[PATCH v4 03/10] x86/fpu/xstate: Separate user and supervisor xfeatures mask
From: Yu-cheng Yu
Date: Tue May 12 2020 - 10:57:12 EST
Before the introduction of XSAVES supervisor states, 'xfeatures_mask' is
used at various places to determine XSAVE buffer components and XCR0 bits.
It contains only user xstates. To support supervisor xstates, it is
necessary to separate user and supervisor xstates:
- First, change 'xfeatures_mask' to 'xfeatures_mask_all', which represents
the full set of bits that should ever be set in a kernel XSAVE buffer.
- Introduce xfeatures_mask_supervisor() and xfeatures_mask_user() to
extract relevant xfeatures from xfeatures_mask_all.
Co-developed-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@xxxxxxxxx>
Reviewed-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
---
v3:
- Change xfeature_enabled() type from static int to static bool while at
it.
v2:
- Fix typo in commit log.
- Move xfeatures_mask_supervisor() from xstate.c to xstate.h.
- Remove printing of user xstates from fpu__init_system_xstate().
arch/x86/include/asm/fpu/internal.h | 2 +-
arch/x86/include/asm/fpu/xstate.h | 13 ++++-
arch/x86/kernel/fpu/signal.c | 16 +++++--
arch/x86/kernel/fpu/xstate.c | 73 +++++++++++++++++------------
4 files changed, 67 insertions(+), 37 deletions(-)
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 44c48e34d799..ccb1bb32ad7d 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -92,7 +92,7 @@ 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;
+ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
}
static inline void fpstate_init_fxstate(struct fxregs_state *fx)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index b08fa823425f..92104b298d77 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -51,7 +51,18 @@
#define REX_PREFIX
#endif
-extern u64 xfeatures_mask;
+extern u64 xfeatures_mask_all;
+
+static inline u64 xfeatures_mask_supervisor(void)
+{
+ return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_user(void)
+{
+ return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
+}
+
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/signal.c b/arch/x86/kernel/fpu/signal.c
index 585e3651b98f..3df0cfae535f 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -252,13 +252,17 @@ sanitize_restored_xstate(union fpregs_state *state,
*/
static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
{
+ u64 init_bv;
+
if (use_xsave()) {
if (fx_only) {
- u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+ init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE;
+
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
return copy_user_to_fxregs(buf);
} else {
- u64 init_bv = xfeatures_mask & ~xbv;
+ init_bv = xfeatures_mask_user() & ~xbv;
+
if (unlikely(init_bv))
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
return copy_user_to_xregs(buf, xbv);
@@ -358,7 +362,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
if (use_xsave() && !fx_only) {
- u64 init_bv = xfeatures_mask & ~xfeatures;
+ u64 init_bv = xfeatures_mask_user() & ~xfeatures;
if (using_compacted_format()) {
ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
@@ -389,7 +393,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
fpregs_lock();
if (use_xsave()) {
- u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+ u64 init_bv;
+
+ init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE;
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
}
@@ -465,7 +471,7 @@ void fpu__init_prepare_fx_sw_frame(void)
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
fx_sw_reserved.extended_size = size;
- fx_sw_reserved.xfeatures = xfeatures_mask;
+ fx_sw_reserved.xfeatures = xfeatures_mask_user();
fx_sw_reserved.xstate_size = fpu_user_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 9997df717339..fa71af643025 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -54,9 +54,10 @@ static short xsave_cpuid_features[] __initdata = {
};
/*
- * Mask of xstate features supported by the CPU and the kernel:
+ * This represents the full set of bits that should ever be set in a kernel
+ * XSAVE buffer, both supervisor and user xstates.
*/
-u64 xfeatures_mask __read_mostly;
+u64 xfeatures_mask_all __read_mostly;
static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
@@ -76,7 +77,7 @@ unsigned int fpu_user_xstate_size;
*/
int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
{
- u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+ u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all;
if (unlikely(feature_name)) {
long xfeature_idx, max_idx;
@@ -150,7 +151,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
* None of the feature bits are in init state. So nothing else
* to do for us, as the memory layout is up to date.
*/
- if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+ if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all)
return;
/*
@@ -177,7 +178,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
* in a special way already:
*/
feature_bit = 0x2;
- xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+ xfeatures = (xfeatures_mask_user() & ~xfeatures) >> 2;
/*
* Update all the remaining memory layouts according to their
@@ -205,19 +206,28 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
*/
void fpu__init_cpu_xstate(void)
{
- if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask)
+ u64 unsup_bits;
+
+ if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all)
return;
/*
* Unsupported supervisor xstates should not be found in
* the xfeatures mask.
*/
- WARN_ONCE((xfeatures_mask & XFEATURE_MASK_SUPERVISOR_UNSUPPORTED),
- "x86/fpu: Found unsupported supervisor xstates.\n");
+ unsup_bits = xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
+ WARN_ONCE(unsup_bits, "x86/fpu: Found unsupported supervisor xstates: 0x%llx\n",
+ unsup_bits);
- xfeatures_mask &= ~XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
+ xfeatures_mask_all &= ~XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
cr4_set_bits(X86_CR4_OSXSAVE);
- xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+
+ /*
+ * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
+ * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user
+ * states can be set here.
+ */
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user());
}
/*
@@ -225,9 +235,9 @@ void fpu__init_cpu_xstate(void)
* functions here: one for user xstates and the other for
* system xstates. For now, they are the same.
*/
-static int xfeature_enabled(enum xfeature xfeature)
+static bool xfeature_enabled(enum xfeature xfeature)
{
- return !!(xfeatures_mask & (1UL << xfeature));
+ return xfeatures_mask_all & BIT_ULL(xfeature);
}
/*
@@ -414,7 +424,7 @@ static void __init setup_init_fpu_buf(void)
if (boot_cpu_has(X86_FEATURE_XSAVES))
init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
- xfeatures_mask;
+ xfeatures_mask_all;
/*
* Init all the features state with header.xfeatures being 0x0
@@ -474,7 +484,7 @@ int using_compacted_format(void)
int validate_user_xstate_header(const struct xstate_header *hdr)
{
/* No unknown or supervisor features may be set */
- if (hdr->xfeatures & ~(xfeatures_mask & XFEATURE_MASK_USER_SUPPORTED))
+ if (hdr->xfeatures & ~xfeatures_mask_user())
return -EINVAL;
/* Userspace must use the uncompacted format */
@@ -609,7 +619,7 @@ static void do_extra_xstate_size_checks(void)
/*
- * Get total size of enabled xstates in XCR0/xfeatures_mask.
+ * Get total size of enabled xstates in XCR0 | IA32_XSS.
*
* Note the SDM's wording here. "sub-function 0" only enumerates
* the size of the *user* states. If we use it to size a buffer
@@ -699,7 +709,7 @@ static int __init init_xstate_size(void)
*/
static void fpu__init_disable_system_xstate(void)
{
- xfeatures_mask = 0;
+ xfeatures_mask_all = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
}
@@ -734,16 +744,21 @@ void __init fpu__init_system_xstate(void)
return;
}
+ /*
+ * Find user xstates supported by the processor.
+ */
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
- xfeatures_mask = eax + ((u64)edx << 32);
+ xfeatures_mask_all = eax + ((u64)edx << 32);
- if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+ /* Place supervisor features in xfeatures_mask_all here */
+ if ((xfeatures_mask_user() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
/*
* This indicates that something really unexpected happened
* with the enumeration. Disable XSAVE and try to continue
* booting without it. This is too early to BUG().
*/
- pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n",
+ xfeatures_mask_all);
goto out_disable;
}
@@ -752,10 +767,10 @@ void __init fpu__init_system_xstate(void)
*/
for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
if (!boot_cpu_has(xsave_cpuid_features[i]))
- xfeatures_mask &= ~BIT(i);
+ xfeatures_mask_all &= ~BIT_ULL(i);
}
- xfeatures_mask &= fpu__get_supported_xfeatures_mask();
+ xfeatures_mask_all &= fpu__get_supported_xfeatures_mask();
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
@@ -767,8 +782,7 @@ 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 & XFEATURE_MASK_USER_SUPPORTED);
+ update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user());
fpu__init_prepare_fx_sw_frame();
setup_init_fpu_buf();
@@ -776,7 +790,7 @@ 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,
+ xfeatures_mask_all,
fpu_kernel_xstate_size,
boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
return;
@@ -795,7 +809,7 @@ void fpu__resume_cpu(void)
* Restore XCR0 on xsave capable CPUs:
*/
if (boot_cpu_has(X86_FEATURE_XSAVE))
- xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user());
}
/*
@@ -840,10 +854,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
/*
* We should not ever be requesting features that we
- * have not enabled. Remember that xfeatures_mask is
- * what we write to the XCR0 register.
+ * have not enabled.
*/
- WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)),
+ WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)),
"get of unsupported state");
/*
* This assumes the last 'xsave*' instruction to
@@ -996,7 +1009,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
*/
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
- header.xfeatures &= XFEATURE_MASK_USER_SUPPORTED;
+ header.xfeatures &= xfeatures_mask_user();
/*
* Copy xregs_state->header:
@@ -1080,7 +1093,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
*/
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
- header.xfeatures &= XFEATURE_MASK_USER_SUPPORTED;
+ header.xfeatures &= xfeatures_mask_user();
/*
* Copy xregs_state->header:
--
2.21.0