
+static void enable_tiledata(void)
+{
+ long rc;
+
+ rc = syscall(SYS_arch_prctl, ARCH_SET_XSTATE_ENABLE, XFEATURE_MASK_XTILEDATA);
+ if (rc)
+ goto fail;
+
+ rc = syscall(SYS_arch_prctl, ARCH_GET_XSTATE_ENABLE, 0);
+ if (rc & XFEATURE_MASK_XTILEDATA)
+ return;
+
+fail:
+ err(1, "ARCH_SET_XSTATE_ENABLE");
+}
+
+#define TEST_EXECV_ARG "nested"
+
+static void test_arch_prctl(int argc, char **argv)
+{
+ pid_t parent, child, grandchild;
+
+ parent = fork();
+ if (parent < 0) {
+ err(1, "fork");
+ } else if (parent > 0) {
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ err(1, "arch_prctl test parent exit");
+ return;
+ }
+
+ printf("[RUN]\tCheck ARCH_SET_XSTATE_ENABLE around process fork().\n");
+
+ printf("\tFork a child.\n");
+ child = fork();
+ if (child < 0) {
+ err(1, "fork");
+ } else if (child > 0) {
+ int status;
+
+ enable_tiledata();
+ printf("\tDo ARCH_SET_XSTATE_ENABLE at parent\n");
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ err(1, "arch_prctl test child exit");
+ _exit(0);
+ }
+
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA);
+ set_rand_tiledata(xsave_buffer + xsave_xtiledata_offset);
+
+ printf("\tLoad tile data without ARCH_SET_XSTATE_ENABLE at child.\n");
+ if (xrstor(xsave_buffer, -1, -1)) {
+ nerrs++;
+ printf("[FAIL]\tSucceeded at child.\n");
+ } else {
+ printf("[OK]\tBlocked at child.\n");
+ }
+
+ printf("\tDo ARCH_SET_XSTATE_ENABLE at child.\n");
+ enable_tiledata();
+
+ printf("\tLoad tile data with ARCH_SET_XSTATE_ENABLE at child:\n");
+ sigsegved = false;
+ if (xrstor(xsave_buffer, -1, -1)) {
+ printf("[OK]\tSucceeded at child.\n");
+ } else {
+ nerrs++;
+ printf("[FAIL]\tBlocked at child.\n");
+ }
+
+ printf("\tFork a grandchild.\n");
+ grandchild = fork();
+ if (grandchild < 0) {
+ err(1, "fork");
+ } else if (!grandchild) {
+ char *args[] = {argv[0], TEST_EXECV_ARG, NULL};
+
+ if (xrstor(xsave_buffer, -1, -1)) {
+ printf("[OK]\tSucceeded at grandchild.\n");
+ } else {
+ nerrs++;
+ printf("[FAIL]\tBlocked at grandchild.\n");
+ }
+ nerrs += execv(args[0], args);
+ } else {
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ err(1, "fork test grandchild");
+ }
+ _exit(0);
+}
+
+/* Testing tile data inheritance */
+
+static void test_fork(void)
+{
+ pid_t child, grandchild;
+
+ child = fork();
+ if (child < 0) {
+ err(1, "fork");
+ } else if (child > 0) {
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ err(1, "fork test child");
+ return;
+ }
+
+ printf("[RUN]\tCheck tile data inheritance.\n\tBefore fork(), load tile data -- yes:\n");
+
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILE);
+ set_rand_tiledata(xsave_buffer + xsave_xtiledata_offset);
+ memset(xsave_buffer + xsave_xtilecfg_offset, 1, xsave_xtilecfg_size);
+ xrstor(xsave_buffer, -1, -1);
+
+ grandchild = fork();
+ if (grandchild < 0) {
+ err(1, "fork");
+ } else if (grandchild > 0) {
+ int status;
+
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ err(1, "fork test grand child");
+ _exit(0);
+ }
+
+ if (__xgetbv(1) & XFEATURE_MASK_XTILE) {
+ nerrs++;
+ printf("[FAIL]\tIn a child, AMX state is not initialized.\n");
+ } else {
+ printf("[OK]\tIn a child, AMX state is initialized.\n");
+ }
+ _exit(0);
+}
+
+/* Context switching test */
+
+#define ITERATIONS 10
+#define NUM_THREADS 5
+
+struct futex_info {
+ int current;
+ int *futex;
+ int next;
+};
+
+static inline void command_wait(struct futex_info *info, int value)
+{
+ do {
+ sched_yield();
+ } while (syscall(SYS_futex, info->futex, FUTEX_WAIT, value, 0, 0, 0));
+}
+
+static inline void command_wake(struct futex_info *info, int value)
+{
+ do {
+ *info->futex = value;
+ while (!syscall(SYS_futex, info->futex, FUTEX_WAKE, 1, 0, 0, 0))
+ sched_yield();
+ } while (0);
+}
+
+static inline int get_iterative_value(int id)
+{
+ return ((id << 1) & ~0x1);
+}
+
+static inline int get_endpoint_value(int id)
+{
+ return ((id << 1) | 0x1);
+}
+
+static void *check_tiledata(void *info)
+{
+ struct futex_info *finfo = (struct futex_info *)info;
+ void *xsave, *tiledata;
+ int i;
+
+ xsave = aligned_alloc(64, xsave_size);
+ if (!xsave)
+ err(1, "aligned_alloc()");
+
+ tiledata = malloc(xsave_xtiledata_size);
+ if (!tiledata)
+ err(1, "malloc()");
+
+ set_xstatebv(xsave, XFEATURE_MASK_XTILEDATA);
+ set_rand_tiledata(xsave + xsave_xtiledata_offset);
+ xrstor(xsave, -1, -1);
+ memcpy(tiledata, xsave + xsave_xtiledata_offset, xsave_xtiledata_size);
+
+ for (i = 0; i < ITERATIONS; i++) {
+ command_wait(finfo, get_iterative_value(finfo->current));
+
+ __xsave(xsave, XFEATURE_MASK_XTILEDATA, 0);
+ if (memcmp(tiledata, xsave + xsave_xtiledata_offset, xsave_xtiledata_size))
+ errs++;
+
+ set_rand_tiledata(xsave + xsave_xtiledata_offset);
+ xrstor(xsave, -1, -1);
+ memcpy(tiledata, xsave + xsave_xtiledata_offset, xsave_xtiledata_size);
+
+ command_wake(finfo, get_iterative_value(finfo->next));
+ }
+
+ command_wait(finfo, get_endpoint_value(finfo->current));
+
+ free(xsave);
+ free(tiledata);
+ return NULL;
+}
+
+static int create_threads(int num, struct futex_info *finfo)
+{
+ const int shm_id = shmget(IPC_PRIVATE, sizeof(int), IPC_CREAT | 0666);
+ int *futex = shmat(shm_id, NULL, 0);
+ pthread_t thread;
+ int i;
+
+ for (i = 0; i < num; i++) {
+ finfo[i].futex = futex;
+ finfo[i].current = i + 1;
+ finfo[i].next = (i + 2) % (num + 1);
+
+ if (pthread_create(&thread, NULL, check_tiledata, &finfo[i]))
+ err(1, "pthread_create()");
+ }
+ return 0;
+}
+
+static void test_context_switch(void)
+{
+ struct futex_info *finfo;
+ int i;
+
+ printf("[RUN]\tCheck tile data context switches.\n");
+ printf("\t# of context switches -- %u, # of threads -- %d:\n",
+ ITERATIONS * NUM_THREADS, NUM_THREADS);
+
+ errs = 0;
+
+ finfo = malloc(sizeof(*finfo) * NUM_THREADS);
+ if (!finfo)
+ err(1, "malloc()");
+
+ create_threads(NUM_THREADS, finfo);
+
+ for (i = 0; i < ITERATIONS; i++) {
+ command_wake(finfo, get_iterative_value(1));
+ command_wait(finfo, get_iterative_value(0));
+ }
+
+ for (i = 1; i <= NUM_THREADS; i++)
+ command_wake(finfo, get_endpoint_value(i));
+
+ if (errs) {
+ nerrs += errs;
+ printf("[FAIL]\tIncorrect cases were found -- (%d / %u).\n",
+ errs, ITERATIONS * NUM_THREADS);
+ } else {
+ printf("[OK]\tNo incorrect case was found.\n");
+ }
+
+ free(finfo);
+ return;
+}
+
+/* Ptrace test */
+
+static bool allow_ptracee_dynstate;
+
+static int inject_tiledata(pid_t target)
+{
+ struct iovec iov;
+
+ iov.iov_base = xsave_buffer;
+ iov.iov_len = xsave_size;
+
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA);
+ set_rand_tiledata(xsave_buffer + xsave_xtiledata_offset);
+ memcpy(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size);
+
+ if (ptrace(PTRACE_SETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov)) {
+ if (errno != EFAULT)
+ err(1, "PTRACE_SETREGSET");
+ else
+ return errno;
+ }
+
+ if (ptrace(PTRACE_GETREGSET, target, (uint32_t)NT_X86_XSTATE, &iov))
+ err(1, "PTRACE_GETREGSET");
+
+ if (!memcmp(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size))
+ return 0;
+ else
+ return -1;
+}
+
+static void test_tile_write(void)
+{
+ int status, rc;
+ pid_t child;
+ bool pass;
+
+ child = fork();
+ if (child < 0) {
+ err(1, "fork");
+ } else if (!child) {
+ if (allow_ptracee_dynstate)
+ enable_tiledata();
+
+ if (ptrace(PTRACE_TRACEME, 0, NULL, NULL))
+ err(1, "PTRACE_TRACEME");
+
+ raise(SIGTRAP);
+ _exit(0);
+ }
+
+ do {
+ wait(&status);
+ } while (WSTOPSIG(status) != SIGTRAP);
+
+ printf("\tInject tile data %s ARCH_SET_XSTATE_ENABLE\n",
+ allow_ptracee_dynstate ? "with" : "without");
+
+ rc = inject_tiledata(child);
+ pass = (rc == EFAULT && !allow_ptracee_dynstate) ||
+ (!rc && allow_ptracee_dynstate);
+ if (!pass)
+ nerrs++;
+ printf("[%s]\tTile data was %swritten on ptracee.\n",
+ pass ? "OK" : "FAIL", errs ? "not " : "");
+
+ ptrace(PTRACE_DETACH, child, NULL, NULL);
+ wait(&status);
+ if (!WIFEXITED(status) || WEXITSTATUS(status))
+ err(1, "ptrace test");
+
+ return;
+}
+
+static void test_ptrace(void)
+{
+ printf("[RUN]\tCheck ptrace() to inject tile data.\n");
+
+ allow_ptracee_dynstate = false;
+ test_tile_write();
+
+ allow_ptracee_dynstate = true;
+ test_tile_write();
+}
+
+/* Signal handling test */
+
+static bool init_tiledata_state_before_signal;
+static bool load_tiledata_at_first;
+static volatile bool sigalarmed, sigused;
+
+#define SIGFRAME_TILEDATA_SIGNATURE 0xFF
+
+static void handle_sigusr1(int sig, siginfo_t *info, void *ctx_void)
+{
+ void *xsave = ((ucontext_t *)ctx_void)->uc_mcontext.fpregs;
+ struct _fpx_sw_bytes *sw_bytes = get_fpx_sw_bytes(xsave);
+
+ if (sw_bytes->xstate_size >= (xsave_xtiledata_offset + xsave_xtiledata_size)) {
+ memset(xsave + xsave_xtiledata_offset, SIGFRAME_TILEDATA_SIGNATURE,
+ xsave_xtiledata_size);
+ }
+
+ sigused = true;
+}
+
+static void handle_sigalrm(int sig, siginfo_t *info, void *ctx_void)
+{
+ bool tiledata_written = false, tiledata_bit, tiledata_expected;
+ void *xsave = ((ucontext_t *)ctx_void)->uc_mcontext.fpregs;
+ struct _fpx_sw_bytes *sw_bytes = get_fpx_sw_bytes(xsave);
+ char d = SIGFRAME_TILEDATA_SIGNATURE;
+ int i;
+
+ printf("\tAt signal delivery,\n");
+
+ /* Check SW reserved data in the buffer: */
+ if ((sw_bytes->xstate_size >= (xsave_xtiledata_offset + xsave_xtiledata_size)) &&
+ (get_fpx_sw_bytes_xstatebv(xsave) & XFEATURE_MASK_XTILEDATA)) {
+ printf("[OK]\tValid xstate size and mask in the SW data of xstate buffer\n");
+ } else {
+ errs++;
+ printf("[FAIL]\tInvalid xstate size and/or mask in the SW data of xstate buffer\n");
+ }
+
+ /* Check XSAVE buffer header: */
+ tiledata_expected = (load_tiledata_at_first && !init_tiledata_state_before_signal);
+ tiledata_bit = get_xstatebv(xsave) & XFEATURE_MASK_XTILEDATA;
+
+ if (tiledata_bit == tiledata_expected) {
+ printf("[OK]\tTiledata bit is %sset in XSTATE_BV of xstate buffer.\n",
+ tiledata_bit ? "" : "not ");
+ } else {
+ errs++;
+ printf("[FAIL]\tTiledata bit is %sset in XSTATE_BV of xstate buffer.\n",
+ tiledata_bit ? "" : "not ");
+ }
+
+ /*
+ * Check the sigframe data:
+ */
+
+ tiledata_expected = (load_tiledata_at_first && !init_tiledata_state_before_signal);
+
+ if (sw_bytes->xstate_size >= (xsave_xtiledata_offset + xsave_xtiledata_size)) {
+ for (i = 0; i < xsave_xtiledata_size; i++) {
+ tiledata_written = memcmp(xsave + xsave_xtiledata_offset + i, &d, 1);
+ if (tiledata_written)
+ break;
+ }
+ }
+
+ if (tiledata_written == tiledata_expected) {
+ printf("[OK]\tTiledata is %ssaved in signal buffer.\n",
+ tiledata_written ? "" : "not ");
+ } else {
+ errs++;
+ printf("[FAIL]\tTiledata is %ssaved in signal buffer.\n",
+ tiledata_written ? "" : "not ");
+ }
+
+ /* Load random tiledata to test sigreturn: */
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA);
+ set_rand_tiledata(xsave_buffer + xsave_xtiledata_offset);
+ xrstor(xsave_buffer, -1, -1);
+ sigalarmed = true;
+}
+
+static void test_signal_handling(void)
+{
+ pid_t child;
+
+ sigalarmed = false;
+ sigused = false;
+
+ child = fork();
+ if (child < 0) {
+ err(1, "fork");
+ } else if (child > 0) {
+ do {
+ int status;
+
+ wait(&status);
+ if (WIFSTOPPED(status))
+ kill(child, SIGCONT);
+ else if (WIFEXITED(status) && !WEXITSTATUS(status))
+ break;
+ else
+ err(1, "signal test child");
+ } while (1);
+ return;
+ }
+
+ printf("\tBefore signal, load tile data -- %s",
+ load_tiledata_at_first ? "yes, " : "no:\n");
+ if (load_tiledata_at_first)
+ printf("re-initialized -- %s:\n",
+ init_tiledata_state_before_signal ? "yes" : "no");
+
+ /*
+ * Raise SIGUSR1 to pre-fill sig stack. Also, load tiledata to size the pre-fill.
+ */
+
+ if (load_tiledata_at_first) {
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA);
+ xrstor(xsave_buffer, -1, -1);
+ }
+
+ raise(SIGUSR1);
+ if (!sigused)
+ err(1, "SIGUSR1");
+
+ /*
+ * Raise SIGALRM to test AMX state handling in signal delivery. Set up the state and
+ * data before the test.
+ */
+
+ if (load_tiledata_at_first) {
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILEDATA);
+ set_rand_tiledata(xsave_buffer + xsave_xtiledata_offset);
+ xrstor(xsave_buffer, -1, -1);
+
+ if (init_tiledata_state_before_signal) {
+ clr_xstatehdr(xsave_buffer);
+ set_xstatebv(xsave_buffer, 0);
+ xrstor(xsave_buffer, -1, -1);
+ memset(tiledata, 0, xsave_xtiledata_size);
+ } else {
+ memcpy(tiledata, xsave_buffer + xsave_xtiledata_offset,
+ xsave_xtiledata_size);
+ }
+ } else {
+ memset(tiledata, 0, xsave_xtiledata_size);
+ }
+
+ raise(SIGALRM);
+ if (!sigalarmed)
+ err(1, "SIGALRM");
+
+ printf("\tAt signal return,\n");
+ __xsave(xsave_buffer, XFEATURE_MASK_XTILEDATA, 0);
+ if (memcmp(tiledata, xsave_buffer + xsave_xtiledata_offset, xsave_xtiledata_size)) {
+ errs++;
+ printf("[FAIL]\tTiledata is not restored.\n");
+ } else {
+ printf("[OK]\tTiledata is restored.\n");
+ }
+
+ if (errs)
+ nerrs++;
+ _exit(0);
+}
+
+static void test_signal(void)
+{
+ printf("[RUN]\tCheck tile data state in signal path:\n");
+
+ sethandler(SIGALRM, handle_sigalrm, 0);
+ sethandler(SIGUSR1, handle_sigusr1, 0);
+
+ load_tiledata_at_first = false;
+ init_tiledata_state_before_signal = false;
+ errs = 0;
+ test_signal_handling();
+
+ load_tiledata_at_first = true;
+ init_tiledata_state_before_signal = false;
+ errs = 0;
+ test_signal_handling();
+
+ load_tiledata_at_first = true;
+ init_tiledata_state_before_signal = true;
+ errs = 0;
+ test_signal_handling();
+
+ clearhandler(SIGALRM);
+ clearhandler(SIGUSR1);
+}
+
+int main(int argc, char **argv)
+{
+ cpu_set_t cpuset;
+
+ if (argc == 2) {
+ int ret;
+
+ if (strcmp(argv[1], TEST_EXECV_ARG))
+ return 0;
+
+ printf("\tRun after execv().\n");
+
+ xsave_buffer = aligned_alloc(64, xsave_size);
+ if (!xsave_buffer)
+ err(1, "aligned_alloc()");
+ clr_xstatehdr(xsave_buffer);
+
+ set_xstatebv(xsave_buffer, XFEATURE_MASK_XTILE);
+ set_rand_tiledata(xsave_buffer + xsave_xtiledata_offset);
+
+ sethandler(SIGSEGV, handle_sigsegv, 0);
+
+ if (xrstor(xsave_buffer, -1, -1)) {
+ printf("[FAIL]\tSucceeded after execv().\n");
+ ret = 1;
+ } else {
+ printf("[OK]\tBlocked after execv().\n");
+ ret = 0;
+ }
+
+ clearhandler(SIGSEGV);
+ free(xsave_buffer);
+ _exit(ret);
+ }
+
+ /* Check hardware availability at first */
+
+ if (!check_xsave_capability()) {
+ if (xsave_disabled)
+ printf("XSAVE disabled.\n");
+ else
+ printf("Tile data not available.\n");
+ return 0;
+ }
+
+ check_cpuid();
+
+ xsave_buffer = aligned_alloc(64, xsave_size);
+ if (!xsave_buffer)
+ err(1, "aligned_alloc()");
+ clr_xstatehdr(xsave_buffer);
+
+ tiledata = malloc(xsave_xtiledata_size);
+ if (!tiledata)
+ err(1, "malloc()");
+
+ nerrs = 0;
+
+ sethandler(SIGSEGV, handle_sigsegv, 0);
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+ err(1, "sched_setaffinity to CPU 0");
+
+ test_arch_prctl(argc, argv);
+ test_ptrace();
+
+ enable_tiledata();
+ test_context_switch();
+ test_fork();
+ test_signal();
+
+ clearhandler(SIGSEGV);
+
+ free(xsave_buffer);
+ free(tiledata);
+ return nerrs ? 1 : 0;
+}
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 24/26] x86/insn/amx: Add TILERELEASE instruction to the opcode map
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (22 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 23/26] selftest/x86/amx: Test cases for the AMX state management Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 25/26] intel_idle/amx: Add SPR support with XTILEDATA capability Chang S. Bae
2021-07-10 13:03 ` [PATCH v7 26/26] x86/fpu/xstate: Add a sanity check for XFD state when saving XSTATE Chang S. Bae
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Include the opcode of TILERELEASE that returns all the AMX state to
INIT-state.
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
---
Changes from v4:
* Added as a new patch as preparatory to use the instruction in the kernel.
---
arch/x86/lib/x86-opcode-map.txt | 8 +++++++-
tools/arch/x86/lib/x86-opcode-map.txt | 8 +++++++-
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index ec31f5b60323..dbc5078ccafe 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -690,7 +690,9 @@ AVXcode: 2
45: vpsrlvd/q Vx,Hx,Wx (66),(v)
46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x4b
+# Skip 0x48
+49: Grp22 (1A)
+# Skip 0x4a-0x4b
4c: vrcp14ps/d Vpd,Wpd (66),(ev)
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
@@ -1082,6 +1084,10 @@ GrpTable: Grp21
7: ENDBR64 (F3),(010),(11B) | ENDBR32 (F3),(011),(11B)
EndTable
+GrpTable: Grp22
+0: TILERELEASE (!F3),(v1),(11B)
+EndTable
+
# AMD's Prefetch Group
GrpTable: GrpP
0: PREFETCH
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index ec31f5b60323..dbc5078ccafe 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -690,7 +690,9 @@ AVXcode: 2
45: vpsrlvd/q Vx,Hx,Wx (66),(v)
46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x4b
+# Skip 0x48
+49: Grp22 (1A)
+# Skip 0x4a-0x4b
4c: vrcp14ps/d Vpd,Wpd (66),(ev)
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
@@ -1082,6 +1084,10 @@ GrpTable: Grp21
7: ENDBR64 (F3),(010),(11B) | ENDBR32 (F3),(011),(11B)
EndTable
+GrpTable: Grp22
+0: TILERELEASE (!F3),(v1),(11B)
+EndTable
+
# AMD's Prefetch Group
GrpTable: GrpP
0: PREFETCH
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* [PATCH v7 25/26] intel_idle/amx: Add SPR support with XTILEDATA capability
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (23 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 24/26] x86/insn/amx: Add TILERELEASE instruction to the opcode map Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
2021-07-16 17:34 ` Rafael J. Wysocki
2021-07-10 13:03 ` [PATCH v7 26/26] x86/fpu/xstate: Add a sanity check for XFD state when saving XSTATE Chang S. Bae
25 siblings, 1 reply; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae, linux-pm
Add a custom Sapphire Rapids (SPR) C-state table to intel_idle driver. The
parameters in this table are preferred over those supplied by ACPI.
SPR supports AMX, and so this custom table uses idle entry points that know
how to initialize AMX TMM state, if necessary.
This guarantees that AMX TMM state will never be the cause of hardware
C-state demotion from C6 to C1E. Under some conditions this may result in
improved power savings, and thus higher available turbo frequency budget.
[ Based on patch by Artem Bityutskiy <artem.bityutskiy@linux.intel.com>. ]
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: linux-pm@vger.kernel.org
---
Changes from v6:
* Update the changelog and function description. (Rafael J. Wysocki)
Changes from v5:
* Moved the code to intel_idle. (Peter Zijlstra)
* Fixed to deactivate fpregs. (Andy Lutomirski and Dave Hansen)
* Updated the code comment. (Dave Hansen)
Changes from v4:
* Added as a new patch. (Thomas Gleixner)
---
arch/x86/include/asm/special_insns.h | 6 +++
drivers/idle/intel_idle.c | 79 ++++++++++++++++++++++++++++
2 files changed, 85 insertions(+)
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index f3fbb84ff8a7..fada1bb82c7b 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -294,6 +294,12 @@ static inline int enqcmds(void __iomem *dst, const void *src)
return 0;
}
+static inline void tile_release(void)
+{
+ /* Instruction opcode for TILERELEASE; supported in binutils >= 2.36. */
+ asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
+}
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index e6c543b5ee1d..00f331b64131 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -54,6 +54,8 @@
#include <asm/intel-family.h>
#include <asm/mwait.h>
#include <asm/msr.h>
+#include <asm/fpu/internal.h>
+#include <asm/special_insns.h>
#define INTEL_IDLE_VERSION "0.5.1"
@@ -155,6 +157,55 @@ static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
return 0;
}
+/**
+ * idle_tile() - Initialize TILE registers in INIT-state
+ *
+ * Leaving state in the dirty TILE registers may prevent the processor from
+ * entering lower-power idle states. Use TILERELEASE to initialize the
+ * state. Destroying fpregs state is safe after the fpstate update.
+ */
+static inline void idle_tile(void)
+{
+ if (boot_cpu_has(X86_FEATURE_XGETBV1) && (xgetbv(1) & XFEATURE_MASK_XTILE)) {
+ tile_release();
+ fpregs_deactivate(¤t->thread.fpu);
+ }
+}
+
+/**
+ * intel_idle_tile - Ask the processor to enter the given idle state.
+ * @dev: cpuidle device of the target CPU.
+ * @drv: cpuidle driver (assumed to point to intel_idle_driver).
+ * @index: Target idle state index.
+ *
+ * Ensure TILE registers in INIT-state before using intel_idle() to
+ * enter the idle state.
+ */
+static __cpuidle int intel_idle_tile(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
+{
+ idle_tile();
+
+ return intel_idle(dev, drv, index);
+}
+
+/**
+ * intel_idle_s2idle_tile - Ask the processor to enter the given idle state.
+ * @dev: cpuidle device of the target CPU.
+ * @drv: cpuidle driver (assumed to point to intel_idle_driver).
+ * @index: Target idle state index.
+ *
+ * Ensure TILE registers in INIT-state before using intel_idle_s2idle() to
+ * enter the idle state.
+ */
+static __cpuidle int intel_idle_s2idle_tile(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
+{
+ idle_tile();
+
+ return intel_idle_s2idle(dev, drv, index);
+}
+
/*
* States are indexed by the cstate number,
* which is also the index into the MWAIT hint array.
@@ -752,6 +803,27 @@ static struct cpuidle_state icx_cstates[] __initdata = {
.enter = NULL }
};
+static struct cpuidle_state spr_cstates[] __initdata = {
+ {
+ .name = "C1",
+ .desc = "MWAIT 0x00",
+ .flags = MWAIT2flg(0x00),
+ .exit_latency = 1,
+ .target_residency = 1,
+ .enter = &intel_idle,
+ .enter_s2idle = intel_idle_s2idle, },
+ {
+ .name = "C6",
+ .desc = "MWAIT 0x20",
+ .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 128,
+ .target_residency = 384,
+ .enter = &intel_idle_tile,
+ .enter_s2idle = intel_idle_s2idle_tile, },
+ {
+ .enter = NULL }
+};
+
static struct cpuidle_state atom_cstates[] __initdata = {
{
.name = "C1E",
@@ -1095,6 +1167,12 @@ static const struct idle_cpu idle_cpu_icx __initconst = {
.use_acpi = true,
};
+static const struct idle_cpu idle_cpu_spr __initconst = {
+ .state_table = spr_cstates,
+ .disable_promotion_to_c1e = true,
+ .use_acpi = true,
+};
+
static const struct idle_cpu idle_cpu_avn __initconst = {
.state_table = avn_cstates,
.disable_promotion_to_c1e = true,
@@ -1157,6 +1235,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &idle_cpu_skx),
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &idle_cpu_icx),
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &idle_cpu_icx),
+ X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &idle_cpu_spr),
X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &idle_cpu_knl),
X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &idle_cpu_knl),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &idle_cpu_bxt),
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread* Re: [PATCH v7 25/26] intel_idle/amx: Add SPR support with XTILEDATA capability
2021-07-10 13:03 ` [PATCH v7 25/26] intel_idle/amx: Add SPR support with XTILEDATA capability Chang S. Bae
@ 2021-07-16 17:34 ` Rafael J. Wysocki
2021-07-16 17:37 ` Bae, Chang Seok
0 siblings, 1 reply; 31+ messages in thread
From: Rafael J. Wysocki @ 2021-07-16 17:34 UTC (permalink / raw)
To: Chang S. Bae
Cc: Borislav Petkov, Andy Lutomirski, Thomas Gleixner, Ingo Molnar,
the arch/x86 maintainers, Len Brown, Dave Hansen,
thiago.macieira, jing2.liu, Ravi V. Shankar,
Linux Kernel Mailing List, Linux PM
On Sat, Jul 10, 2021 at 3:09 PM Chang S. Bae <chang.seok.bae@intel.com> wrote:
>
> Add a custom Sapphire Rapids (SPR) C-state table to intel_idle driver. The
> parameters in this table are preferred over those supplied by ACPI.
>
> SPR supports AMX, and so this custom table uses idle entry points that know
> how to initialize AMX TMM state, if necessary.
>
> This guarantees that AMX TMM state will never be the cause of hardware
> C-state demotion from C6 to C1E. Under some conditions this may result in
> improved power savings, and thus higher available turbo frequency budget.
>
> [ Based on patch by Artem Bityutskiy <artem.bityutskiy@linux.intel.com>. ]
>
> 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: linux-pm@vger.kernel.org
> ---
> Changes from v6:
> * Update the changelog and function description. (Rafael J. Wysocki)
>
> Changes from v5:
> * Moved the code to intel_idle. (Peter Zijlstra)
> * Fixed to deactivate fpregs. (Andy Lutomirski and Dave Hansen)
> * Updated the code comment. (Dave Hansen)
>
> Changes from v4:
> * Added as a new patch. (Thomas Gleixner)
> ---
> arch/x86/include/asm/special_insns.h | 6 +++
> drivers/idle/intel_idle.c | 79 ++++++++++++++++++++++++++++
> 2 files changed, 85 insertions(+)
>
> diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
> index f3fbb84ff8a7..fada1bb82c7b 100644
> --- a/arch/x86/include/asm/special_insns.h
> +++ b/arch/x86/include/asm/special_insns.h
> @@ -294,6 +294,12 @@ static inline int enqcmds(void __iomem *dst, const void *src)
> return 0;
> }
>
> +static inline void tile_release(void)
> +{
> + /* Instruction opcode for TILERELEASE; supported in binutils >= 2.36. */
> + asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0");
> +}
> +
> #endif /* __KERNEL__ */
>
> #endif /* _ASM_X86_SPECIAL_INSNS_H */
> diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
> index e6c543b5ee1d..00f331b64131 100644
> --- a/drivers/idle/intel_idle.c
> +++ b/drivers/idle/intel_idle.c
> @@ -54,6 +54,8 @@
> #include <asm/intel-family.h>
> #include <asm/mwait.h>
> #include <asm/msr.h>
> +#include <asm/fpu/internal.h>
> +#include <asm/special_insns.h>
>
> #define INTEL_IDLE_VERSION "0.5.1"
>
> @@ -155,6 +157,55 @@ static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
> return 0;
> }
>
> +/**
> + * idle_tile() - Initialize TILE registers in INIT-state
The parens should not be present here.
With this fixed:
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> + *
> + * Leaving state in the dirty TILE registers may prevent the processor from
> + * entering lower-power idle states. Use TILERELEASE to initialize the
> + * state. Destroying fpregs state is safe after the fpstate update.
> + */
> +static inline void idle_tile(void)
> +{
> + if (boot_cpu_has(X86_FEATURE_XGETBV1) && (xgetbv(1) & XFEATURE_MASK_XTILE)) {
> + tile_release();
> + fpregs_deactivate(¤t->thread.fpu);
> + }
> +}
> +
> +/**
> + * intel_idle_tile - Ask the processor to enter the given idle state.
> + * @dev: cpuidle device of the target CPU.
> + * @drv: cpuidle driver (assumed to point to intel_idle_driver).
> + * @index: Target idle state index.
> + *
> + * Ensure TILE registers in INIT-state before using intel_idle() to
> + * enter the idle state.
> + */
> +static __cpuidle int intel_idle_tile(struct cpuidle_device *dev,
> + struct cpuidle_driver *drv, int index)
> +{
> + idle_tile();
> +
> + return intel_idle(dev, drv, index);
> +}
> +
> +/**
> + * intel_idle_s2idle_tile - Ask the processor to enter the given idle state.
> + * @dev: cpuidle device of the target CPU.
> + * @drv: cpuidle driver (assumed to point to intel_idle_driver).
> + * @index: Target idle state index.
> + *
> + * Ensure TILE registers in INIT-state before using intel_idle_s2idle() to
> + * enter the idle state.
> + */
> +static __cpuidle int intel_idle_s2idle_tile(struct cpuidle_device *dev,
> + struct cpuidle_driver *drv, int index)
> +{
> + idle_tile();
> +
> + return intel_idle_s2idle(dev, drv, index);
> +}
> +
> /*
> * States are indexed by the cstate number,
> * which is also the index into the MWAIT hint array.
> @@ -752,6 +803,27 @@ static struct cpuidle_state icx_cstates[] __initdata = {
> .enter = NULL }
> };
>
> +static struct cpuidle_state spr_cstates[] __initdata = {
> + {
> + .name = "C1",
> + .desc = "MWAIT 0x00",
> + .flags = MWAIT2flg(0x00),
> + .exit_latency = 1,
> + .target_residency = 1,
> + .enter = &intel_idle,
> + .enter_s2idle = intel_idle_s2idle, },
> + {
> + .name = "C6",
> + .desc = "MWAIT 0x20",
> + .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
> + .exit_latency = 128,
> + .target_residency = 384,
> + .enter = &intel_idle_tile,
> + .enter_s2idle = intel_idle_s2idle_tile, },
> + {
> + .enter = NULL }
> +};
> +
> static struct cpuidle_state atom_cstates[] __initdata = {
> {
> .name = "C1E",
> @@ -1095,6 +1167,12 @@ static const struct idle_cpu idle_cpu_icx __initconst = {
> .use_acpi = true,
> };
>
> +static const struct idle_cpu idle_cpu_spr __initconst = {
> + .state_table = spr_cstates,
> + .disable_promotion_to_c1e = true,
> + .use_acpi = true,
> +};
> +
> static const struct idle_cpu idle_cpu_avn __initconst = {
> .state_table = avn_cstates,
> .disable_promotion_to_c1e = true,
> @@ -1157,6 +1235,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
> X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &idle_cpu_skx),
> X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &idle_cpu_icx),
> X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &idle_cpu_icx),
> + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &idle_cpu_spr),
> X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &idle_cpu_knl),
> X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &idle_cpu_knl),
> X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &idle_cpu_bxt),
> --
> 2.17.1
>
^ permalink raw reply [flat|nested] 31+ messages in thread* Re: [PATCH v7 25/26] intel_idle/amx: Add SPR support with XTILEDATA capability
2021-07-16 17:34 ` Rafael J. Wysocki
@ 2021-07-16 17:37 ` Bae, Chang Seok
0 siblings, 0 replies; 31+ messages in thread
From: Bae, Chang Seok @ 2021-07-16 17:37 UTC (permalink / raw)
To: Rafael J. Wysocki
Cc: Borislav Petkov, Lutomirski, Andy, Thomas Gleixner, Ingo Molnar,
the arch/x86 maintainers, Brown, Len, Hansen, Dave, Macieira,
Thiago, Liu, Jing2, Shankar, Ravi V, Linux Kernel Mailing List,
Linux PM
On Jul 16, 2021, at 10:34, Rafael J. Wysocki <rafael@kernel.org> wrote:
> On Sat, Jul 10, 2021 at 3:09 PM Chang S. Bae <chang.seok.bae@intel.com> wrote:
>>
>> +/**
>> + * idle_tile() - Initialize TILE registers in INIT-state
>
> The parens should not be present here.
Okay. Perhaps, I need to do for other changes in this series.
> With this fixed:
>
> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Thanks!
Chang
^ permalink raw reply [flat|nested] 31+ messages in thread
* [PATCH v7 26/26] x86/fpu/xstate: Add a sanity check for XFD state when saving XSTATE
2021-07-10 13:02 [PATCH v7 00/26] x86: Support Intel Advanced Matrix Extensions Chang S. Bae
` (24 preceding siblings ...)
2021-07-10 13:03 ` [PATCH v7 25/26] intel_idle/amx: Add SPR support with XTILEDATA capability Chang S. Bae
@ 2021-07-10 13:03 ` Chang S. Bae
25 siblings, 0 replies; 31+ messages in thread
From: Chang S. Bae @ 2021-07-10 13:03 UTC (permalink / raw)
To: bp, luto, tglx, mingo, x86
Cc: len.brown, dave.hansen, thiago.macieira, jing2.liu,
ravi.v.shankar, linux-kernel, chang.seok.bae
Add a DEBUG sanity check that XFD state matches with XINUSE state.
Instead of reading MSR IA32_XFD directly, read a per-cpu value that is
recorded at every MSR write.
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
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
---
Changes from v5:
* Added as a new patch. (Dave Hansen)
---
arch/x86/include/asm/fpu/internal.h | 15 +++++++++++++++
arch/x86/kernel/fpu/core.c | 13 +++++++++++++
2 files changed, 28 insertions(+)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index c9f1573f3ff8..1b3062d5f5a0 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -570,10 +570,25 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
/* The Extended Feature Disable (XFD) helpers: */
+#ifdef CONFIG_X86_DEBUG_FPU
+DECLARE_PER_CPU(u64, xfd_shadow);
+static inline u64 xfd_debug_shadow(void)
+{
+ return this_cpu_read(xfd_shadow);
+}
+
+static inline void xfd_write(u64 value)
+{
+ wrmsrl_safe(MSR_IA32_XFD, value);
+ this_cpu_write(xfd_shadow, value);
+}
+#else
+#define xfd_debug_shadow() 0
static inline void xfd_write(u64 value)
{
wrmsrl_safe(MSR_IA32_XFD, value);
}
+#endif
static inline u64 xfd_read(void)
{
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e8912b5b9369..1b1306488fb6 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -82,6 +82,10 @@ bool irq_fpu_usable(void)
}
EXPORT_SYMBOL(irq_fpu_usable);
+#ifdef CONFIG_X86_DEBUG_FPU
+DEFINE_PER_CPU(u64, xfd_shadow);
+#endif
+
/*
* Save the FPU register state in fpu->state. The register state is
* preserved.
@@ -99,6 +103,15 @@ EXPORT_SYMBOL(irq_fpu_usable);
void save_fpregs_to_fpstate(struct fpu *fpu)
{
if (likely(use_xsave())) {
+ /*
+ * If XFD is armed for an xfeature, XSAVE* will not save
+ * its state. Verify XFD is clear for all features that
+ * are in use before XSAVE*.
+ */
+ if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) && xfd_capable() &&
+ boot_cpu_has(X86_FEATURE_XGETBV1))
+ WARN_ON_FPU(xgetbv(1) & xfd_debug_shadow());
+
os_xsave(&fpu->state->xsave, fpu->state_mask);
/*
--
2.17.1
^ permalink raw reply related [flat|nested] 31+ messages in thread