summaryrefslogtreecommitdiff
path: root/arch/x86/xen
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/xen')
-rw-r--r--arch/x86/xen/enlighten.c17
-rw-r--r--arch/x86/xen/enlighten_pv.c63
-rw-r--r--arch/x86/xen/enlighten_pvh.c19
-rw-r--r--arch/x86/xen/mmu_pv.c4
-rw-r--r--arch/x86/xen/multicalls.c26
-rw-r--r--arch/x86/xen/pmu.c73
-rw-r--r--arch/x86/xen/setup.c3
-rw-r--r--arch/x86/xen/smp_pv.c1
-rw-r--r--arch/x86/xen/suspend.c7
-rw-r--r--arch/x86/xen/xen-asm.S4
-rw-r--r--arch/x86/xen/xen-ops.h8
11 files changed, 99 insertions, 126 deletions
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 43dcd8c7badc..53282dc7d5ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -70,6 +70,9 @@ EXPORT_SYMBOL(xen_start_flags);
*/
struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
+/* Number of pages released from the initial allocation. */
+unsigned long xen_released_pages;
+
static __ref void xen_get_vendor(void)
{
init_cpu_devs();
@@ -100,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void)
void (*func)(void);
/*
- * Xen is supported only on CPUs with CPUID, so testing for
- * X86_FEATURE_CPUID is a test for early_cpu_init() having been
- * run.
- *
* Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
* dependency chain: it is being called via the xen_hypercall static
* call when running as a PVH or HVM guest. Hypercalls need to be
@@ -115,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void)
*/
instrumentation_begin();
- if (!boot_cpu_has(X86_FEATURE_CPUID))
- xen_get_vendor();
+ xen_get_vendor();
if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
@@ -466,6 +464,13 @@ int __init arch_xen_unpopulated_init(struct resource **res)
xen_free_unpopulated_pages(1, &pg);
}
+ /*
+ * Account for the region being in the physmap but unpopulated.
+ * The value in xen_released_pages is used by the balloon
+ * driver to know how much of the physmap is unpopulated and
+ * set an accurate initial memory target.
+ */
+ xen_released_pages += xen_extra_mem[i].n_pfns;
/* Zero so region is not also added to the balloon driver. */
xen_extra_mem[i].n_pfns = 0;
}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 846b5737d320..26bbaf4b7330 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -49,7 +49,7 @@
#include <xen/hvc-console.h>
#include <xen/acpi.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/paravirt.h>
#include <asm/apic.h>
#include <asm/page.h>
@@ -61,6 +61,7 @@
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/msr-index.h>
+#include <asm/msr.h>
#include <asm/traps.h>
#include <asm/setup.h>
#include <asm/desc.h>
@@ -1086,15 +1087,15 @@ static void xen_write_cr4(unsigned long cr4)
native_write_cr4(cr4);
}
-static u64 xen_do_read_msr(unsigned int msr, int *err)
+static u64 xen_do_read_msr(u32 msr, int *err)
{
u64 val = 0; /* Avoid uninitialized value for safe variant. */
- if (pmu_msr_read(msr, &val, err))
+ if (pmu_msr_chk_emulated(msr, &val, true))
return val;
if (err)
- val = native_read_msr_safe(msr, err);
+ *err = native_read_msr_safe(msr, &val);
else
val = native_read_msr(msr);
@@ -1110,17 +1111,9 @@ static u64 xen_do_read_msr(unsigned int msr, int *err)
return val;
}
-static void set_seg(unsigned int which, unsigned int low, unsigned int high,
- int *err)
+static void set_seg(u32 which, u64 base)
{
- u64 base = ((u64)high << 32) | low;
-
- if (HYPERVISOR_set_segment_base(which, base) == 0)
- return;
-
- if (err)
- *err = -EIO;
- else
+ if (HYPERVISOR_set_segment_base(which, base))
WARN(1, "Xen set_segment_base(%u, %llx) failed\n", which, base);
}
@@ -1129,20 +1122,19 @@ static void set_seg(unsigned int which, unsigned int low, unsigned int high,
* With err == NULL write_msr() semantics are selected.
* Supplying an err pointer requires err to be pre-initialized with 0.
*/
-static void xen_do_write_msr(unsigned int msr, unsigned int low,
- unsigned int high, int *err)
+static void xen_do_write_msr(u32 msr, u64 val, int *err)
{
switch (msr) {
case MSR_FS_BASE:
- set_seg(SEGBASE_FS, low, high, err);
+ set_seg(SEGBASE_FS, val);
break;
case MSR_KERNEL_GS_BASE:
- set_seg(SEGBASE_GS_USER, low, high, err);
+ set_seg(SEGBASE_GS_USER, val);
break;
case MSR_GS_BASE:
- set_seg(SEGBASE_GS_KERNEL, low, high, err);
+ set_seg(SEGBASE_GS_KERNEL, val);
break;
case MSR_STAR:
@@ -1158,42 +1150,45 @@ static void xen_do_write_msr(unsigned int msr, unsigned int low,
break;
default:
- if (!pmu_msr_write(msr, low, high, err)) {
- if (err)
- *err = native_write_msr_safe(msr, low, high);
- else
- native_write_msr(msr, low, high);
- }
+ if (pmu_msr_chk_emulated(msr, &val, false))
+ return;
+
+ if (err)
+ *err = native_write_msr_safe(msr, val);
+ else
+ native_write_msr(msr, val);
}
}
-static u64 xen_read_msr_safe(unsigned int msr, int *err)
+static int xen_read_msr_safe(u32 msr, u64 *val)
{
- return xen_do_read_msr(msr, err);
+ int err = 0;
+
+ *val = xen_do_read_msr(msr, &err);
+ return err;
}
-static int xen_write_msr_safe(unsigned int msr, unsigned int low,
- unsigned int high)
+static int xen_write_msr_safe(u32 msr, u64 val)
{
int err = 0;
- xen_do_write_msr(msr, low, high, &err);
+ xen_do_write_msr(msr, val, &err);
return err;
}
-static u64 xen_read_msr(unsigned int msr)
+static u64 xen_read_msr(u32 msr)
{
- int err;
+ int err = 0;
return xen_do_read_msr(msr, xen_msr_safe ? &err : NULL);
}
-static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+static void xen_write_msr(u32 msr, u64 val)
{
int err;
- xen_do_write_msr(msr, low, high, xen_msr_safe ? &err : NULL);
+ xen_do_write_msr(msr, val, xen_msr_safe ? &err : NULL);
}
/* This is called once we have the cpu_possible_mask */
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 0e3d930bcb89..9d25d9373945 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -1,5 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/acpi.h>
+#include <linux/cpufreq.h>
+#include <linux/cpuidle.h>
#include <linux/export.h>
#include <linux/mm.h>
@@ -123,8 +125,23 @@ static void __init pvh_arch_setup(void)
{
pvh_reserve_extra_memory();
- if (xen_initial_domain())
+ if (xen_initial_domain()) {
xen_add_preferred_consoles();
+
+ /*
+ * Disable usage of CPU idle and frequency drivers: when
+ * running as hardware domain the exposed native ACPI tables
+ * causes idle and/or frequency drivers to attach and
+ * malfunction. It's Xen the entity that controls the idle and
+ * frequency states.
+ *
+ * For unprivileged domains the exposed ACPI tables are
+ * fabricated and don't contain such data.
+ */
+ disable_cpuidle();
+ disable_cpufreq();
+ WARN_ON(xen_set_default_idle());
+ }
}
void __init xen_pvh_init(struct boot_params *boot_params)
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 38971c6dcd4b..2a4a8deaf612 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -578,7 +578,6 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
xen_mc_issue(XEN_LAZY_MMU);
}
-#if CONFIG_PGTABLE_LEVELS >= 5
__visible p4dval_t xen_p4d_val(p4d_t p4d)
{
return pte_mfn_to_pfn(p4d.p4d);
@@ -592,7 +591,6 @@ __visible p4d_t xen_make_p4d(p4dval_t p4d)
return native_make_p4d(p4d);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d);
-#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
void (*func)(struct mm_struct *mm, struct page *,
@@ -2222,10 +2220,8 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
.alloc_pud = xen_alloc_pmd_init,
.release_pud = xen_release_pmd_init,
-#if CONFIG_PGTABLE_LEVELS >= 5
.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
-#endif
.enter_mmap = xen_enter_mmap,
.exit_mmap = xen_exit_mmap,
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 10c660fae8b3..7237d56a9d3f 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,14 +54,20 @@ struct mc_debug_data {
static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
static struct mc_debug_data mc_debug_data_early __initdata;
-static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) =
- &mc_debug_data_early;
static struct mc_debug_data __percpu *mc_debug_data_ptr;
DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
static struct static_key mc_debug __ro_after_init;
static bool mc_debug_enabled __initdata;
+static struct mc_debug_data * __ref get_mc_debug(void)
+{
+ if (!mc_debug_data_ptr)
+ return &mc_debug_data_early;
+
+ return this_cpu_ptr(mc_debug_data_ptr);
+}
+
static int __init xen_parse_mc_debug(char *arg)
{
mc_debug_enabled = true;
@@ -71,20 +77,16 @@ static int __init xen_parse_mc_debug(char *arg)
}
early_param("xen_mc_debug", xen_parse_mc_debug);
-void mc_percpu_init(unsigned int cpu)
-{
- per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu);
-}
-
static int __init mc_debug_enable(void)
{
unsigned long flags;
+ struct mc_debug_data __percpu *mcdb;
if (!mc_debug_enabled)
return 0;
- mc_debug_data_ptr = alloc_percpu(struct mc_debug_data);
- if (!mc_debug_data_ptr) {
+ mcdb = alloc_percpu(struct mc_debug_data);
+ if (!mcdb) {
pr_err("xen_mc_debug inactive\n");
static_key_slow_dec(&mc_debug);
return -ENOMEM;
@@ -93,7 +95,7 @@ static int __init mc_debug_enable(void)
/* Be careful when switching to percpu debug data. */
local_irq_save(flags);
xen_mc_flush();
- mc_percpu_init(0);
+ mc_debug_data_ptr = mcdb;
local_irq_restore(flags);
pr_info("xen_mc_debug active\n");
@@ -155,7 +157,7 @@ void xen_mc_flush(void)
trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
if (static_key_false(&mc_debug)) {
- mcdb = __this_cpu_read(mc_debug_data);
+ mcdb = get_mc_debug();
memcpy(mcdb->entries, b->entries,
b->mcidx * sizeof(struct multicall_entry));
}
@@ -235,7 +237,7 @@ struct multicall_space __xen_mc_entry(size_t args)
ret.mc = &b->entries[b->mcidx];
if (static_key_false(&mc_debug)) {
- struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data);
+ struct mc_debug_data *mcdb = get_mc_debug();
mcdb->caller[b->mcidx] = __builtin_return_address(0);
mcdb->argsz[b->mcidx] = args;
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index f06987b0efc3..8f89ce0b67e3 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -2,6 +2,7 @@
#include <linux/types.h>
#include <linux/interrupt.h>
+#include <asm/msr.h>
#include <asm/xen/hypercall.h>
#include <xen/xen.h>
#include <xen/page.h>
@@ -128,7 +129,7 @@ static inline uint32_t get_fam15h_addr(u32 addr)
return addr;
}
-static inline bool is_amd_pmu_msr(unsigned int msr)
+static bool is_amd_pmu_msr(u32 msr)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -194,8 +195,7 @@ static bool is_intel_pmu_msr(u32 msr_index, int *type, int *index)
}
}
-static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
- int index, bool is_read)
+static bool xen_intel_pmu_emulate(u32 msr, u64 *val, int type, int index, bool is_read)
{
uint64_t *reg = NULL;
struct xen_pmu_intel_ctxt *ctxt;
@@ -257,7 +257,7 @@ static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
return false;
}
-static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
+static bool xen_amd_pmu_emulate(u32 msr, u64 *val, bool is_read)
{
uint64_t *reg = NULL;
int i, off = 0;
@@ -298,55 +298,20 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
return false;
}
-static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read,
- bool *emul)
+bool pmu_msr_chk_emulated(u32 msr, u64 *val, bool is_read)
{
int type, index = 0;
if (is_amd_pmu_msr(msr))
- *emul = xen_amd_pmu_emulate(msr, val, is_read);
- else if (is_intel_pmu_msr(msr, &type, &index))
- *emul = xen_intel_pmu_emulate(msr, val, type, index, is_read);
- else
- return false;
-
- return true;
-}
-
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
-{
- bool emulated;
+ return xen_amd_pmu_emulate(msr, val, is_read);
- if (!pmu_msr_chk_emulated(msr, val, true, &emulated))
- return false;
+ if (is_intel_pmu_msr(msr, &type, &index))
+ return xen_intel_pmu_emulate(msr, val, type, index, is_read);
- if (!emulated) {
- *val = err ? native_read_msr_safe(msr, err)
- : native_read_msr(msr);
- }
-
- return true;
-}
-
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
-{
- uint64_t val = ((uint64_t)high << 32) | low;
- bool emulated;
-
- if (!pmu_msr_chk_emulated(msr, &val, false, &emulated))
- return false;
-
- if (!emulated) {
- if (err)
- *err = native_write_msr_safe(msr, low, high);
- else
- native_write_msr(msr, low, high);
- }
-
- return true;
+ return false;
}
-static unsigned long long xen_amd_read_pmc(int counter)
+static u64 xen_amd_read_pmc(int counter)
{
struct xen_pmu_amd_ctxt *ctxt;
uint64_t *counter_regs;
@@ -354,11 +319,12 @@ static unsigned long long xen_amd_read_pmc(int counter)
uint8_t xenpmu_flags = get_xenpmu_flags();
if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
- uint32_t msr;
- int err;
+ u32 msr;
+ u64 val;
msr = amd_counters_base + (counter * amd_msr_step);
- return native_read_msr_safe(msr, &err);
+ native_read_msr_safe(msr, &val);
+ return val;
}
ctxt = &xenpmu_data->pmu.c.amd;
@@ -366,7 +332,7 @@ static unsigned long long xen_amd_read_pmc(int counter)
return counter_regs[counter];
}
-static unsigned long long xen_intel_read_pmc(int counter)
+static u64 xen_intel_read_pmc(int counter)
{
struct xen_pmu_intel_ctxt *ctxt;
uint64_t *fixed_counters;
@@ -375,15 +341,16 @@ static unsigned long long xen_intel_read_pmc(int counter)
uint8_t xenpmu_flags = get_xenpmu_flags();
if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
- uint32_t msr;
- int err;
+ u32 msr;
+ u64 val;
if (counter & (1 << INTEL_PMC_TYPE_SHIFT))
msr = MSR_CORE_PERF_FIXED_CTR0 + (counter & 0xffff);
else
msr = MSR_IA32_PERFCTR0 + counter;
- return native_read_msr_safe(msr, &err);
+ native_read_msr_safe(msr, &val);
+ return val;
}
ctxt = &xenpmu_data->pmu.c.intel;
@@ -396,7 +363,7 @@ static unsigned long long xen_intel_read_pmc(int counter)
return arch_cntr_pair[counter].counter;
}
-unsigned long long xen_read_pmc(int counter)
+u64 xen_read_pmc(int counter)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return xen_amd_read_pmc(counter);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c3db71d96c43..3823e52aef52 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -37,9 +37,6 @@
#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
-/* Number of pages released from the initial allocation. */
-unsigned long xen_released_pages;
-
/* Memory map would allow PCI passthrough. */
bool xen_pv_pci_possible;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 688ff59318ae..9bb8ff8bff30 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -305,7 +305,6 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
return rc;
xen_pmu_init(cpu);
- mc_percpu_init(cpu);
/*
* Why is this a BUG? If the hypercall fails then everything can be
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 77a6ea1c60e4..ba2f17e64321 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -13,6 +13,7 @@
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
#include <asm/fixmap.h>
+#include <asm/msr.h>
#include "xen-ops.h"
@@ -39,7 +40,7 @@ void xen_arch_post_suspend(int cancelled)
static void xen_vcpu_notify_restore(void *data)
{
if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
- wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+ wrmsrq(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
/* Boot processor notified via generic timekeeping_resume() */
if (smp_processor_id() == 0)
@@ -55,9 +56,9 @@ static void xen_vcpu_notify_suspend(void *data)
tick_suspend_local();
if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
- rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+ rdmsrq(MSR_IA32_SPEC_CTRL, tmp);
this_cpu_write(spec_ctrl, tmp);
- wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ wrmsrq(MSR_IA32_SPEC_CTRL, 0);
}
}
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 109af12f7647..461bb1526502 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -226,9 +226,7 @@ SYM_CODE_END(xen_early_idt_handler_array)
push %rax
mov $__HYPERVISOR_iret, %eax
syscall /* Do the IRET. */
-#ifdef CONFIG_MITIGATION_SLS
- int3
-#endif
+ ud2 /* The SYSCALL should never return. */
.endm
SYM_CODE_START(xen_iret)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 63c13a2ccf55..090349baec09 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -261,9 +261,6 @@ void xen_mc_callback(void (*fn)(void *), void *data);
*/
struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size);
-/* Do percpu data initialization for multicalls. */
-void mc_percpu_init(unsigned int cpu);
-
extern bool is_xen_pmu;
irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id);
@@ -274,10 +271,9 @@ void xen_pmu_finish(int cpu);
static inline void xen_pmu_init(int cpu) {}
static inline void xen_pmu_finish(int cpu) {}
#endif
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
+bool pmu_msr_chk_emulated(u32 msr, u64 *val, bool is_read);
int pmu_apic_update(uint32_t reg);
-unsigned long long xen_read_pmc(int counter);
+u64 xen_read_pmc(int counter);
#ifdef CONFIG_SMP
generated by cgit (git 2.34.1) at 2025-06-02 15:30:03 +0000