summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/mach-rockchip/platsmp.c15
-rw-r--r--arch/arm/mach-tegra/reset.c2
-rw-r--r--arch/arm64/boot/dts/ti/k3-j722s-evm.dts4
-rw-r--r--arch/arm64/include/asm/acpi.h2
-rw-r--r--arch/arm64/kernel/acpi.c10
-rw-r--r--arch/arm64/kernel/stacktrace.c2
-rw-r--r--arch/arm64/kernel/traps.c1
-rw-r--r--arch/arm64/mm/fault.c1
-rw-r--r--arch/arm64/mm/ptdump_debugfs.c3
-rw-r--r--arch/loongarch/kernel/env.c13
-rw-r--r--arch/loongarch/kernel/relocate_kernel.S2
-rw-r--r--arch/loongarch/kernel/unwind_orc.c2
-rw-r--r--arch/loongarch/net/bpf_jit.c21
-rw-r--r--arch/mips/include/asm/vpe.h8
-rw-r--r--arch/mips/kernel/process.c16
-rw-r--r--arch/mips/lantiq/falcon/sysctrl.c23
-rw-r--r--arch/parisc/Makefile2
-rw-r--r--arch/powerpc/include/asm/floppy.h5
-rw-r--r--arch/powerpc/platforms/512x/mpc512x_lpbfifo.c6
-rw-r--r--arch/riscv/mm/ptdump.c3
-rw-r--r--arch/s390/include/asm/timex.h13
-rw-r--r--arch/s390/kernel/early.c1
-rw-r--r--arch/s390/kernel/time.c2
-rw-r--r--arch/s390/mm/dump_pagetables.c2
-rw-r--r--arch/um/include/asm/thread_info.h4
-rw-r--r--arch/um/kernel/process.c20
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h15
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/kernel/cpu/bugs.c5
-rw-r--r--arch/x86/kvm/svm/svm.c14
-rw-r--r--arch/x86/kvm/vmx/main.c3
-rw-r--r--arch/x86/kvm/vmx/nested.c21
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c8
-rw-r--r--arch/x86/kvm/vmx/vmx.c57
-rw-r--r--arch/x86/kvm/vmx/vmx.h26
-rw-r--r--arch/x86/kvm/vmx/x86_ops.h2
-rw-r--r--arch/x86/kvm/x86.c25
38 files changed, 224 insertions, 137 deletions
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index 36915a073c23..f432d22bfed8 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -279,11 +279,6 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
}
if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) {
- if (rockchip_smp_prepare_sram(node)) {
- of_node_put(node);
- return;
- }
-
/* enable the SCU power domain */
pmu_set_power_domain(PMU_PWRDN_SCU, true);
@@ -316,11 +311,19 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
asm ("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
ncores = ((l2ctlr >> 24) & 0x3) + 1;
}
- of_node_put(node);
/* Make sure that all cores except the first are really off */
for (i = 1; i < ncores; i++)
pmu_set_power_domain(0 + i, false);
+
+ if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) {
+ if (rockchip_smp_prepare_sram(node)) {
+ of_node_put(node);
+ return;
+ }
+ }
+
+ of_node_put(node);
}
static void __init rk3036_smp_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c
index d5c805adf7a8..ea706fac6358 100644
--- a/arch/arm/mach-tegra/reset.c
+++ b/arch/arm/mach-tegra/reset.c
@@ -63,7 +63,7 @@ static void __init tegra_cpu_reset_handler_enable(void)
BUG_ON(is_enabled);
BUG_ON(tegra_cpu_reset_handler_size > TEGRA_IRAM_RESET_HANDLER_SIZE);
- memcpy(iram_base, (void *)__tegra_cpu_reset_handler_start,
+ memcpy_toio(iram_base, (void *)__tegra_cpu_reset_handler_start,
tegra_cpu_reset_handler_size);
err = call_firmware_op(set_cpu_boot_addr, 0, reset_address);
diff --git a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
index 710f80a14b64..98fc1c0f86a4 100644
--- a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
+++ b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
@@ -495,8 +495,8 @@
p05-hog {
/* P05 - USB2.0_MUX_SEL */
gpio-hog;
- gpios = <5 GPIO_ACTIVE_HIGH>;
- output-high;
+ gpios = <5 GPIO_ACTIVE_LOW>;
+ output-low;
};
p01_hog: p01-hog {
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index a407f9cd549e..c07a58b96329 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -150,7 +150,7 @@ acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor)
{}
#endif
-static inline const char *acpi_get_enable_method(int cpu)
+static __always_inline const char *acpi_get_enable_method(int cpu)
{
if (acpi_psci_present())
return "psci";
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index e6f66491fbe9..862bb1cba4f0 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -197,6 +197,8 @@ out:
*/
void __init acpi_boot_table_init(void)
{
+ int ret;
+
/*
* Enable ACPI instead of device tree unless
* - ACPI has been disabled explicitly (acpi=off), or
@@ -250,10 +252,12 @@ done:
* behaviour, use acpi=nospcr to disable console in ACPI SPCR
* table as default serial console.
*/
- acpi_parse_spcr(earlycon_acpi_spcr_enable,
+ ret = acpi_parse_spcr(earlycon_acpi_spcr_enable,
!param_acpi_nospcr);
- pr_info("Use ACPI SPCR as default console: %s\n",
- param_acpi_nospcr ? "No" : "Yes");
+ if (!ret || param_acpi_nospcr || !IS_ENABLED(CONFIG_ACPI_SPCR_TABLE))
+ pr_info("Use ACPI SPCR as default console: No\n");
+ else
+ pr_info("Use ACPI SPCR as default console: Yes\n");
if (IS_ENABLED(CONFIG_ACPI_BGRT))
acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 2729faaee4b4..1d60a08a2184 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -123,6 +123,8 @@ kunwind_recover_return_address(struct kunwind_state *state)
orig_pc = kretprobe_find_ret_addr(state->task,
(void *)state->common.fp,
&state->kr_cur);
+ if (!orig_pc)
+ return -EINVAL;
state->common.pc = orig_pc;
}
#endif /* CONFIG_KRETPROBES */
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 563cbce11126..e2e8ffa65aa5 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -921,6 +921,7 @@ void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigne
void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr)
{
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
console_verbose();
pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n",
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 850307b49bab..2d1ebc0c3437 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -798,6 +798,7 @@ static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs)
*/
siaddr = untagged_addr(far);
}
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
return 0;
diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
index 68bf1a125502..1e308328c079 100644
--- a/arch/arm64/mm/ptdump_debugfs.c
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/debugfs.h>
-#include <linux/memory_hotplug.h>
#include <linux/seq_file.h>
#include <asm/ptdump.h>
@@ -9,9 +8,7 @@ static int ptdump_show(struct seq_file *m, void *v)
{
struct ptdump_info *info = m->private;
- get_online_mems();
ptdump_walk(m, info);
- put_online_mems();
return 0;
}
DEFINE_SHOW_ATTRIBUTE(ptdump);
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 27144de5c5fe..c0a5dc9aeae2 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -39,16 +39,19 @@ void __init init_environ(void)
static int __init init_cpu_fullname(void)
{
- struct device_node *root;
int cpu, ret;
- char *model;
+ char *cpuname;
+ const char *model;
+ struct device_node *root;
/* Parsing cpuname from DTS model property */
root = of_find_node_by_path("/");
- ret = of_property_read_string(root, "model", (const char **)&model);
+ ret = of_property_read_string(root, "model", &model);
+ if (ret == 0) {
+ cpuname = kstrdup(model, GFP_KERNEL);
+ loongson_sysconf.cpuname = strsep(&cpuname, " ");
+ }
of_node_put(root);
- if (ret == 0)
- loongson_sysconf.cpuname = strsep(&model, " ");
if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) {
for (cpu = 0; cpu < NR_CPUS; cpu++)
diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S
index 84e6de2fd973..8b5140ac9ea1 100644
--- a/arch/loongarch/kernel/relocate_kernel.S
+++ b/arch/loongarch/kernel/relocate_kernel.S
@@ -109,4 +109,4 @@ SYM_CODE_END(kexec_smp_wait)
relocate_new_kernel_end:
.section ".data"
-SYM_DATA(relocate_new_kernel_size, .long relocate_new_kernel_end - relocate_new_kernel)
+SYM_DATA(relocate_new_kernel_size, .quad relocate_new_kernel_end - relocate_new_kernel)
diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c
index b25722876331..b4b4ac8dbf41 100644
--- a/arch/loongarch/kernel/unwind_orc.c
+++ b/arch/loongarch/kernel/unwind_orc.c
@@ -507,7 +507,7 @@ bool unwind_next_frame(struct unwind_state *state)
state->pc = bt_address(pc);
if (!state->pc) {
- pr_err("cannot find unwind pc at %pK\n", (void *)pc);
+ pr_err("cannot find unwind pc at %p\n", (void *)pc);
goto err;
}
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index fa1500d4aa3e..5ba3249cea98 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -208,11 +208,9 @@ bool bpf_jit_supports_far_kfunc_call(void)
return true;
}
-/* initialized on the first pass of build_body() */
-static int out_offset = -1;
-static int emit_bpf_tail_call(struct jit_ctx *ctx)
+static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn)
{
- int off;
+ int off, tc_ninsn = 0;
u8 tcc = tail_call_reg(ctx);
u8 a1 = LOONGARCH_GPR_A1;
u8 a2 = LOONGARCH_GPR_A2;
@@ -222,7 +220,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
const int idx0 = ctx->idx;
#define cur_offset (ctx->idx - idx0)
-#define jmp_offset (out_offset - (cur_offset))
+#define jmp_offset (tc_ninsn - (cur_offset))
/*
* a0: &ctx
@@ -232,6 +230,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
* if (index >= array->map.max_entries)
* goto out;
*/
+ tc_ninsn = insn ? ctx->offset[insn+1] - ctx->offset[insn] : ctx->offset[0];
off = offsetof(struct bpf_array, map.max_entries);
emit_insn(ctx, ldwu, t1, a1, off);
/* bgeu $a2, $t1, jmp_offset */
@@ -263,15 +262,6 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
emit_insn(ctx, ldd, t3, t2, off);
__build_epilogue(ctx, true);
- /* out: */
- if (out_offset == -1)
- out_offset = cur_offset;
- if (cur_offset != out_offset) {
- pr_err_once("tail_call out_offset = %d, expected %d!\n",
- cur_offset, out_offset);
- return -1;
- }
-
return 0;
toofar:
@@ -916,7 +906,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
/* tail call */
case BPF_JMP | BPF_TAIL_CALL:
mark_tail_call(ctx);
- if (emit_bpf_tail_call(ctx) < 0)
+ if (emit_bpf_tail_call(ctx, i) < 0)
return -EINVAL;
break;
@@ -1342,7 +1332,6 @@ out:
if (tmp_blinded)
bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog);
- out_offset = -1;
return prog;
diff --git a/arch/mips/include/asm/vpe.h b/arch/mips/include/asm/vpe.h
index 61fd4d0aeda4..c0769dc4b853 100644
--- a/arch/mips/include/asm/vpe.h
+++ b/arch/mips/include/asm/vpe.h
@@ -119,4 +119,12 @@ void cleanup_tc(struct tc *tc);
int __init vpe_module_init(void);
void __exit vpe_module_exit(void);
+
+#ifdef CONFIG_MIPS_VPE_LOADER_MT
+void *vpe_alloc(void);
+int vpe_start(void *vpe, unsigned long start);
+int vpe_stop(void *vpe);
+int vpe_free(void *vpe);
+#endif /* CONFIG_MIPS_VPE_LOADER_MT */
+
#endif /* _ASM_VPE_H */
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index b630604c577f..02aa6a04a21d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -690,18 +690,20 @@ unsigned long mips_stack_top(void)
}
/* Space for the VDSO, data page & GIC user page */
- top -= PAGE_ALIGN(current->thread.abi->vdso->size);
- top -= PAGE_SIZE;
- top -= mips_gic_present() ? PAGE_SIZE : 0;
+ if (current->thread.abi) {
+ top -= PAGE_ALIGN(current->thread.abi->vdso->size);
+ top -= PAGE_SIZE;
+ top -= mips_gic_present() ? PAGE_SIZE : 0;
+
+ /* Space to randomize the VDSO base */
+ if (current->flags & PF_RANDOMIZE)
+ top -= VDSO_RANDOMIZE_SIZE;
+ }
/* Space for cache colour alignment */
if (cpu_has_dc_aliases)
top -= shm_align_mask + 1;
- /* Space to randomize the VDSO base */
- if (current->flags & PF_RANDOMIZE)
- top -= VDSO_RANDOMIZE_SIZE;
-
return top;
}
diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c
index 1187729d8cbb..357543996ee6 100644
--- a/arch/mips/lantiq/falcon/sysctrl.c
+++ b/arch/mips/lantiq/falcon/sysctrl.c
@@ -214,19 +214,16 @@ void __init ltq_soc_init(void)
of_node_put(np_syseth);
of_node_put(np_sysgpe);
- if ((request_mem_region(res_status.start, resource_size(&res_status),
- res_status.name) < 0) ||
- (request_mem_region(res_ebu.start, resource_size(&res_ebu),
- res_ebu.name) < 0) ||
- (request_mem_region(res_sys[0].start,
- resource_size(&res_sys[0]),
- res_sys[0].name) < 0) ||
- (request_mem_region(res_sys[1].start,
- resource_size(&res_sys[1]),
- res_sys[1].name) < 0) ||
- (request_mem_region(res_sys[2].start,
- resource_size(&res_sys[2]),
- res_sys[2].name) < 0))
+ if ((!request_mem_region(res_status.start, resource_size(&res_status),
+ res_status.name)) ||
+ (!request_mem_region(res_ebu.start, resource_size(&res_ebu),
+ res_ebu.name)) ||
+ (!request_mem_region(res_sys[0].start, resource_size(&res_sys[0]),
+ res_sys[0].name)) ||
+ (!request_mem_region(res_sys[1].start, resource_size(&res_sys[1]),
+ res_sys[1].name)) ||
+ (!request_mem_region(res_sys[2].start, resource_size(&res_sys[2]),
+ res_sys[2].name)))
pr_err("Failed to request core resources");
status_membase = ioremap(res_status.start,
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 21b8166a6883..9cd9aa3d16f2 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -139,7 +139,7 @@ palo lifimage: vmlinuz
fi
@if test ! -f "$(PALOCONF)"; then \
cp $(srctree)/arch/parisc/defpalo.conf $(objtree)/palo.conf; \
- echo 'A generic palo config file ($(objree)/palo.conf) has been created for you.'; \
+ echo 'A generic palo config file ($(objtree)/palo.conf) has been created for you.'; \
echo 'You should check it and re-run "make palo".'; \
echo 'WARNING: the "lifimage" file is now placed in this directory by default!'; \
false; \
diff --git a/arch/powerpc/include/asm/floppy.h b/arch/powerpc/include/asm/floppy.h
index f8ce178b43b7..34abf8bea2cc 100644
--- a/arch/powerpc/include/asm/floppy.h
+++ b/arch/powerpc/include/asm/floppy.h
@@ -144,9 +144,12 @@ static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
bus_addr = 0;
}
- if (!bus_addr) /* need to map it */
+ if (!bus_addr) { /* need to map it */
bus_addr = dma_map_single(&isa_bridge_pcidev->dev, addr, size,
dir);
+ if (dma_mapping_error(&isa_bridge_pcidev->dev, bus_addr))
+ return -ENOMEM;
+ }
/* remember this one as prev */
prev_addr = addr;
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 9668b052cd4b..f251e0f68262 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -240,10 +240,8 @@ static int mpc512x_lpbfifo_kick(void)
dma_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
/* Make DMA channel work with LPB FIFO data register */
- if (dma_dev->device_config(lpbfifo.chan, &dma_conf)) {
- ret = -EINVAL;
- goto err_dma_prep;
- }
+ if (dma_dev->device_config(lpbfifo.chan, &dma_conf))
+ return -EINVAL;
sg_init_table(&sg, 1);
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 9d5f657a251b..1289cc6d3700 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -6,7 +6,6 @@
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/debugfs.h>
-#include <linux/memory_hotplug.h>
#include <linux/seq_file.h>
#include <linux/ptdump.h>
@@ -371,9 +370,7 @@ bool ptdump_check_wx(void)
static int ptdump_show(struct seq_file *m, void *v)
{
- get_online_mems();
ptdump_walk(m, m->private);
- put_online_mems();
return 0;
}
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 640901f2fbc3..811ec531954b 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -192,13 +192,6 @@ static inline unsigned long get_tod_clock_fast(void)
asm volatile("stckf %0" : "=Q" (clk) : : "cc");
return clk;
}
-
-static inline cycles_t get_cycles(void)
-{
- return (cycles_t) get_tod_clock() >> 2;
-}
-#define get_cycles get_cycles
-
int get_phys_clock(unsigned long *clock);
void init_cpu_timer(void);
@@ -226,6 +219,12 @@ static inline unsigned long get_tod_clock_monotonic(void)
return tod;
}
+static inline cycles_t get_cycles(void)
+{
+ return (cycles_t)get_tod_clock_monotonic() >> 2;
+}
+#define get_cycles get_cycles
+
/**
* tod_to_ns - convert a TOD format value to nanoseconds
* @todval: to be converted TOD format value
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 62f8f5a750a3..0c054e2d1e03 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -183,6 +183,7 @@ void __init __do_early_pgm_check(struct pt_regs *regs)
regs->int_code = lc->pgm_int_code;
regs->int_parm_long = lc->trans_exc_code;
+ regs->last_break = lc->pgm_last_break;
ip = __rewind_psw(regs->psw, regs->int_code >> 16);
/* Monitor Event? Might be a warning */
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index b713effe0579..96fc41f26d7e 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -579,7 +579,7 @@ static int stp_sync_clock(void *data)
atomic_dec(&sync->cpus);
/* Wait for in_sync to be set. */
while (READ_ONCE(sync->in_sync) == 0)
- __udelay(1);
+ ;
}
if (sync->in_sync != 1)
/* Didn't work. Clear per-cpu in sync bit again. */
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index fa54f3bc0c8d..70f184ca648f 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -203,11 +203,9 @@ static int ptdump_show(struct seq_file *m, void *v)
.marker = markers,
};
- get_online_mems();
mutex_lock(&cpa_mutex);
ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
mutex_unlock(&cpa_mutex);
- put_online_mems();
return 0;
}
DEFINE_SHOW_ATTRIBUTE(ptdump);
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index c7b4b49826a2..40d823f36c09 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -68,7 +68,11 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
#define _TIF_MEMDIE (1 << TIF_MEMDIE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
+#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
+#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \
+ _TIF_NOTIFY_RESUME)
+
#endif
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 9c6cf03ed02b..eaeeedd62930 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -81,14 +81,18 @@ struct task_struct *__switch_to(struct task_struct *from, struct task_struct *to
void interrupt_end(void)
{
struct pt_regs *regs = &current->thread.regs;
-
- if (need_resched())
- schedule();
- if (test_thread_flag(TIF_SIGPENDING) ||
- test_thread_flag(TIF_NOTIFY_SIGNAL))
- do_signal(regs);
- if (test_thread_flag(TIF_NOTIFY_RESUME))
- resume_user_mode_work(regs);
+ unsigned long thread_flags;
+
+ thread_flags = read_thread_flags();
+ while (thread_flags & _TIF_WORK_MASK) {
+ if (thread_flags & _TIF_NEED_RESCHED)
+ schedule();
+ if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+ do_signal(regs);
+ if (thread_flags & _TIF_NOTIFY_RESUME)
+ resume_user_mode_work(regs);
+ thread_flags = read_thread_flags();
+ }
}
int get_current_pid(void)
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index cfb22f8c451a..861d080ed4c6 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -47,7 +47,6 @@ KVM_X86_OP(set_idt)
KVM_X86_OP(get_gdt)
KVM_X86_OP(set_gdt)
KVM_X86_OP(sync_dirty_debug_regs)
-KVM_X86_OP(set_dr6)
KVM_X86_OP(set_dr7)
KVM_X86_OP(cache_reg)
KVM_X86_OP(get_rflags)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0caa3293f6db..d27df86aa62c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1627,6 +1627,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
}
+enum kvm_x86_run_flags {
+ KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0),
+ KVM_RUN_LOAD_GUEST_DR6 = BIT(1),
+ KVM_RUN_LOAD_DEBUGCTL = BIT(2),
+};
+
struct kvm_x86_ops {
const char *name;
@@ -1654,6 +1660,12 @@ struct kvm_x86_ops {
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
+ /*
+ * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to
+ * match the host's value even while the guest is active.
+ */
+ const u64 HOST_OWNED_DEBUGCTL;
+
void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
@@ -1675,7 +1687,6 @@ struct kvm_x86_ops {
void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
- void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
@@ -1706,7 +1717,7 @@ struct kvm_x86_ops {
int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
- bool force_immediate_exit);
+ u64 run_flags);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7ebe76f69417..2b6e3127ef4e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -417,6 +417,7 @@
#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12)
#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14
#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+#define DEBUGCTLMSR_RTM_DEBUG BIT(15)
#define MSR_PEBS_FRONTEND 0x000003f7
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c2c7b76d953f..31b4b73e5405 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -71,10 +71,9 @@ void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
static void __init set_return_thunk(void *thunk)
{
- if (x86_return_thunk != __x86_return_thunk)
- pr_warn("x86/bugs: return thunk changed\n");
-
x86_return_thunk = thunk;
+
+ pr_info("active return thunk: %ps\n", thunk);
}
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1f42a71b15c0..800f781475c0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4226,9 +4226,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
guest_state_exit_irqoff();
}
-static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
- bool force_immediate_exit)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_svm *svm = to_svm(vcpu);
bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL);
@@ -4270,10 +4270,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
svm_hv_update_vp_id(svm->vmcb, vcpu);
/*
- * Run with all-zero DR6 unless needed, so that we can get the exact cause
- * of a #DB.
+ * Run with all-zero DR6 unless the guest can write DR6 freely, so that
+ * KVM can get the exact cause of a #DB. Note, loading guest DR6 from
+ * KVM's snapshot is only necessary when DR accesses won't exit.
*/
- if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+ if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6))
+ svm_set_dr6(vcpu, vcpu->arch.dr6);
+ else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
clgi();
@@ -5084,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.set_idt = svm_set_idt,
.get_gdt = svm_get_gdt,
.set_gdt = svm_set_gdt,
- .set_dr6 = svm_set_dr6,
.set_dr7 = svm_set_dr7,
.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
.cache_reg = svm_cache_reg,
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 47476fcc179a..3f83e36a657b 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -42,6 +42,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.vcpu_load = vmx_vcpu_load,
.vcpu_put = vmx_vcpu_put,
+ .HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM,
+
.update_exception_bitmap = vmx_update_exception_bitmap,
.get_feature_msr = vmx_get_feature_msr,
.get_msr = vmx_get_msr,
@@ -60,7 +62,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
.set_gdt = vmx_set_gdt,
- .set_dr6 = vmx_set_dr6,
.set_dr7 = vmx_set_dr7,
.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
.cache_reg = vmx_cache_reg,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 903e874041ac..60bd2791d933 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2653,10 +2653,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
+ vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl);
}
if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -3135,7 +3136,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -3525,7 +3527,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
if (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
- vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read();
if (kvm_mpx_supported() &&
(!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -4576,6 +4578,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
@@ -4766,7 +4774,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
kvm_set_dr(vcpu, 7, 0x400);
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+ vmx_guest_debugctl_write(vcpu, 0);
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
vmcs12->vm_exit_msr_load_count))
@@ -4821,6 +4829,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
}
+ /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */
+ vmx_reload_guest_debugctl(vcpu);
+
/*
* Note that calling vmx_set_{efer,cr0,cr4} is important as they
* handle a variety of side effects to KVM's software model.
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 9c9d4a336166..a5edc623166a 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -605,11 +605,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
*/
static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
{
- u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ u64 data = vmx_guest_debugctl_read();
if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
data &= ~DEBUGCTLMSR_LBR;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+ vmx_guest_debugctl_write(vcpu, data);
}
}
@@ -679,7 +679,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
if (!lbr_desc->event) {
vmx_disable_lbr_msrs_passthrough(vcpu);
- if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+ if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)
goto warn;
if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
goto warn;
@@ -701,7 +701,7 @@ warn:
static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
{
- if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+ if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR))
intel_pmu_release_guest_lbr_event(vcpu);
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9a4ebf3dfbfc..6c185a260c5b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2148,7 +2148,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
break;
case MSR_IA32_DEBUGCTLMSR:
- msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ msr_info->data = vmx_guest_debugctl_read();
break;
default:
find_uret_msr:
@@ -2173,7 +2173,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2185,9 +2185,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
(host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+ if (boot_cpu_has(X86_FEATURE_RTM) &&
+ (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_RTM)))
+ debugctl |= DEBUGCTLMSR_RTM_DEBUG;
+
return debugctl;
}
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
+{
+ u64 invalid;
+
+ invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated);
+ if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) {
+ kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+ invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR);
+ }
+ return !invalid;
+}
+
/*
* Writes msr value into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
@@ -2256,29 +2272,22 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
- case MSR_IA32_DEBUGCTLMSR: {
- u64 invalid;
-
- invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
- if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
- kvm_pr_unimpl_wrmsr(vcpu, msr_index, data);
- data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
- invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
- }
-
- if (invalid)
+ case MSR_IA32_DEBUGCTLMSR:
+ if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated))
return 1;
+ data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
+
if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls &
VM_EXIT_SAVE_DEBUG_CONTROLS)
get_vmcs12(vcpu)->guest_ia32_debugctl = data;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+ vmx_guest_debugctl_write(vcpu, data);
+
if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event &&
(data & DEBUGCTLMSR_LBR))
intel_pmu_create_guest_lbr_event(vcpu);
return 0;
- }
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
(!msr_info->host_initiated &&
@@ -4823,7 +4832,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write32(GUEST_SYSENTER_CS, 0);
vmcs_writel(GUEST_SYSENTER_ESP, 0);
vmcs_writel(GUEST_SYSENTER_EIP, 0);
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+ vmx_guest_debugctl_write(&vmx->vcpu, 0);
if (cpu_has_vmx_tpr_shadow()) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
@@ -5630,12 +5640,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
set_debugreg(DR6_RESERVED, 6);
}
-void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
- lockdep_assert_irqs_disabled();
- set_debugreg(vcpu->arch.dr6, 6);
-}
-
void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
{
vmcs_writel(GUEST_DR7, val);
@@ -7353,8 +7357,9 @@ out:
guest_state_exit_irqoff();
}
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long cr3, cr4;
@@ -7399,6 +7404,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
vcpu->arch.regs_dirty = 0;
+ if (run_flags & KVM_RUN_LOAD_GUEST_DR6)
+ set_debugreg(vcpu->arch.dr6, 6);
+
+ if (run_flags & KVM_RUN_LOAD_DEBUGCTL)
+ vmx_reload_guest_debugctl(vcpu);
+
/*
* Refresh vmcs.HOST_CR3 if necessary. This must be done immediately
* prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index cf57fbf12104..a7e2de50d27f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -435,6 +435,32 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val)
+{
+ WARN_ON_ONCE(val & DEBUGCTLMSR_FREEZE_IN_SMM);
+
+ val |= vcpu->arch.host_debugctl & DEBUGCTLMSR_FREEZE_IN_SMM;
+ vmcs_write64(GUEST_IA32_DEBUGCTL, val);
+}
+
+static inline u64 vmx_guest_debugctl_read(void)
+{
+ return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~DEBUGCTLMSR_FREEZE_IN_SMM;
+}
+
+static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu)
+{
+ u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+ if (!((val ^ vcpu->arch.host_debugctl) & DEBUGCTLMSR_FREEZE_IN_SMM))
+ return;
+
+ vmx_guest_debugctl_write(vcpu, val & ~DEBUGCTLMSR_FREEZE_IN_SMM);
+}
+
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
* the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 4aba200f435d..5e4ce13ab305 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm);
int vmx_vcpu_precreate(struct kvm *kvm);
int vmx_vcpu_create(struct kvm_vcpu *vcpu);
int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
void vmx_vcpu_free(struct kvm_vcpu *vcpu);
void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 213af0fda768..dbd295ef3eba 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10711,6 +10711,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
dm_request_for_irq_injection(vcpu) &&
kvm_cpu_accept_dm_intr(vcpu);
fastpath_t exit_fastpath;
+ u64 run_flags, debug_ctl;
bool req_immediate_exit = false;
@@ -10955,8 +10956,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
- if (req_immediate_exit)
+ run_flags = 0;
+ if (req_immediate_exit) {
+ run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
fpregs_assert_state_consistent();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -10973,12 +10977,22 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
set_debugreg(vcpu->arch.eff_db[3], 3);
/* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
- kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
+ run_flags |= KVM_RUN_LOAD_GUEST_DR6;
} else if (unlikely(hw_breakpoint_active())) {
set_debugreg(DR7_FIXED_1, 7);
}
- vcpu->arch.host_debugctl = get_debugctlmsr();
+ /*
+ * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL
+ * can be modified in IRQ context, e.g. via SMP function calls. Inform
+ * vendor code if any host-owned bits were changed, e.g. so that the
+ * value loaded into hardware while running the guest can be updated.
+ */
+ debug_ctl = get_debugctlmsr();
+ if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL &&
+ !vcpu->arch.guest_state_protected)
+ run_flags |= KVM_RUN_LOAD_DEBUGCTL;
+ vcpu->arch.host_debugctl = debug_ctl;
guest_timing_enter_irqoff();
@@ -10992,8 +11006,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
(kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));
- exit_fastpath = kvm_x86_call(vcpu_run)(vcpu,
- req_immediate_exit);
+ exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags);
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
@@ -11005,6 +11018,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
break;
}
+ run_flags = 0;
+
/* Note, VM-Exits that go down the "slow" path are accounted below. */
++vcpu->stat.exits;
}