aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-11-14 09:29:03 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2021-11-14 09:29:03 -0800
commit1654e95ee30a82bec843e73a591f9ea3db8da8db (patch)
tree7bd8d2c6d1d0f0dc176abcf02fccdfbb0c8e4fc8
parentMerge tag 'perf-tools-for-v5.16-2021-11-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux (diff)
parentx86/cpu: Add Raptor Lake to Intel family (diff)
downloadlinux-dev-1654e95ee30a82bec843e73a591f9ea3db8da8db.tar.xz
linux-dev-1654e95ee30a82bec843e73a591f9ea3db8da8db.zip
Merge tag 'x86_urgent_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Borislav Petkov: - Add the model number of a new, Raptor Lake CPU, to intel-family.h - Do not log spurious corrected MCEs on SKL too, due to an erratum - Clarify the path of paravirt ops patches upstream - Add an optimization to avoid writing out AMX components to sigframes when former are in init state * tag 'x86_urgent_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/cpu: Add Raptor Lake to Intel family x86/mce: Add errata workaround for Skylake SKX37 MAINTAINERS: Add some information to PARAVIRT_OPS entry x86/fpu: Optimize out sigframe xfeatures when in init state
-rw-r--r--Documentation/x86/xstate.rst9
-rw-r--r--MAINTAINERS2
-rw-r--r--arch/x86/include/asm/fpu/xcr.h12
-rw-r--r--arch/x86/include/asm/fpu/xstate.h7
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c1
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c5
-rw-r--r--arch/x86/kernel/fpu/xstate.h37
8 files changed, 71 insertions, 4 deletions
diff --git a/Documentation/x86/xstate.rst b/Documentation/x86/xstate.rst
index 65de3f054ba5..5cec7fb558d6 100644
--- a/Documentation/x86/xstate.rst
+++ b/Documentation/x86/xstate.rst
@@ -63,3 +63,12 @@ kernel sends SIGILL to the application. If the process has permission then
the handler allocates a larger xstate buffer for the task so the large
state can be context switched. In the unlikely cases that the allocation
fails, the kernel sends SIGSEGV.
+
+Dynamic features in signal frames
+---------------------------------
+
+Dynamcally enabled features are not written to the signal frame upon signal
+entry if the feature is in its initial configuration. This differs from
+non-dynamic features which are always written regardless of their
+configuration. Signal handlers can examine the XSAVE buffer's XSTATE_BV
+field to determine if a features was written.
diff --git a/MAINTAINERS b/MAINTAINERS
index 349022a3a375..7a2345ce8521 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14412,7 +14412,9 @@ M: Juergen Gross <jgross@suse.com>
M: Deep Shah <sdeep@vmware.com>
M: "VMware, Inc." <pv-drivers@vmware.com>
L: virtualization@lists.linux-foundation.org
+L: x86@kernel.org
S: Supported
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
F: Documentation/virt/paravirt_ops.rst
F: arch/*/include/asm/paravirt*.h
F: arch/*/kernel/paravirt*
diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h
index 79f95d3787e2..9656a5bc6fea 100644
--- a/arch/x86/include/asm/fpu/xcr.h
+++ b/arch/x86/include/asm/fpu/xcr.h
@@ -3,6 +3,7 @@
#define _ASM_X86_FPU_XCR_H
#define XCR_XFEATURE_ENABLED_MASK 0x00000000
+#define XCR_XFEATURE_IN_USE_MASK 0x00000001
static inline u64 xgetbv(u32 index)
{
@@ -20,4 +21,15 @@ static inline void xsetbv(u32 index, u64 value)
asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
}
+/*
+ * Return a mask of xfeatures which are currently being tracked
+ * by the processor as being in the initial configuration.
+ *
+ * Callers should check X86_FEATURE_XGETBV1.
+ */
+static inline u64 xfeatures_in_use(void)
+{
+ return xgetbv(XCR_XFEATURE_IN_USE_MASK);
+}
+
#endif /* _ASM_X86_FPU_XCR_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 0f8b90ab18c9..cd3dd170e23a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -92,6 +92,13 @@
#define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \
XFEATURE_MASK_SUPERVISOR_SUPPORTED)
+/*
+ * Features in this mask have space allocated in the signal frame, but may not
+ * have that space initialized when the feature is in its init state.
+ */
+#define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \
+ XFEATURE_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/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 27158436f322..5a0bcf8b78d7 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -108,6 +108,8 @@
#define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */
+#define INTEL_FAM6_RAPTOR_LAKE 0xB7
+
/* "Small Core" Processors (Atom) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index cb2fdd130aae..c881bcafba7d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -76,6 +76,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_SGX1, X86_FEATURE_SGX },
{ X86_FEATURE_SGX2, X86_FEATURE_SGX1 },
{ X86_FEATURE_XFD, X86_FEATURE_XSAVES },
+ { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 },
{ X86_FEATURE_AMX_TILE, X86_FEATURE_XFD },
{}
};
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index acfd5d9f93c6..bb9a46a804bf 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
- /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */
+ /* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */
if ((c->x86 == 6) &&
((c->x86_model == INTEL_FAM6_HASWELL) ||
(c->x86_model == INTEL_FAM6_HASWELL_L) ||
(c->x86_model == INTEL_FAM6_BROADWELL) ||
- (c->x86_model == INTEL_FAM6_HASWELL_G)) &&
+ (c->x86_model == INTEL_FAM6_HASWELL_G) ||
+ (c->x86_model == INTEL_FAM6_SKYLAKE_X)) &&
(m->bank == 0) &&
((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
return true;
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index e18210dff88c..86ea7c0fa2f6 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -4,6 +4,7 @@
#include <asm/cpufeature.h>
#include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(u64, xfd_state);
@@ -199,6 +200,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate)
}
/*
+ * XSAVE itself always writes all requested xfeatures. Removing features
+ * from the request bitmap reduces the features which are written.
+ * Generate a mask of features which must be written to a sigframe. The
+ * unset features can be optimized away and not written.
+ *
+ * This optimization is user-visible. Only use for states where
+ * uninitialized sigframe contents are tolerable, like dynamic features.
+ *
+ * Users of buffers produced with this optimization must check XSTATE_BV
+ * to determine which features have been optimized out.
+ */
+static inline u64 xfeatures_need_sigframe_write(void)
+{
+ u64 xfeaures_to_write;
+
+ /* In-use features must be written: */
+ xfeaures_to_write = xfeatures_in_use();
+
+ /* Also write all non-optimizable sigframe features: */
+ xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED &
+ ~XFEATURE_MASK_SIGFRAME_INITOPT;
+
+ return xfeaures_to_write;
+}
+
+/*
* Save xstate to user space xsave area.
*
* We don't use modified optimization because xrstor/xrstors might track
@@ -220,10 +247,16 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
*/
struct fpstate *fpstate = current->thread.fpu.fpstate;
u64 mask = fpstate->user_xfeatures;
- u32 lmask = mask;
- u32 hmask = mask >> 32;
+ u32 lmask;
+ u32 hmask;
int err;
+ /* Optimize away writing unnecessary xfeatures: */
+ if (fpu_state_size_dynamic())
+ mask &= xfeatures_need_sigframe_write();
+
+ lmask = mask;
+ hmask = mask >> 32;
xfd_validate_state(fpstate, mask, false);
stac();