summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/fpu/xstate.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/fpu/xstate.c')
-rw-r--r--arch/x86/kernel/fpu/xstate.c177
1 files changed, 116 insertions, 61 deletions
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6a41d1610d8b..9aa9ac8399ae 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -14,13 +14,15 @@
#include <linux/proc_fs.h>
#include <linux/vmalloc.h>
#include <linux/coredump.h>
+#include <linux/sort.h>
#include <asm/fpu/api.h>
#include <asm/fpu/regset.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/xcr.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
+#include <asm/msr.h>
#include <asm/tlbflush.h>
#include <asm/prctl.h>
#include <asm/elf.h>
@@ -62,6 +64,7 @@ static const char *xfeature_names[] =
"unknown xstate feature",
"AMX Tile config",
"AMX Tile data",
+ "APX registers",
"unknown xstate feature",
};
@@ -80,6 +83,7 @@ static unsigned short xsave_cpuid_features[] __initdata = {
[XFEATURE_CET_USER] = X86_FEATURE_SHSTK,
[XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE,
[XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE,
+ [XFEATURE_APX] = X86_FEATURE_APX,
};
static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
@@ -88,6 +92,31 @@ static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
+/*
+ * Ordering of xstate components in uncompacted format: The xfeature
+ * number does not necessarily indicate its position in the XSAVE buffer.
+ * This array defines the traversal order of xstate features.
+ */
+static unsigned int xfeature_uncompact_order[XFEATURE_MAX] __ro_after_init =
+ { [ 0 ... XFEATURE_MAX - 1] = -1};
+
+static inline unsigned int next_xfeature_order(unsigned int i, u64 mask)
+{
+ for (; xfeature_uncompact_order[i] != -1; i++) {
+ if (mask & BIT_ULL(xfeature_uncompact_order[i]))
+ break;
+ }
+
+ return i;
+}
+
+/* Iterate xstate features in uncompacted order: */
+#define for_each_extended_xfeature_in_order(i, mask) \
+ for (i = 0; \
+ i = next_xfeature_order(i, mask), \
+ xfeature_uncompact_order[i] != -1; \
+ i++)
+
#define XSTATE_FLAG_SUPERVISOR BIT(0)
#define XSTATE_FLAG_ALIGNED64 BIT(1)
@@ -199,7 +228,7 @@ void fpu__init_cpu_xstate(void)
* MSR_IA32_XSS sets supervisor states managed by XSAVES.
*/
if (boot_cpu_has(X86_FEATURE_XSAVES)) {
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
}
@@ -209,16 +238,20 @@ static bool xfeature_enabled(enum xfeature xfeature)
return fpu_kernel_cfg.max_features & BIT_ULL(xfeature);
}
+static int compare_xstate_offsets(const void *xfeature1, const void *xfeature2)
+{
+ return xstate_offsets[*(unsigned int *)xfeature1] -
+ xstate_offsets[*(unsigned int *)xfeature2];
+}
+
/*
* Record the offsets and sizes of various xstates contained
- * in the XSAVE state memory layout.
+ * in the XSAVE state memory layout. Also, create an ordered
+ * list of xfeatures for handling out-of-order offsets.
*/
static void __init setup_xstate_cache(void)
{
- u32 eax, ebx, ecx, edx, i;
- /* start at the beginning of the "extended state" */
- unsigned int last_good_offset = offsetof(struct xregs_state,
- extended_state_area);
+ u32 eax, ebx, ecx, edx, xfeature, i = 0;
/*
* The FP xstates and SSE xstates are legacy states. They are always
* in the fixed offsets in the xsave area in either compacted form
@@ -232,31 +265,30 @@ static void __init setup_xstate_cache(void)
xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state,
xmm_space);
- for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
- cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx);
+ for_each_extended_xfeature(xfeature, fpu_kernel_cfg.max_features) {
+ cpuid_count(CPUID_LEAF_XSTATE, xfeature, &eax, &ebx, &ecx, &edx);
- xstate_sizes[i] = eax;
- xstate_flags[i] = ecx;
+ xstate_sizes[xfeature] = eax;
+ xstate_flags[xfeature] = ecx;
/*
* If an xfeature is supervisor state, the offset in EBX is
* invalid, leave it to -1.
*/
- if (xfeature_is_supervisor(i))
+ if (xfeature_is_supervisor(xfeature))
continue;
- xstate_offsets[i] = ebx;
+ xstate_offsets[xfeature] = ebx;
- /*
- * In our xstate size checks, we assume that the highest-numbered
- * xstate feature has the highest offset in the buffer. Ensure
- * it does.
- */
- WARN_ONCE(last_good_offset > xstate_offsets[i],
- "x86/fpu: misordered xstate at %d\n", last_good_offset);
-
- last_good_offset = xstate_offsets[i];
+ /* Populate the list of xfeatures before sorting */
+ xfeature_uncompact_order[i++] = xfeature;
}
+
+ /*
+ * Sort xfeatures by their offsets to support out-of-order
+ * offsets in the uncompacted format.
+ */
+ sort(xfeature_uncompact_order, i, sizeof(unsigned int), compare_xstate_offsets, NULL);
}
/*
@@ -340,7 +372,8 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
XFEATURE_MASK_BNDCSR | \
XFEATURE_MASK_PASID | \
XFEATURE_MASK_CET_USER | \
- XFEATURE_MASK_XTILE)
+ XFEATURE_MASK_XTILE | \
+ XFEATURE_MASK_APX)
/*
* setup the xstate image representing the init state
@@ -540,6 +573,7 @@ static bool __init check_xstate_against_struct(int nr)
case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg);
case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state);
+ case XFEATURE_APX: return XCHECK_SZ(sz, nr, struct apx_state);
case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
default:
XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
@@ -552,13 +586,20 @@ static bool __init check_xstate_against_struct(int nr)
static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
{
unsigned int topmost = fls64(xfeatures) - 1;
- unsigned int offset = xstate_offsets[topmost];
+ unsigned int offset, i;
if (topmost <= XFEATURE_SSE)
return sizeof(struct xregs_state);
- if (compacted)
+ if (compacted) {
offset = xfeature_get_offset(xfeatures, topmost);
+ } else {
+ /* Walk through the xfeature order to pick the last */
+ for_each_extended_xfeature_in_order(i, xfeatures)
+ topmost = xfeature_uncompact_order[i];
+ offset = xstate_offsets[topmost];
+ }
+
return offset + xstate_sizes[topmost];
}
@@ -639,7 +680,7 @@ static unsigned int __init get_xsave_compacted_size(void)
return get_compacted_size();
/* Disable independent features. */
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor());
/*
* Ask the hardware what size is required of the buffer.
@@ -648,7 +689,7 @@ static unsigned int __init get_xsave_compacted_size(void)
size = get_compacted_size();
/* Re-enable independent features so XSAVES will work on them again. */
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
return size;
}
@@ -711,6 +752,8 @@ static int __init init_xstate_size(void)
*/
static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
{
+ pr_info("x86/fpu: XSAVE disabled\n");
+
fpu_kernel_cfg.max_features = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
@@ -727,7 +770,7 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
*/
init_fpstate.xfd = 0;
- fpstate_reset(&current->thread.fpu);
+ fpstate_reset(x86_task_fpu(current));
}
/*
@@ -775,6 +818,17 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
goto out_disable;
}
+ if (fpu_kernel_cfg.max_features & XFEATURE_MASK_APX &&
+ fpu_kernel_cfg.max_features & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) {
+ /*
+ * This is a problematic CPU configuration where two
+ * conflicting state components are both enumerated.
+ */
+ pr_err("x86/fpu: Both APX/MPX present in the CPU's xstate features: 0x%llx.\n",
+ fpu_kernel_cfg.max_features);
+ goto out_disable;
+ }
+
fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features &
XFEATURE_MASK_INDEPENDENT;
@@ -834,9 +888,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
if (err)
goto out_disable;
- /* Reset the state for the current task */
- fpstate_reset(&current->thread.fpu);
-
/*
* Update info used for ptrace frames; use standard-format size and no
* supervisor xstates:
@@ -852,7 +903,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
init_fpstate.xfeatures = fpu_kernel_cfg.default_features;
if (init_fpstate.size > sizeof(init_fpstate.regs)) {
- pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+ pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d)\n",
sizeof(init_fpstate.regs), init_fpstate.size);
goto out_disable;
}
@@ -864,7 +915,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
* xfeatures mask.
*/
if (xfeatures != fpu_kernel_cfg.max_features) {
- pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n",
+ pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init\n",
xfeatures, fpu_kernel_cfg.max_features);
goto out_disable;
}
@@ -904,12 +955,12 @@ void fpu__resume_cpu(void)
* of XSAVES and MSR_IA32_XSS.
*/
if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
if (fpu_state_size_dynamic())
- wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+ wrmsrq(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd);
}
/*
@@ -1071,10 +1122,9 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
struct xregs_state *xinit = &init_fpstate.regs.xsave;
struct xregs_state *xsave = &fpstate->regs.xsave;
+ unsigned int zerofrom, i, xfeature;
struct xstate_header header;
- unsigned int zerofrom;
u64 mask;
- int i;
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
@@ -1143,15 +1193,16 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
*/
mask = header.xfeatures;
- for_each_extended_xfeature(i, mask) {
+ for_each_extended_xfeature_in_order(i, mask) {
+ xfeature = xfeature_uncompact_order[i];
/*
* If there was a feature or alignment gap, zero the space
* in the destination buffer.
*/
- if (zerofrom < xstate_offsets[i])
- membuf_zero(&to, xstate_offsets[i] - zerofrom);
+ if (zerofrom < xstate_offsets[xfeature])
+ membuf_zero(&to, xstate_offsets[xfeature] - zerofrom);
- if (i == XFEATURE_PKRU) {
+ if (xfeature == XFEATURE_PKRU) {
struct pkru_state pkru = {0};
/*
* PKRU is not necessarily up to date in the
@@ -1161,14 +1212,14 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
membuf_write(&to, &pkru, sizeof(pkru));
} else {
membuf_write(&to,
- __raw_xsave_addr(xsave, i),
- xstate_sizes[i]);
+ __raw_xsave_addr(xsave, xfeature),
+ xstate_sizes[xfeature]);
}
/*
* Keep track of the last copied state in the non-compacted
* target buffer for gap zeroing.
*/
- zerofrom = xstate_offsets[i] + xstate_sizes[i];
+ zerofrom = xstate_offsets[xfeature] + xstate_sizes[xfeature];
}
out:
@@ -1191,8 +1242,8 @@ out:
void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode copy_mode)
{
- __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
- tsk->thread.fpu.fpstate->user_xfeatures,
+ __copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate,
+ x86_task_fpu(tsk)->fpstate->user_xfeatures,
tsk->thread.pkru, copy_mode);
}
@@ -1332,7 +1383,7 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u
int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
const void __user *ubuf)
{
- return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
+ return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru);
}
static bool validate_independent_components(u64 mask)
@@ -1398,9 +1449,9 @@ void xrstors(struct xregs_state *xstate, u64 mask)
}
#if IS_ENABLED(CONFIG_KVM)
-void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature)
+void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature)
{
- void *addr = get_xsave_addr(&fps->regs.xsave, xfeature);
+ void *addr = get_xsave_addr(&fpstate->regs.xsave, xfeature);
if (addr)
memset(addr, 0, xstate_sizes[xfeature]);
@@ -1426,7 +1477,7 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
* The XFD MSR does not match fpstate->xfd. That's invalid when
* the passed in fpstate is current's fpstate.
*/
- if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+ if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd)
return false;
/*
@@ -1503,7 +1554,7 @@ void fpstate_free(struct fpu *fpu)
static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
unsigned int usize, struct fpu_guest *guest_fpu)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
struct fpstate *curfps, *newfps = NULL;
unsigned int fpsize;
bool in_use;
@@ -1596,7 +1647,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
* AVX512.
*/
bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
- struct fpu *fpu = &current->group_leader->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current->group_leader);
struct fpu_state_perm *perm;
unsigned int ksize, usize;
u64 mask;
@@ -1606,16 +1657,20 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
if ((permitted & requested) == requested)
return 0;
- /* Calculate the resulting kernel state size */
+ /*
+ * Calculate the resulting kernel state size. Note, @permitted also
+ * contains supervisor xfeatures even though supervisor are always
+ * permitted for kernel and guest FPUs, and never permitted for user
+ * FPUs.
+ */
mask = permitted | requested;
- /* Take supervisor states into account on the host */
- if (!guest)
- mask |= xfeatures_mask_supervisor();
ksize = xstate_calculate_size(mask, compacted);
- /* Calculate the resulting user state size */
- mask &= XFEATURE_MASK_USER_SUPPORTED;
- usize = xstate_calculate_size(mask, false);
+ /*
+ * Calculate the resulting user state size. Take care not to clobber
+ * the supervisor xfeatures in the new mask!
+ */
+ usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false);
if (!guest) {
ret = validate_sigaltstack(usize);
@@ -1699,7 +1754,7 @@ int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
return -EPERM;
}
- fpu = &current->group_leader->thread.fpu;
+ fpu = x86_task_fpu(current->group_leader);
perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
ksize = perm->__state_size;
usize = perm->__user_state_size;
@@ -1804,7 +1859,7 @@ long fpu_xstate_prctl(int option, unsigned long arg2)
*/
static void avx512_status(struct seq_file *m, struct task_struct *task)
{
- unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+ unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp);
long delta;
if (!timestamp) {
generated by cgit (git 2.34.1) at 2025-05-28 19:41:14 +0000