aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/futex.h9
-rw-r--r--arch/arm64/kernel/ptrace.c7
-rw-r--r--arch/powerpc/Kconfig2
-rw-r--r--arch/s390/include/asm/pci_io.h10
-rw-r--r--arch/s390/kernel/machine_kexec_file.c2
-rw-r--r--arch/s390/kernel/machine_kexec_reloc.c1
-rw-r--r--arch/s390/pci/pci_mmio.c213
-rw-r--r--arch/x86/include/asm/kvm_host.h1
-rw-r--r--arch/x86/kernel/apic/apic.c27
-rw-r--r--arch/x86/kernel/unwind_orc.c7
-rw-r--r--arch/x86/kvm/svm.c13
-rw-r--r--arch/x86/kvm/vmx/vmx.c18
-rw-r--r--arch/x86/kvm/x86.c17
-rw-r--r--arch/x86/mm/pageattr.c12
14 files changed, 286 insertions, 53 deletions
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 83c391b597d4..fdc4ae3e7378 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -164,8 +164,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
preempt_enable();
#endif
- if (!ret)
- *oval = oldval;
+ /*
+ * Store unconditionally. If ret != 0 the extra store is the least
+ * of the worries but GCC cannot figure out that __futex_atomic_op()
+ * is either setting ret to -EFAULT or storing the old value in
+ * oldval which results in a uninitialized warning at the call site.
+ */
+ *oval = oldval;
return ret;
}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 9168c4f1a37f..8d2d9d5b418f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1829,10 +1829,11 @@ static void tracehook_report_syscall(struct pt_regs *regs,
int syscall_trace_enter(struct pt_regs *regs)
{
- if (test_thread_flag(TIF_SYSCALL_TRACE) ||
- test_thread_flag(TIF_SYSCALL_EMU)) {
+ unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
+ if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
- if (!in_syscall(regs) || test_thread_flag(TIF_SYSCALL_EMU))
+ if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU))
return -1;
}
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 0d3c76b6a535..7f9fead5fec9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -133,7 +133,7 @@ config PPC
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_MEMBARRIER_CALLBACKS
select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
- select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
+ select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION)
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_HAS_UACCESS_FLUSHCACHE
select ARCH_HAS_UACCESS_MCSAFE if PPC64
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cd060b5dd8fd..e4dc64cc9c55 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -8,6 +8,10 @@
#include <linux/slab.h>
#include <asm/pci_insn.h>
+/* I/O size constraints */
+#define ZPCI_MAX_READ_SIZE 8
+#define ZPCI_MAX_WRITE_SIZE 128
+
/* I/O Map */
#define ZPCI_IOMAP_SHIFT 48
#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL
@@ -140,7 +144,8 @@ static inline int zpci_memcpy_fromio(void *dst,
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) src,
- (u64) dst, n, 8);
+ (u64) dst, n,
+ ZPCI_MAX_READ_SIZE);
rc = zpci_read_single(dst, src, size);
if (rc)
break;
@@ -161,7 +166,8 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) dst,
- (u64) src, n, 128);
+ (u64) src, n,
+ ZPCI_MAX_WRITE_SIZE);
if (size > 8) /* main path */
rc = zpci_write_block(dst, src, size);
else
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 8415ae7d2a23..f9e4baa64b67 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -151,7 +151,7 @@ static int kexec_file_add_initrd(struct kimage *image,
buf.mem += crashk_res.start;
buf.memsz = buf.bufsz;
- data->parm->initrd_start = buf.mem;
+ data->parm->initrd_start = data->memsz;
data->parm->initrd_size = buf.memsz;
data->memsz += buf.memsz;
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
index d5035de9020e..b7182cec48dc 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -28,6 +28,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
break;
case R_390_64: /* Direct 64 bit. */
case R_390_GLOB_DAT:
+ case R_390_JMP_SLOT:
*(u64 *)loc = val;
break;
case R_390_PC16: /* PC relative 16 bit. */
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 7d42a8794f10..020a2c514d96 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -11,6 +11,113 @@
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/pci.h>
+#include <asm/pci_io.h>
+#include <asm/pci_debug.h>
+
+static inline void zpci_err_mmio(u8 cc, u8 status, u64 offset)
+{
+ struct {
+ u64 offset;
+ u8 cc;
+ u8 status;
+ } data = {offset, cc, status};
+
+ zpci_err_hex(&data, sizeof(data));
+}
+
+static inline int __pcistb_mio_inuser(
+ void __iomem *ioaddr, const void __user *src,
+ u64 len, u8 *status)
+{
+ int cc = -ENXIO;
+
+ asm volatile (
+ " sacf 256\n"
+ "0: .insn rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n"
+ "1: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "2: sacf 768\n"
+ EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+ : [cc] "+d" (cc), [len] "+d" (len)
+ : [ioaddr] "a" (ioaddr), [src] "Q" (*((u8 __force *)src))
+ : "cc", "memory");
+ *status = len >> 24 & 0xff;
+ return cc;
+}
+
+static inline int __pcistg_mio_inuser(
+ void __iomem *ioaddr, const void __user *src,
+ u64 ulen, u8 *status)
+{
+ register u64 addr asm("2") = (u64 __force) ioaddr;
+ register u64 len asm("3") = ulen;
+ int cc = -ENXIO;
+ u64 val = 0;
+ u64 cnt = ulen;
+ u8 tmp;
+
+ /*
+ * copy 0 < @len <= 8 bytes from @src into the right most bytes of
+ * a register, then store it to PCI at @ioaddr while in secondary
+ * address space. pcistg then uses the user mappings.
+ */
+ asm volatile (
+ " sacf 256\n"
+ "0: llgc %[tmp],0(%[src])\n"
+ " sllg %[val],%[val],8\n"
+ " aghi %[src],1\n"
+ " ogr %[val],%[tmp]\n"
+ " brctg %[cnt],0b\n"
+ "1: .insn rre,0xb9d40000,%[val],%[ioaddr]\n"
+ "2: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ "3: sacf 768\n"
+ EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+ :
+ [src] "+a" (src), [cnt] "+d" (cnt),
+ [val] "+d" (val), [tmp] "=d" (tmp),
+ [len] "+d" (len), [cc] "+d" (cc),
+ [ioaddr] "+a" (addr)
+ :: "cc", "memory");
+ *status = len >> 24 & 0xff;
+
+ /* did we read everything from user memory? */
+ if (!cc && cnt != 0)
+ cc = -EFAULT;
+
+ return cc;
+}
+
+static inline int __memcpy_toio_inuser(void __iomem *dst,
+ const void __user *src, size_t n)
+{
+ int size, rc = 0;
+ u8 status = 0;
+ mm_segment_t old_fs;
+
+ if (!src)
+ return -EINVAL;
+
+ old_fs = enable_sacf_uaccess();
+ while (n > 0) {
+ size = zpci_get_max_write_size((u64 __force) dst,
+ (u64 __force) src, n,
+ ZPCI_MAX_WRITE_SIZE);
+ if (size > 8) /* main path */
+ rc = __pcistb_mio_inuser(dst, src, size, &status);
+ else
+ rc = __pcistg_mio_inuser(dst, src, size, &status);
+ if (rc)
+ break;
+ src += size;
+ dst += size;
+ n -= size;
+ }
+ disable_sacf_uaccess(old_fs);
+ if (rc)
+ zpci_err_mmio(rc, status, (__force u64) dst);
+ return rc;
+}
static long get_pfn(unsigned long user_addr, unsigned long access,
unsigned long *pfn)
@@ -46,6 +153,20 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
return -EINVAL;
+
+ /*
+ * Only support read access to MIO capable devices on a MIO enabled
+ * system. Otherwise we would have to check for every address if it is
+ * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+ * don't need for MIO capable devices.
+ */
+ if (static_branch_likely(&have_mio)) {
+ ret = __memcpy_toio_inuser((void __iomem *) mmio_addr,
+ user_buffer,
+ length);
+ return ret;
+ }
+
if (length > 64) {
buf = kmalloc(length, GFP_KERNEL);
if (!buf)
@@ -56,7 +177,8 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
if (ret)
goto out;
- io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+ io_addr = (void __iomem *)((pfn << PAGE_SHIFT) |
+ (mmio_addr & ~PAGE_MASK));
ret = -EFAULT;
if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
@@ -72,6 +194,78 @@ out:
return ret;
}
+static inline int __pcilg_mio_inuser(
+ void __user *dst, const void __iomem *ioaddr,
+ u64 ulen, u8 *status)
+{
+ register u64 addr asm("2") = (u64 __force) ioaddr;
+ register u64 len asm("3") = ulen;
+ u64 cnt = ulen;
+ int shift = ulen * 8;
+ int cc = -ENXIO;
+ u64 val, tmp;
+
+ /*
+ * read 0 < @len <= 8 bytes from the PCI memory mapped at @ioaddr (in
+ * user space) into a register using pcilg then store these bytes at
+ * user address @dst
+ */
+ asm volatile (
+ " sacf 256\n"
+ "0: .insn rre,0xb9d60000,%[val],%[ioaddr]\n"
+ "1: ipm %[cc]\n"
+ " srl %[cc],28\n"
+ " ltr %[cc],%[cc]\n"
+ " jne 4f\n"
+ "2: ahi %[shift],-8\n"
+ " srlg %[tmp],%[val],0(%[shift])\n"
+ "3: stc %[tmp],0(%[dst])\n"
+ " aghi %[dst],1\n"
+ " brctg %[cnt],2b\n"
+ "4: sacf 768\n"
+ EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+ :
+ [cc] "+d" (cc), [val] "=d" (val), [len] "+d" (len),
+ [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp),
+ [shift] "+d" (shift)
+ :
+ [ioaddr] "a" (addr)
+ : "cc", "memory");
+
+ /* did we write everything to the user space buffer? */
+ if (!cc && cnt != 0)
+ cc = -EFAULT;
+
+ *status = len >> 24 & 0xff;
+ return cc;
+}
+
+static inline int __memcpy_fromio_inuser(void __user *dst,
+ const void __iomem *src,
+ unsigned long n)
+{
+ int size, rc = 0;
+ u8 status;
+ mm_segment_t old_fs;
+
+ old_fs = enable_sacf_uaccess();
+ while (n > 0) {
+ size = zpci_get_max_write_size((u64 __force) src,
+ (u64 __force) dst, n,
+ ZPCI_MAX_READ_SIZE);
+ rc = __pcilg_mio_inuser(dst, src, size, &status);
+ if (rc)
+ break;
+ src += size;
+ dst += size;
+ n -= size;
+ }
+ disable_sacf_uaccess(old_fs);
+ if (rc)
+ zpci_err_mmio(rc, status, (__force u64) dst);
+ return rc;
+}
+
SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
void __user *, user_buffer, size_t, length)
{
@@ -86,12 +280,27 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
return -EINVAL;
+
+ /*
+ * Only support write access to MIO capable devices on a MIO enabled
+ * system. Otherwise we would have to check for every address if it is
+ * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+ * don't need for MIO capable devices.
+ */
+ if (static_branch_likely(&have_mio)) {
+ ret = __memcpy_fromio_inuser(
+ user_buffer, (const void __iomem *)mmio_addr,
+ length);
+ return ret;
+ }
+
if (length > 64) {
buf = kmalloc(length, GFP_KERNEL);
if (!buf)
return -ENOMEM;
- } else
+ } else {
buf = local_buf;
+ }
ret = get_pfn(mmio_addr, VM_READ, &pfn);
if (ret)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f5341edbfa16..7d91a3f5b26a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -550,6 +550,7 @@ struct kvm_vcpu_arch {
unsigned long cr4;
unsigned long cr4_guest_owned_bits;
unsigned long cr8;
+ u32 host_pkru;
u32 pkru;
u32 hflags;
u64 efer;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index df891f874614..25b8c45467fc 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
* According to Intel, MFENCE can do the serialization here.
*/
asm volatile("mfence" : : : "memory");
-
- printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
return;
}
@@ -552,7 +550,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
#define DEADLINE_MODEL_MATCH_REV(model, rev) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev }
-static u32 hsx_deadline_rev(void)
+static __init u32 hsx_deadline_rev(void)
{
switch (boot_cpu_data.x86_stepping) {
case 0x02: return 0x3a; /* EP */
@@ -562,7 +560,7 @@ static u32 hsx_deadline_rev(void)
return ~0U;
}
-static u32 bdx_deadline_rev(void)
+static __init u32 bdx_deadline_rev(void)
{
switch (boot_cpu_data.x86_stepping) {
case 0x02: return 0x00000011;
@@ -574,7 +572,7 @@ static u32 bdx_deadline_rev(void)
return ~0U;
}
-static u32 skx_deadline_rev(void)
+static __init u32 skx_deadline_rev(void)
{
switch (boot_cpu_data.x86_stepping) {
case 0x03: return 0x01000136;
@@ -587,7 +585,7 @@ static u32 skx_deadline_rev(void)
return ~0U;
}
-static const struct x86_cpu_id deadline_match[] = {
+static const struct x86_cpu_id deadline_match[] __initconst = {
DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev),
DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020),
DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D, bdx_deadline_rev),
@@ -609,18 +607,19 @@ static const struct x86_cpu_id deadline_match[] = {
{},
};
-static void apic_check_deadline_errata(void)
+static __init bool apic_validate_deadline_timer(void)
{
const struct x86_cpu_id *m;
u32 rev;
- if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
- boot_cpu_has(X86_FEATURE_HYPERVISOR))
- return;
+ if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return false;
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return true;
m = x86_match_cpu(deadline_match);
if (!m)
- return;
+ return true;
/*
* Function pointers will have the MSB set due to address layout,
@@ -632,11 +631,12 @@ static void apic_check_deadline_errata(void)
rev = (u32)m->driver_data;
if (boot_cpu_data.microcode >= rev)
- return;
+ return true;
setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; "
"please update microcode to version: 0x%x (or later)\n", rev);
+ return false;
}
/*
@@ -2098,7 +2098,8 @@ void __init init_apic_mappings(void)
{
unsigned int new_apicid;
- apic_check_deadline_errata();
+ if (apic_validate_deadline_timer())
+ pr_debug("TSC deadline timer available\n");
if (x2apic_mode) {
boot_cpu_physical_apicid = read_apic_id();
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 647e6af0883d..aa0f39dc8129 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -311,12 +311,19 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address);
unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
{
+ struct task_struct *task = state->task;
+
if (unwind_done(state))
return NULL;
if (state->regs)
return &state->regs->ip;
+ if (task != current && state->sp == task->thread.sp) {
+ struct inactive_task_frame *frame = (void *)task->thread.sp;
+ return &frame->ret_addr;
+ }
+
if (state->sp)
return (unsigned long *)state->sp - 1;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fda2126f9a97..cc7da664fd39 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -998,33 +998,32 @@ static void svm_cpu_uninit(int cpu)
static int svm_cpu_init(int cpu)
{
struct svm_cpu_data *sd;
- int r;
sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
if (!sd)
return -ENOMEM;
sd->cpu = cpu;
- r = -ENOMEM;
sd->save_area = alloc_page(GFP_KERNEL);
if (!sd->save_area)
- goto err_1;
+ goto free_cpu_data;
if (svm_sev_enabled()) {
- r = -ENOMEM;
sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
sizeof(void *),
GFP_KERNEL);
if (!sd->sev_vmcbs)
- goto err_1;
+ goto free_save_area;
}
per_cpu(svm_data, cpu) = sd;
return 0;
-err_1:
+free_save_area:
+ __free_page(sd->save_area);
+free_cpu_data:
kfree(sd);
- return r;
+ return -ENOMEM;
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 72f51275247e..7a2c05277f4c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1360,7 +1360,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vmx_vcpu_pi_load(vcpu, cpu);
- vmx->host_pkru = read_pkru();
vmx->host_debugctlmsr = get_debugctlmsr();
}
@@ -6521,11 +6520,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
kvm_load_guest_xcr0(vcpu);
- if (static_cpu_has(X86_FEATURE_PKU) &&
- kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
- vcpu->arch.pkru != vmx->host_pkru)
- __write_pkru(vcpu->arch.pkru);
-
pt_guest_enter(vmx);
atomic_switch_perf_msrs(vmx);
@@ -6614,18 +6608,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
pt_guest_exit(vmx);
- /*
- * eager fpu is enabled if PKEY is supported and CR4 is switched
- * back on host, so it is safe to read guest PKRU from current
- * XSAVE.
- */
- if (static_cpu_has(X86_FEATURE_PKU) &&
- kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
- vcpu->arch.pkru = rdpkru();
- if (vcpu->arch.pkru != vmx->host_pkru)
- __write_pkru(vmx->host_pkru);
- }
-
kvm_put_guest_xcr0(vcpu);
vmx->nested.nested_run_pending = 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7b62c8ee1742..0b2028536848 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -832,11 +832,25 @@ void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
vcpu->guest_xcr0_loaded = 1;
}
+
+ if (static_cpu_has(X86_FEATURE_PKU) &&
+ (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+ (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
+ vcpu->arch.pkru != vcpu->arch.host_pkru)
+ __write_pkru(vcpu->arch.pkru);
}
EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
+ if (static_cpu_has(X86_FEATURE_PKU) &&
+ (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+ (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+ vcpu->arch.pkru = rdpkru();
+ if (vcpu->arch.pkru != vcpu->arch.host_pkru)
+ __write_pkru(vcpu->arch.host_pkru);
+ }
+
if (vcpu->guest_xcr0_loaded) {
if (vcpu->arch.xcr0 != host_xcr0)
xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
@@ -8230,6 +8244,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
trace_kvm_entry(vcpu->vcpu_id);
guest_enter_irqoff();
+ /* Save host pkru register if supported */
+ vcpu->arch.host_pkru = read_pkru();
+
fpregs_assert_state_consistent();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
switch_fpu_return();
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a19a71b4d185..281e584cfe39 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -42,7 +42,8 @@ struct cpa_data {
unsigned long pfn;
unsigned int flags;
unsigned int force_split : 1,
- force_static_prot : 1;
+ force_static_prot : 1,
+ force_flush_all : 1;
struct page **pages;
};
@@ -352,10 +353,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
return;
}
- if (cpa->numpages <= tlb_single_page_flush_ceiling)
- on_each_cpu(__cpa_flush_tlb, cpa, 1);
- else
+ if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
flush_tlb_all();
+ else
+ on_each_cpu(__cpa_flush_tlb, cpa, 1);
if (!cache)
return;
@@ -1584,6 +1585,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
alias_cpa.curpage = 0;
+ cpa->force_flush_all = 1;
+
ret = __change_page_attr_set_clr(&alias_cpa, 0);
if (ret)
return ret;
@@ -1604,6 +1607,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
alias_cpa.curpage = 0;
+ cpa->force_flush_all = 1;
/*
* The high mapping range is imprecise, so ignore the
* return value.
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-09 18:56:16 +0000