Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index ba5a418..218acbd 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -19,6 +19,7 @@
bool "Xen PV guest support"
default y
depends on XEN
+ depends on X86_64
select PARAVIRT_XXL
select XEN_HAVE_PVMMU
select XEN_HAVE_VPMU
@@ -50,7 +51,7 @@
config XEN_512GB
bool "Limit Xen pv-domain memory to 512GB"
- depends on XEN_PV && X86_64
+ depends on XEN_PV
default y
help
Limit paravirtualized user domains to 512GB of RAM.
@@ -62,10 +63,10 @@
boot parameter "xen_512gb_limit".
config XEN_SAVE_RESTORE
- bool
- depends on XEN
- select HIBERNATE_CALLBACKS
- default y
+ bool
+ depends on XEN
+ select HIBERNATE_CALLBACKS
+ default y
config XEN_DEBUG_FS
bool "Enable Xen debug and tuning parameters in debugfs"
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 084de77..fc5c5ba 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y
+OBJECT_FILES_NON_STANDARD_xen-asm.o := y
ifdef CONFIG_FUNCTION_TRACER
# Do not profile debug and lowlevel utilities
@@ -9,9 +9,8 @@
endif
# Make sure early boot has no stackprotector
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_enlighten_pv.o := $(nostackp)
-CFLAGS_mmu_pv.o := $(nostackp)
+CFLAGS_enlighten_pv.o := -fno-stack-protector
+CFLAGS_mmu_pv.o := -fno-stack-protector
obj-y += enlighten.o
obj-y += mmu.o
@@ -34,7 +33,6 @@
obj-$(CONFIG_XEN_PV) += irq.o
obj-$(CONFIG_XEN_PV) += multicalls.o
obj-$(CONFIG_XEN_PV) += xen-asm.o
-obj-$(CONFIG_XEN_PV) += xen-asm_$(BITS).o
obj-$(CONFIG_XEN_PVH) += enlighten_pvh.o
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 5e53bfb..e82fd19 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -1,8 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/init.h>
+#include <linux/thread_info.h>
#include <asm/x86_init.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/xen/hypercall.h>
#include <xen/xen.h>
@@ -58,10 +60,6 @@
if (reg == APIC_LVR)
return 0x14;
-#ifdef CONFIG_X86_32
- if (reg == APIC_LDR)
- return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-#endif
if (reg != APIC_ID)
return 0;
@@ -127,14 +125,6 @@
return initial_apic_id >> index_msb;
}
-#ifdef CONFIG_X86_32
-static int xen_x86_32_early_logical_apicid(int cpu)
-{
- /* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */
- return 1 << cpu;
-}
-#endif
-
static void xen_noop(void)
{
}
@@ -197,11 +187,6 @@
.icr_write = xen_apic_icr_write,
.wait_icr_idle = xen_noop,
.safe_wait_icr_idle = xen_safe_apic_wait_icr_idle,
-
-#ifdef CONFIG_X86_32
- /* generic_processor_info and setup_local_APIC. */
- .x86_32_early_logical_apicid = xen_x86_32_early_logical_apicid,
-#endif
};
static void __init xen_apic_check(void)
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index a04551e..205a9bc 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -29,9 +29,9 @@
.fw_vendor = EFI_INVALID_TABLE_ADDR, /* Initialized later. */
.fw_revision = 0, /* Initialized later. */
.con_in_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
- .con_in = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .con_in = NULL, /* Not used under Xen. */
.con_out_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
- .con_out = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .con_out = NULL, /* Not used under Xen. */
.stderr_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
.stderr = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
.runtime = (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR,
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 205b117..0f68c6d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -51,9 +51,6 @@
DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
-enum xen_domain_type xen_domain_type = XEN_NATIVE;
-EXPORT_SYMBOL_GPL(xen_domain_type);
-
unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
EXPORT_SYMBOL(machine_to_phys_mapping);
unsigned long machine_to_phys_nr;
@@ -68,10 +65,12 @@
EXPORT_SYMBOL_GPL(xen_have_vector_callback);
/*
- * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
- * before clearing the bss.
+ * NB: These need to live in .data or alike because they're used by
+ * xen_prepare_pvh() which runs before clearing the bss.
*/
-uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE;
+EXPORT_SYMBOL_GPL(xen_domain_type);
+uint32_t xen_start_flags __section(".data") = 0;
EXPORT_SYMBOL(xen_start_flags);
/*
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 6024faf..ec50b74 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -11,8 +11,10 @@
#include <asm/cpu.h>
#include <asm/smp.h>
+#include <asm/io_apic.h>
#include <asm/reboot.h>
#include <asm/setup.h>
+#include <asm/idtentry.h>
#include <asm/hypervisor.h>
#include <asm/e820/api.h>
#include <asm/early_ioremap.h>
@@ -118,6 +120,17 @@
this_cpu_write(xen_vcpu_id, smp_processor_id());
}
+DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ inc_irq_stat(irq_hv_callback_count);
+
+ xen_hvm_evtchn_do_upcall();
+
+ set_irq_regs(old_regs);
+}
+
#ifdef CONFIG_KEXEC_CORE
static void xen_hvm_shutdown(void)
{
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index b99074c..804c65d 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -32,7 +32,7 @@
#include <linux/pci.h>
#include <linux/gfp.h>
#include <linux/edd.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
#include <xen/xen.h>
#include <xen/events.h>
@@ -63,7 +63,6 @@
#include <asm/setup.h>
#include <asm/desc.h>
#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
#include <asm/stackprotector.h>
@@ -72,6 +71,9 @@
#include <asm/mwait.h>
#include <asm/pci_x86.h>
#include <asm/cpu.h>
+#ifdef CONFIG_X86_IOPL_IOPERM
+#include <asm/io_bitmap.h>
+#endif
#ifdef CONFIG_ACPI
#include <linux/acpi.h>
@@ -117,14 +119,6 @@
printk(KERN_INFO "Xen version: %d.%d%s%s\n",
version >> 16, version & 0xffff, extra.extraversion,
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
-
-#ifdef CONFIG_X86_32
- pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"
- "Support for running as 32-bit PV-guest under Xen will soon be removed\n"
- "from the Linux kernel!\n"
- "Please use either a 64-bit kernel or switch to HVM or PVH mode!\n"
- "WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n");
-#endif
}
static void __init xen_pv_init_platform(void)
@@ -351,15 +345,13 @@
pte_t *ptep;
pte_t pte;
unsigned long pfn;
- struct page *page;
unsigned char dummy;
+ void *va;
ptep = lookup_address((unsigned long)v, &level);
BUG_ON(ptep == NULL);
pfn = pte_pfn(*ptep);
- page = pfn_to_page(pfn);
-
pte = pfn_pte(pfn, prot);
/*
@@ -384,19 +376,15 @@
preempt_disable();
- probe_kernel_read(&dummy, v, 1);
+ copy_from_kernel_nofault(&dummy, v, 1);
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
- if (!PageHighMem(page)) {
- void *av = __va(PFN_PHYS(pfn));
+ va = __va(PFN_PHYS(pfn));
- if (av != v)
- if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
- BUG();
- } else
- kmap_flush_unused();
+ if (va != v && HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0))
+ BUG();
preempt_enable();
}
@@ -536,30 +524,12 @@
static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
{
/*
- * XXX sleazy hack: If we're being called in a lazy-cpu zone
- * and lazy gs handling is enabled, it means we're in a
- * context switch, and %gs has just been saved. This means we
- * can zero it out to prevent faults on exit from the
- * hypervisor if the next process has no %gs. Either way, it
- * has been saved, and the new value will get loaded properly.
- * This will go away as soon as Xen has been modified to not
- * save/restore %gs for normal hypercalls.
- *
- * On x86_64, this hack is not used for %gs, because gs points
- * to KERNEL_GS_BASE (and uses it for PDA references), so we
- * must not zero %gs on x86_64
- *
- * For x86_64, we need to zero %fs, otherwise we may get an
+ * In lazy mode we need to zero %fs, otherwise we may get an
* exception between the new %fs descriptor being loaded and
* %fs being effectively cleared at __switch_to().
*/
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-#ifdef CONFIG_X86_32
- lazy_load_gs(0);
-#else
+ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
loadsegment(fs, 0);
-#endif
- }
xen_mc_batch();
@@ -570,13 +540,11 @@
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
-#ifdef CONFIG_X86_64
static void xen_load_gs_index(unsigned int idx)
{
if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx))
BUG();
}
-#endif
static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
const void *ptr)
@@ -595,51 +563,90 @@
preempt_enable();
}
-#ifdef CONFIG_X86_64
+void noist_exc_debug(struct pt_regs *regs);
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
+{
+ /* On Xen PV, NMI doesn't use IST. The C part is the sane as native. */
+ exc_nmi(regs);
+}
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
+{
+ /*
+ * There's no IST on Xen PV, but we still need to dispatch
+ * to the correct handler.
+ */
+ if (user_mode(regs))
+ noist_exc_debug(regs);
+ else
+ exc_debug(regs);
+}
+
+DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap)
+{
+ /* This should never happen and there is no way to handle it. */
+ instrumentation_begin();
+ pr_err("Unknown trap in Xen PV mode.");
+ BUG();
+ instrumentation_end();
+}
+
struct trap_array_entry {
void (*orig)(void);
void (*xen)(void);
bool ist_okay;
};
+#define TRAP_ENTRY(func, ist_ok) { \
+ .orig = asm_##func, \
+ .xen = xen_asm_##func, \
+ .ist_okay = ist_ok }
+
+#define TRAP_ENTRY_REDIR(func, ist_ok) { \
+ .orig = asm_##func, \
+ .xen = xen_asm_xenpv_##func, \
+ .ist_okay = ist_ok }
+
static struct trap_array_entry trap_array[] = {
- { debug, xen_xendebug, true },
- { double_fault, xen_double_fault, true },
+ TRAP_ENTRY_REDIR(exc_debug, true ),
+ TRAP_ENTRY(exc_double_fault, true ),
#ifdef CONFIG_X86_MCE
- { machine_check, xen_machine_check, true },
+ TRAP_ENTRY(exc_machine_check, true ),
#endif
- { nmi, xen_xennmi, true },
- { int3, xen_int3, false },
- { overflow, xen_overflow, false },
+ TRAP_ENTRY_REDIR(exc_nmi, true ),
+ TRAP_ENTRY(exc_int3, false ),
+ TRAP_ENTRY(exc_overflow, false ),
#ifdef CONFIG_IA32_EMULATION
{ entry_INT80_compat, xen_entry_INT80_compat, false },
#endif
- { page_fault, xen_page_fault, false },
- { divide_error, xen_divide_error, false },
- { bounds, xen_bounds, false },
- { invalid_op, xen_invalid_op, false },
- { device_not_available, xen_device_not_available, false },
- { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false },
- { invalid_TSS, xen_invalid_TSS, false },
- { segment_not_present, xen_segment_not_present, false },
- { stack_segment, xen_stack_segment, false },
- { general_protection, xen_general_protection, false },
- { spurious_interrupt_bug, xen_spurious_interrupt_bug, false },
- { coprocessor_error, xen_coprocessor_error, false },
- { alignment_check, xen_alignment_check, false },
- { simd_coprocessor_error, xen_simd_coprocessor_error, false },
+ TRAP_ENTRY(exc_page_fault, false ),
+ TRAP_ENTRY(exc_divide_error, false ),
+ TRAP_ENTRY(exc_bounds, false ),
+ TRAP_ENTRY(exc_invalid_op, false ),
+ TRAP_ENTRY(exc_device_not_available, false ),
+ TRAP_ENTRY(exc_coproc_segment_overrun, false ),
+ TRAP_ENTRY(exc_invalid_tss, false ),
+ TRAP_ENTRY(exc_segment_not_present, false ),
+ TRAP_ENTRY(exc_stack_segment, false ),
+ TRAP_ENTRY(exc_general_protection, false ),
+ TRAP_ENTRY(exc_spurious_interrupt_bug, false ),
+ TRAP_ENTRY(exc_coprocessor_error, false ),
+ TRAP_ENTRY(exc_alignment_check, false ),
+ TRAP_ENTRY(exc_simd_coprocessor_error, false ),
};
static bool __ref get_trap_addr(void **addr, unsigned int ist)
{
unsigned int nr;
bool ist_okay = false;
+ bool found = false;
/*
* Replace trap handler addresses by Xen specific ones.
* Check for known traps using IST and whitelist them.
* The debugger ones are the only ones we care about.
- * Xen will handle faults like double_fault, * so we should never see
+ * Xen will handle faults like double_fault, so we should never see
* them. Warn if there's an unexpected IST-using fault handler.
*/
for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) {
@@ -648,6 +655,7 @@
if (*addr == entry->orig) {
*addr = entry->xen;
ist_okay = entry->ist_okay;
+ found = true;
break;
}
}
@@ -658,14 +666,17 @@
nr = (*addr - (void *)early_idt_handler_array[0]) /
EARLY_IDT_HANDLER_SIZE;
*addr = (void *)xen_early_idt_handler_array[nr];
+ found = true;
}
- if (WARN_ON(ist != 0 && !ist_okay))
+ if (!found)
+ *addr = (void *)xen_asm_exc_xen_unknown_trap;
+
+ if (WARN_ON(found && ist != 0 && !ist_okay))
return false;
return true;
}
-#endif
static int cvt_gate_to_trap(int vector, const gate_desc *val,
struct trap_info *info)
@@ -678,10 +689,8 @@
info->vector = vector;
addr = gate_offset(val);
-#ifdef CONFIG_X86_64
if (!get_trap_addr((void **)&addr, val->bits.ist))
return 0;
-#endif /* CONFIG_X86_64 */
info->address = addr;
info->cs = gate_segment(val);
@@ -727,8 +736,8 @@
preempt_enable();
}
-static void xen_convert_trap_info(const struct desc_ptr *desc,
- struct trap_info *traps)
+static unsigned xen_convert_trap_info(const struct desc_ptr *desc,
+ struct trap_info *traps, bool full)
{
unsigned in, out, count;
@@ -738,17 +747,18 @@
for (in = out = 0; in < count; in++) {
gate_desc *entry = (gate_desc *)(desc->address) + in;
- if (cvt_gate_to_trap(in, entry, &traps[out]))
+ if (cvt_gate_to_trap(in, entry, &traps[out]) || full)
out++;
}
- traps[out].address = 0;
+
+ return out;
}
void xen_copy_trap_info(struct trap_info *traps)
{
const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
- xen_convert_trap_info(desc, traps);
+ xen_convert_trap_info(desc, traps, true);
}
/* Load a new IDT into Xen. In principle this can be per-CPU, so we
@@ -758,6 +768,7 @@
{
static DEFINE_SPINLOCK(lock);
static struct trap_info traps[257];
+ unsigned out;
trace_xen_cpu_load_idt(desc);
@@ -765,7 +776,8 @@
memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
- xen_convert_trap_info(desc, traps);
+ out = xen_convert_trap_info(desc, traps, false);
+ memset(&traps[out], 0, sizeof(traps[0]));
xen_mc_flush();
if (HYPERVISOR_set_trap_table(traps))
@@ -837,15 +849,36 @@
this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}
-void xen_set_iopl_mask(unsigned mask)
+#ifdef CONFIG_X86_IOPL_IOPERM
+static void xen_invalidate_io_bitmap(void)
{
- struct physdev_set_iopl set_iopl;
+ struct physdev_set_iobitmap iobitmap = {
+ .bitmap = NULL,
+ .nr_ports = 0,
+ };
- /* Force the change at ring 0. */
- set_iopl.iopl = (mask == 0) ? 1 : (mask >> 12) & 3;
- HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+ native_tss_invalidate_io_bitmap();
+ HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
}
+static void xen_update_io_bitmap(void)
+{
+ struct physdev_set_iobitmap iobitmap;
+ struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
+
+ native_tss_update_io_bitmap();
+
+ iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) +
+ tss->x86_tss.io_bitmap_base;
+ if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID)
+ iobitmap.nr_ports = 0;
+ else
+ iobitmap.nr_ports = IO_BITMAP_BITS;
+
+ HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
+}
+#endif
+
static void xen_io_delay(void)
{
}
@@ -905,15 +938,12 @@
static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
{
int ret;
-#ifdef CONFIG_X86_64
unsigned int which;
u64 base;
-#endif
ret = 0;
switch (msr) {
-#ifdef CONFIG_X86_64
case MSR_FS_BASE: which = SEGBASE_FS; goto set;
case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set;
case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set;
@@ -923,7 +953,6 @@
if (HYPERVISOR_set_segment_base(which, base) != 0)
ret = -EIO;
break;
-#endif
case MSR_STAR:
case MSR_CSTAR:
@@ -1003,11 +1032,7 @@
}
static const struct pv_info xen_info __initconst = {
- .shared_kernel_pmd = 0,
-
-#ifdef CONFIG_X86_64
.extra_user_64bit_cs = FLAT_USER_CS64,
-#endif
.name = "Xen",
};
@@ -1033,18 +1058,14 @@
.read_pmc = xen_read_pmc,
.iret = xen_iret,
-#ifdef CONFIG_X86_64
.usergs_sysret64 = xen_sysret64,
-#endif
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
.load_gdt = xen_load_gdt,
.load_idt = xen_load_idt,
.load_tls = xen_load_tls,
-#ifdef CONFIG_X86_64
.load_gs_index = xen_load_gs_index,
-#endif
.alloc_ldt = xen_alloc_ldt,
.free_ldt = xen_free_ldt,
@@ -1056,12 +1077,12 @@
.write_idt_entry = xen_write_idt_entry,
.load_sp0 = xen_load_sp0,
- .set_iopl_mask = xen_set_iopl_mask,
+#ifdef CONFIG_X86_IOPL_IOPERM
+ .invalidate_io_bitmap = xen_invalidate_io_bitmap,
+ .update_io_bitmap = xen_update_io_bitmap,
+#endif
.io_delay = xen_io_delay,
- /* Xen takes care of %gs when switching to usermode for us */
- .swapgs = paravirt_nop,
-
.start_context_switch = paravirt_start_context_switch,
.end_context_switch = xen_end_context_switch,
};
@@ -1248,16 +1269,16 @@
/* Get mfn list */
xen_build_dynamic_phys_to_machine();
+ /* Work out if we support NX */
+ get_cpu_cap(&boot_cpu_data);
+ x86_configure_nx();
+
/*
* Set up kernel GDT and segment registers, mainly so that
* -fstack-protector code can be executed.
*/
xen_setup_gdt(0);
- /* Work out if we support NX */
- get_cpu_cap(&boot_cpu_data);
- x86_configure_nx();
-
/* Determine virtual and physical address sizes */
get_cpu_address_sizes(&boot_cpu_data);
@@ -1299,7 +1320,7 @@
* any NUMA information the kernel tries to get from ACPI will
* be meaningless. Prevent it from trying.
*/
- acpi_numa = -1;
+ disable_srat();
#endif
WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
@@ -1311,18 +1332,6 @@
xen_start_info->nr_pages);
xen_reserve_special_pages();
- /* keep using Xen gdt for now; no urgent need to change it */
-
-#ifdef CONFIG_X86_32
- pv_info.kernel_rpl = 1;
- if (xen_feature(XENFEAT_supervisor_mode_kernel))
- pv_info.kernel_rpl = 0;
-#else
- pv_info.kernel_rpl = 0;
-#endif
- /* set the limit of our address space */
- xen_reserve_top();
-
/*
* We used to do this in xen_arch_setup, but that is too late
* on AMD were early_cpu_init (run before ->arch_setup()) calls
@@ -1333,12 +1342,6 @@
if (rc != 0)
xen_raw_printk("physdev_op failed %d\n", rc);
-#ifdef CONFIG_X86_32
- /* set up basic CPUID stuff */
- cpu_detect(&new_cpu_data);
- set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
- new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
-#endif
if (xen_start_info->mod_start) {
if (xen_start_info->flags & SIF_MOD_START_PFN)
@@ -1384,10 +1387,6 @@
xen_acpi_sleep_register();
- /* Avoid searching for BIOS MP tables */
- x86_init.mpparse.find_smp_config = x86_init_noop;
- x86_init.mpparse.get_smp_config = x86_init_uint_noop;
-
xen_boot_params_init_edd();
#ifdef CONFIG_ACPI
@@ -1418,12 +1417,8 @@
xen_efi_init(&boot_params);
/* Start the world */
-#ifdef CONFIG_X86_32
- i386_start_kernel();
-#else
cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
x86_64_start_reservations((char *)__pa_symbol(&boot_params));
-#endif
}
static int xen_cpu_up_prepare_pv(unsigned int cpu)
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 80a79db..0d5e34b 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -21,7 +21,7 @@
* The variable xen_pvh needs to live in the data segment since it is used
* after startup_{32|64} is invoked, which will clear the .bss segment.
*/
-bool xen_pvh __attribute__((section(".data"))) = 0;
+bool xen_pvh __section(".data") = 0;
void __init xen_pvh_init(struct boot_params *boot_params)
{
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index ecb0d54..1e681bf 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -21,11 +21,11 @@
#include <xen/grant_table.h>
#include <xen/xen.h>
-#include <asm/pgtable.h>
static struct gnttab_vm_area {
struct vm_struct *area;
pte_t **ptes;
+ int idx;
} gnttab_shared_vm_area, gnttab_status_vm_area;
int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
@@ -91,19 +91,31 @@
}
}
+static int gnttab_apply(pte_t *pte, unsigned long addr, void *data)
+{
+ struct gnttab_vm_area *area = data;
+
+ area->ptes[area->idx++] = pte;
+ return 0;
+}
+
static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
{
area->ptes = kmalloc_array(nr_frames, sizeof(*area->ptes), GFP_KERNEL);
if (area->ptes == NULL)
return -ENOMEM;
-
- area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes);
- if (area->area == NULL) {
- kfree(area->ptes);
- return -ENOMEM;
- }
-
+ area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_IOREMAP);
+ if (!area->area)
+ goto out_free_ptes;
+ if (apply_to_page_range(&init_mm, (unsigned long)area->area->addr,
+ PAGE_SIZE * nr_frames, gnttab_apply, area))
+ goto out_free_vm_area;
return 0;
+out_free_vm_area:
+ free_vm_area(area->area);
+out_free_ptes:
+ kfree(area->ptes);
+ return -ENOMEM;
}
static void arch_gnttab_vfree(struct gnttab_vm_area *area)
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index c8dbee6..cf2ade8 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -51,13 +51,13 @@
#include <linux/memblock.h>
#include <linux/seq_file.h>
#include <linux/crash_dump.h>
+#include <linux/pgtable.h>
#ifdef CONFIG_KEXEC_CORE
#include <linux/kexec.h>
#endif
#include <trace/events/xen.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
#include <asm/mmu_context.h>
@@ -67,7 +67,7 @@
#include <asm/linkage.h>
#include <asm/page.h>
#include <asm/init.h>
-#include <asm/pat.h>
+#include <asm/memtype.h>
#include <asm/smp.h>
#include <asm/tlb.h>
@@ -86,19 +86,8 @@
#include "mmu.h"
#include "debugfs.h"
-#ifdef CONFIG_X86_32
-/*
- * Identity map, in addition to plain kernel map. This needs to be
- * large enough to allocate page table pages to allocate the rest.
- * Each page can map 2MB.
- */
-#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4)
-static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-#endif
-#ifdef CONFIG_X86_64
/* l3 pud for userspace vsyscall mapping */
static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
-#endif /* CONFIG_X86_64 */
/*
* Protects atomic reservation decrease/increase against concurrent increases.
@@ -280,10 +269,7 @@
if (!xen_batched_set_pte(ptep, pteval)) {
/*
* Could call native_set_pte() here and trap and
- * emulate the PTE write but with 32-bit guests this
- * needs two traps (one for each of the two 32-bit
- * words in the PTE) so do one hypercall directly
- * instead.
+ * emulate the PTE write, but a hypercall is much cheaper.
*/
struct mmu_update u;
@@ -299,13 +285,6 @@
__xen_set_pte(ptep, pteval);
}
-static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pteval)
-{
- trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
- __xen_set_pte(ptep, pteval);
-}
-
pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
@@ -439,26 +418,6 @@
xen_set_pud_hyper(ptr, val);
}
-#ifdef CONFIG_X86_PAE
-static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
- trace_xen_mmu_set_pte_atomic(ptep, pte);
- __xen_set_pte(ptep, pte);
-}
-
-static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
- trace_xen_mmu_pte_clear(mm, addr, ptep);
- __xen_set_pte(ptep, native_make_pte(0));
-}
-
-static void xen_pmd_clear(pmd_t *pmdp)
-{
- trace_xen_mmu_pmd_clear(pmdp);
- set_pmd(pmdp, __pmd(0));
-}
-#endif /* CONFIG_X86_PAE */
-
__visible pmd_t xen_make_pmd(pmdval_t pmd)
{
pmd = pte_pfn_to_mfn(pmd);
@@ -466,7 +425,6 @@
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
-#ifdef CONFIG_X86_64
__visible pudval_t xen_pud_val(pud_t pud)
{
return pte_mfn_to_pfn(pud.pud);
@@ -571,27 +529,27 @@
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d);
#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
-#endif /* CONFIG_X86_64 */
-static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
- int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
- bool last, unsigned long limit)
+static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
+ void (*func)(struct mm_struct *mm, struct page *,
+ enum pt_level),
+ bool last, unsigned long limit)
{
- int i, nr, flush = 0;
+ int i, nr;
nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD;
for (i = 0; i < nr; i++) {
if (!pmd_none(pmd[i]))
- flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE);
+ (*func)(mm, pmd_page(pmd[i]), PT_PTE);
}
- return flush;
}
-static int xen_pud_walk(struct mm_struct *mm, pud_t *pud,
- int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
- bool last, unsigned long limit)
+static void xen_pud_walk(struct mm_struct *mm, pud_t *pud,
+ void (*func)(struct mm_struct *mm, struct page *,
+ enum pt_level),
+ bool last, unsigned long limit)
{
- int i, nr, flush = 0;
+ int i, nr;
nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD;
for (i = 0; i < nr; i++) {
@@ -602,29 +560,26 @@
pmd = pmd_offset(&pud[i], 0);
if (PTRS_PER_PMD > 1)
- flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
- flush |= xen_pmd_walk(mm, pmd, func,
- last && i == nr - 1, limit);
+ (*func)(mm, virt_to_page(pmd), PT_PMD);
+ xen_pmd_walk(mm, pmd, func, last && i == nr - 1, limit);
}
- return flush;
}
-static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
- int (*func)(struct mm_struct *mm, struct page *, enum pt_level),
- bool last, unsigned long limit)
+static void xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d,
+ void (*func)(struct mm_struct *mm, struct page *,
+ enum pt_level),
+ bool last, unsigned long limit)
{
- int flush = 0;
pud_t *pud;
if (p4d_none(*p4d))
- return flush;
+ return;
pud = pud_offset(p4d, 0);
if (PTRS_PER_PUD > 1)
- flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
- flush |= xen_pud_walk(mm, pud, func, last, limit);
- return flush;
+ (*func)(mm, virt_to_page(pud), PT_PUD);
+ xen_pud_walk(mm, pud, func, last, limit);
}
/*
@@ -636,32 +591,27 @@
* will be STACK_TOP_MAX, but at boot we need to pin up to
* FIXADDR_TOP.
*
- * For 32-bit the important bit is that we don't pin beyond there,
- * because then we start getting into Xen's ptes.
- *
- * For 64-bit, we must skip the Xen hole in the middle of the address
- * space, just after the big x86-64 virtual hole.
+ * We must skip the Xen hole in the middle of the address space, just after
+ * the big x86-64 virtual hole.
*/
-static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
- int (*func)(struct mm_struct *mm, struct page *,
- enum pt_level),
- unsigned long limit)
+static void __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
+ void (*func)(struct mm_struct *mm, struct page *,
+ enum pt_level),
+ unsigned long limit)
{
- int i, nr, flush = 0;
+ int i, nr;
unsigned hole_low = 0, hole_high = 0;
/* The limit is the last byte to be touched */
limit--;
BUG_ON(limit >= FIXADDR_TOP);
-#ifdef CONFIG_X86_64
/*
* 64-bit has a great big hole in the middle of the address
* space, which contains the Xen mappings.
*/
hole_low = pgd_index(GUARD_HOLE_BASE_ADDR);
hole_high = pgd_index(GUARD_HOLE_END_ADDR);
-#endif
nr = pgd_index(limit) + 1;
for (i = 0; i < nr; i++) {
@@ -674,22 +624,20 @@
continue;
p4d = p4d_offset(&pgd[i], 0);
- flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
+ xen_p4d_walk(mm, p4d, func, i == nr - 1, limit);
}
/* Do the top level last, so that the callbacks can use it as
a cue to do final things like tlb flushes. */
- flush |= (*func)(mm, virt_to_page(pgd), PT_PGD);
-
- return flush;
+ (*func)(mm, virt_to_page(pgd), PT_PGD);
}
-static int xen_pgd_walk(struct mm_struct *mm,
- int (*func)(struct mm_struct *mm, struct page *,
- enum pt_level),
- unsigned long limit)
+static void xen_pgd_walk(struct mm_struct *mm,
+ void (*func)(struct mm_struct *mm, struct page *,
+ enum pt_level),
+ unsigned long limit)
{
- return __xen_pgd_walk(mm, mm->pgd, func, limit);
+ __xen_pgd_walk(mm, mm->pgd, func, limit);
}
/* If we're using split pte locks, then take the page's lock and
@@ -722,26 +670,17 @@
xen_extend_mmuext_op(&op);
}
-static int xen_pin_page(struct mm_struct *mm, struct page *page,
- enum pt_level level)
+static void xen_pin_page(struct mm_struct *mm, struct page *page,
+ enum pt_level level)
{
unsigned pgfl = TestSetPagePinned(page);
- int flush;
- if (pgfl)
- flush = 0; /* already pinned */
- else if (PageHighMem(page))
- /* kmaps need flushing if we found an unpinned
- highpage */
- flush = 1;
- else {
+ if (!pgfl) {
void *pt = lowmem_page_address(page);
unsigned long pfn = page_to_pfn(page);
struct multicall_space mcs = __xen_mc_entry(0);
spinlock_t *ptl;
- flush = 0;
-
/*
* We need to hold the pagetable lock between the time
* we make the pagetable RO and when we actually pin
@@ -778,8 +717,6 @@
xen_mc_callback(xen_pte_unlock, ptl);
}
}
-
- return flush;
}
/* This is called just after a mm has been created, but it has not
@@ -787,39 +724,22 @@
read-only, and can be pinned. */
static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
{
+ pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
trace_xen_mmu_pgd_pin(mm, pgd);
xen_mc_batch();
- if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
- /* re-enable interrupts for flushing */
- xen_mc_issue(0);
+ __xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT);
- kmap_flush_unused();
+ xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));
- xen_mc_batch();
+ if (user_pgd) {
+ xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
+ xen_do_pin(MMUEXT_PIN_L4_TABLE,
+ PFN_DOWN(__pa(user_pgd)));
}
-#ifdef CONFIG_X86_64
- {
- pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
- xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));
-
- if (user_pgd) {
- xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
- xen_do_pin(MMUEXT_PIN_L4_TABLE,
- PFN_DOWN(__pa(user_pgd)));
- }
- }
-#else /* CONFIG_X86_32 */
-#ifdef CONFIG_X86_PAE
- /* Need to make sure unshared kernel PMD is pinnable */
- xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
- PT_PMD);
-#endif
- xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
-#endif /* CONFIG_X86_64 */
xen_mc_issue(0);
}
@@ -854,11 +774,10 @@
spin_unlock(&pgd_lock);
}
-static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
- enum pt_level level)
+static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
+ enum pt_level level)
{
SetPagePinned(page);
- return 0;
}
/*
@@ -870,18 +789,16 @@
static void __init xen_after_bootmem(void)
{
static_branch_enable(&xen_struct_pages_ready);
-#ifdef CONFIG_X86_64
SetPagePinned(virt_to_page(level3_user_vsyscall));
-#endif
xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
}
-static int xen_unpin_page(struct mm_struct *mm, struct page *page,
- enum pt_level level)
+static void xen_unpin_page(struct mm_struct *mm, struct page *page,
+ enum pt_level level)
{
unsigned pgfl = TestClearPagePinned(page);
- if (pgfl && !PageHighMem(page)) {
+ if (pgfl) {
void *pt = lowmem_page_address(page);
unsigned long pfn = page_to_pfn(page);
spinlock_t *ptl = NULL;
@@ -912,36 +829,24 @@
xen_mc_callback(xen_pte_unlock, ptl);
}
}
-
- return 0; /* never need to flush on unpin */
}
/* Release a pagetables pages back as normal RW */
static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
{
+ pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
trace_xen_mmu_pgd_unpin(mm, pgd);
xen_mc_batch();
xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-#ifdef CONFIG_X86_64
- {
- pgd_t *user_pgd = xen_get_user_pgd(pgd);
-
- if (user_pgd) {
- xen_do_pin(MMUEXT_UNPIN_TABLE,
- PFN_DOWN(__pa(user_pgd)));
- xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
- }
+ if (user_pgd) {
+ xen_do_pin(MMUEXT_UNPIN_TABLE,
+ PFN_DOWN(__pa(user_pgd)));
+ xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
}
-#endif
-
-#ifdef CONFIG_X86_PAE
- /* Need to make sure unshared kernel PMD is unpinned */
- xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
- PT_PMD);
-#endif
__xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
@@ -1089,7 +994,6 @@
BUG();
}
-#ifdef CONFIG_X86_64
static void __init xen_cleanhighmap(unsigned long vaddr,
unsigned long vaddr_end)
{
@@ -1238,7 +1142,7 @@
* We could be in __ka space.
* We roundup to the PMD, which means that if anybody at this stage is
* using the __ka address of xen_start_info or
- * xen_start_info->shared_info they are in going to crash. Fortunatly
+ * xen_start_info->shared_info they are in going to crash. Fortunately
* we have already revectored in xen_setup_kernel_pagetable.
*/
size = roundup(size, PMD_SIZE);
@@ -1273,17 +1177,15 @@
xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2));
xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
}
-#endif
static void __init xen_pagetable_p2m_setup(void)
{
xen_vmalloc_p2m_tree();
-#ifdef CONFIG_X86_64
xen_pagetable_p2m_free();
xen_pagetable_cleanhighmap();
-#endif
+
/* And revector! Bye bye old array */
xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
}
@@ -1420,6 +1322,8 @@
}
static void xen_write_cr3(unsigned long cr3)
{
+ pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
+
BUG_ON(preemptible());
xen_mc_batch(); /* disables interrupts */
@@ -1430,20 +1334,14 @@
__xen_write_cr3(true, cr3);
-#ifdef CONFIG_X86_64
- {
- pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
- if (user_pgd)
- __xen_write_cr3(false, __pa(user_pgd));
- else
- __xen_write_cr3(false, 0);
- }
-#endif
+ if (user_pgd)
+ __xen_write_cr3(false, __pa(user_pgd));
+ else
+ __xen_write_cr3(false, 0);
xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
}
-#ifdef CONFIG_X86_64
/*
* At the start of the day - when Xen launches a guest, it has already
* built pagetables for the guest. We diligently look over them
@@ -1478,49 +1376,39 @@
xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
}
-#endif
static int xen_pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd = mm->pgd;
- int ret = 0;
+ struct page *page = virt_to_page(pgd);
+ pgd_t *user_pgd;
+ int ret = -ENOMEM;
BUG_ON(PagePinned(virt_to_page(pgd)));
+ BUG_ON(page->private != 0);
-#ifdef CONFIG_X86_64
- {
- struct page *page = virt_to_page(pgd);
- pgd_t *user_pgd;
+ user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ page->private = (unsigned long)user_pgd;
- BUG_ON(page->private != 0);
-
- ret = -ENOMEM;
-
- user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
- page->private = (unsigned long)user_pgd;
-
- if (user_pgd != NULL) {
+ if (user_pgd != NULL) {
#ifdef CONFIG_X86_VSYSCALL_EMULATION
- user_pgd[pgd_index(VSYSCALL_ADDR)] =
- __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+ user_pgd[pgd_index(VSYSCALL_ADDR)] =
+ __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
#endif
- ret = 0;
- }
-
- BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+ ret = 0;
}
-#endif
+
+ BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
+
return ret;
}
static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
-#ifdef CONFIG_X86_64
pgd_t *user_pgd = xen_get_user_pgd(pgd);
if (user_pgd)
free_page((unsigned long)user_pgd);
-#endif
}
/*
@@ -1539,7 +1427,6 @@
*/
__visible pte_t xen_make_pte_init(pteval_t pte)
{
-#ifdef CONFIG_X86_64
unsigned long pfn;
/*
@@ -1553,7 +1440,7 @@
pfn >= xen_start_info->first_p2m_pfn &&
pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
pte &= ~_PAGE_RW;
-#endif
+
pte = pte_pfn_to_mfn(pte);
return native_make_pte(pte);
}
@@ -1561,13 +1448,6 @@
static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
{
-#ifdef CONFIG_X86_32
- /* If there's an existing pte, then don't allow _PAGE_RW to be set */
- if (pte_mfn(pte) != INVALID_P2M_ENTRY
- && pte_val_ma(*ptep) & _PAGE_PRESENT)
- pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
- pte_val_ma(pte));
-#endif
__xen_set_pte(ptep, pte);
}
@@ -1642,20 +1522,14 @@
if (static_branch_likely(&xen_struct_pages_ready))
SetPagePinned(page);
- if (!PageHighMem(page)) {
- xen_mc_batch();
+ xen_mc_batch();
- __set_pfn_prot(pfn, PAGE_KERNEL_RO);
+ __set_pfn_prot(pfn, PAGE_KERNEL_RO);
- if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
- __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+ if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+ __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
- } else {
- /* make sure there are no stray mappings of
- this page */
- kmap_flush_unused();
- }
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
}
}
@@ -1678,16 +1552,15 @@
trace_xen_mmu_release_ptpage(pfn, level, pinned);
if (pinned) {
- if (!PageHighMem(page)) {
- xen_mc_batch();
+ xen_mc_batch();
- if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
- __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+ if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+ __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
- __set_pfn_prot(pfn, PAGE_KERNEL);
+ __set_pfn_prot(pfn, PAGE_KERNEL);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
- }
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
ClearPagePinned(page);
}
}
@@ -1702,7 +1575,6 @@
xen_release_ptpage(pfn, PT_PMD);
}
-#ifdef CONFIG_X86_64
static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
{
xen_alloc_ptpage(mm, pfn, PT_PUD);
@@ -1712,20 +1584,6 @@
{
xen_release_ptpage(pfn, PT_PUD);
}
-#endif
-
-void __init xen_reserve_top(void)
-{
-#ifdef CONFIG_X86_32
- unsigned long top = HYPERVISOR_VIRT_START;
- struct xen_platform_parameters pp;
-
- if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
- top = pp.virt_start;
-
- reserve_top_address(-top);
-#endif /* CONFIG_X86_32 */
-}
/*
* Like __va(), but returns address in the kernel mapping (which is
@@ -1733,11 +1591,7 @@
*/
static void * __init __ka(phys_addr_t paddr)
{
-#ifdef CONFIG_X86_64
return (void *)(paddr + __START_KERNEL_map);
-#else
- return __va(paddr);
-#endif
}
/* Convert a machine address to physical address */
@@ -1771,56 +1625,7 @@
{
return set_page_prot_flags(addr, prot, UVMF_NONE);
}
-#ifdef CONFIG_X86_32
-static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
-{
- unsigned pmdidx, pteidx;
- unsigned ident_pte;
- unsigned long pfn;
- level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES,
- PAGE_SIZE);
-
- ident_pte = 0;
- pfn = 0;
- for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
- pte_t *pte_page;
-
- /* Reuse or allocate a page of ptes */
- if (pmd_present(pmd[pmdidx]))
- pte_page = m2v(pmd[pmdidx].pmd);
- else {
- /* Check for free pte pages */
- if (ident_pte == LEVEL1_IDENT_ENTRIES)
- break;
-
- pte_page = &level1_ident_pgt[ident_pte];
- ident_pte += PTRS_PER_PTE;
-
- pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
- }
-
- /* Install mappings */
- for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
- pte_t pte;
-
- if (pfn > max_pfn_mapped)
- max_pfn_mapped = pfn;
-
- if (!pte_none(pte_page[pteidx]))
- continue;
-
- pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
- pte_page[pteidx] = pte;
- }
- }
-
- for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
- set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
-
- set_page_prot(pmd, PAGE_KERNEL_RO);
-}
-#endif
void __init xen_setup_machphys_mapping(void)
{
struct xen_machphys_mapping mapping;
@@ -1831,13 +1636,8 @@
} else {
machine_to_phys_nr = MACH2PHYS_NR_ENTRIES;
}
-#ifdef CONFIG_X86_32
- WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1))
- < machine_to_phys_mapping);
-#endif
}
-#ifdef CONFIG_X86_64
static void __init convert_pfn_mfn(void *v)
{
pte_t *pte = v;
@@ -2168,105 +1968,6 @@
xen_start_info->nr_p2m_frames = n_frames;
}
-#else /* !CONFIG_X86_64 */
-static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
-static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
-RESERVE_BRK(fixup_kernel_pmd, PAGE_SIZE);
-RESERVE_BRK(fixup_kernel_pte, PAGE_SIZE);
-
-static void __init xen_write_cr3_init(unsigned long cr3)
-{
- unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
-
- BUG_ON(read_cr3_pa() != __pa(initial_page_table));
- BUG_ON(cr3 != __pa(swapper_pg_dir));
-
- /*
- * We are switching to swapper_pg_dir for the first time (from
- * initial_page_table) and therefore need to mark that page
- * read-only and then pin it.
- *
- * Xen disallows sharing of kernel PMDs for PAE
- * guests. Therefore we must copy the kernel PMD from
- * initial_page_table into a new kernel PMD to be used in
- * swapper_pg_dir.
- */
- swapper_kernel_pmd =
- extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- copy_page(swapper_kernel_pmd, initial_kernel_pmd);
- swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
- __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
- set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
-
- set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
- xen_write_cr3(cr3);
- pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
-
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
- PFN_DOWN(__pa(initial_page_table)));
- set_page_prot(initial_page_table, PAGE_KERNEL);
- set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
-
- pv_ops.mmu.write_cr3 = &xen_write_cr3;
-}
-
-/*
- * For 32 bit domains xen_start_info->pt_base is the pgd address which might be
- * not the first page table in the page table pool.
- * Iterate through the initial page tables to find the real page table base.
- */
-static phys_addr_t __init xen_find_pt_base(pmd_t *pmd)
-{
- phys_addr_t pt_base, paddr;
- unsigned pmdidx;
-
- pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd));
-
- for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++)
- if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) {
- paddr = m2p(pmd[pmdidx].pmd);
- pt_base = min(pt_base, paddr);
- }
-
- return pt_base;
-}
-
-void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
-{
- pmd_t *kernel_pmd;
-
- kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-
- xen_pt_base = xen_find_pt_base(kernel_pmd);
- xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE;
-
- initial_kernel_pmd =
- extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
-
- max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024);
-
- copy_page(initial_kernel_pmd, kernel_pmd);
-
- xen_map_identity_early(initial_kernel_pmd, max_pfn);
-
- copy_page(initial_page_table, pgd);
- initial_page_table[KERNEL_PGD_BOUNDARY] =
- __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
-
- set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
- set_page_prot(initial_page_table, PAGE_KERNEL_RO);
- set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
-
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
-
- pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
- PFN_DOWN(__pa(initial_page_table)));
- xen_write_cr3(__pa(initial_page_table));
-
- memblock_reserve(xen_pt_base, xen_pt_size);
-}
-#endif /* CONFIG_X86_64 */
-
void __init xen_reserve_special_pages(void)
{
phys_addr_t paddr;
@@ -2300,12 +2001,7 @@
switch (idx) {
case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-#ifdef CONFIG_X86_32
- case FIX_WP_TEST:
-# ifdef CONFIG_HIGHMEM
- case FIX_KMAP_BEGIN ... FIX_KMAP_END:
-# endif
-#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
case VSYSCALL_PAGE:
#endif
/* All local page mappings */
@@ -2357,9 +2053,7 @@
pv_ops.mmu.set_pte = xen_set_pte;
pv_ops.mmu.set_pmd = xen_set_pmd;
pv_ops.mmu.set_pud = xen_set_pud;
-#ifdef CONFIG_X86_64
pv_ops.mmu.set_p4d = xen_set_p4d;
-#endif
/* This will work as long as patching hasn't happened yet
(which it hasn't) */
@@ -2367,15 +2061,11 @@
pv_ops.mmu.alloc_pmd = xen_alloc_pmd;
pv_ops.mmu.release_pte = xen_release_pte;
pv_ops.mmu.release_pmd = xen_release_pmd;
-#ifdef CONFIG_X86_64
pv_ops.mmu.alloc_pud = xen_alloc_pud;
pv_ops.mmu.release_pud = xen_release_pud;
-#endif
pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte);
-#ifdef CONFIG_X86_64
pv_ops.mmu.write_cr3 = &xen_write_cr3;
-#endif
}
static void xen_leave_lazy_mmu(void)
@@ -2408,7 +2098,6 @@
.release_pmd = xen_release_pmd_init,
.set_pte = xen_set_pte_init,
- .set_pte_at = xen_set_pte_at,
.set_pmd = xen_set_pmd_hyper,
.ptep_modify_prot_start = __ptep_modify_prot_start,
@@ -2420,17 +2109,11 @@
.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
-#ifdef CONFIG_X86_PAE
- .set_pte_atomic = xen_set_pte_atomic,
- .pte_clear = xen_pte_clear,
- .pmd_clear = xen_pmd_clear,
-#endif /* CONFIG_X86_PAE */
.set_pud = xen_set_pud_hyper,
.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
-#ifdef CONFIG_X86_64
.pud_val = PV_CALLEE_SAVE(xen_pud_val),
.make_pud = PV_CALLEE_SAVE(xen_make_pud),
.set_p4d = xen_set_p4d_hyper,
@@ -2442,7 +2125,6 @@
.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
#endif
-#endif /* CONFIG_X86_64 */
.activate_mm = xen_activate_mm,
.dup_mmap = xen_dup_mmap,
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b1e40e..e809f14 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -98,8 +98,8 @@
unsigned long xen_max_p2m_pfn __read_mostly;
EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
-#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
+#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
#else
#define P2M_LIMIT 0
#endif
@@ -379,12 +379,8 @@
if (type == P2M_TYPE_PFN || i < chunk) {
/* Use initial p2m page contents. */
-#ifdef CONFIG_X86_64
mfns = alloc_p2m_page();
copy_page(mfns, xen_p2m_addr + pfn);
-#else
- mfns = xen_p2m_addr + pfn;
-#endif
ptep = populate_extra_pte((unsigned long)(p2m + pfn));
set_pte(ptep,
pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL));
@@ -467,7 +463,7 @@
* Allocate new pmd(s). It is checked whether the old pmd is still in place.
* If not, nothing is changed. This is okay as the only reason for allocating
* a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual
- * pmd. In case of PAE/x86-32 there are multiple pmds to allocate!
+ * pmd.
*/
static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
{
@@ -656,10 +652,9 @@
pte_t *ptep;
unsigned int level;
- if (unlikely(pfn >= xen_p2m_size)) {
- BUG_ON(mfn != INVALID_P2M_ENTRY);
- return true;
- }
+ /* Only invalid entries allowed above the highest p2m covered frame. */
+ if (unlikely(pfn >= xen_p2m_size))
+ return mfn == INVALID_P2M_ENTRY;
/*
* The interface requires atomic updates on p2m elements.
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 33293ce..19ae3e4 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -2,7 +2,7 @@
/* Glue code to lib/swiotlb-xen.c */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
#include <linux/pci.h>
#include <xen/swiotlb-xen.h>
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 548d1e0..8bfc103 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -20,6 +20,7 @@
#include <asm/setup.h>
#include <asm/acpi.h>
#include <asm/numa.h>
+#include <asm/idtentry.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
@@ -31,7 +32,6 @@
#include <xen/features.h>
#include <xen/hvc-console.h>
#include "xen-ops.h"
-#include "vdso.h"
#include "mmu.h"
#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
@@ -59,13 +59,13 @@
} xen_remap_buf __initdata __aligned(PAGE_SIZE);
static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
-/*
+/*
* The maximum amount of extra memory compared to the base size. The
* main scaling factor is the size of struct page. At extreme ratios
* of base:extra, all the base memory can be filled with page
* structures for the extra memory, leaving no space for anything
* else.
- *
+ *
* 10x seems like a reasonable balance between scaling flexibility and
* leaving a practically usable system.
*/
@@ -412,7 +412,7 @@
remap_range_size = xen_find_pfn_range(&remap_pfn);
if (!remap_range_size) {
- pr_warning("Unable to find available pfn range, not remapping identity pages\n");
+ pr_warn("Unable to find available pfn range, not remapping identity pages\n");
xen_set_identity_and_release_chunk(cur_pfn,
cur_pfn + left, nr_pages);
break;
@@ -544,13 +544,10 @@
{
unsigned long limit;
-#ifdef CONFIG_X86_32
- limit = GB(64) / PAGE_SIZE;
-#else
limit = MAXMEM / PAGE_SIZE;
if (!xen_initial_domain() && xen_512gb_limit)
limit = GB(512) / PAGE_SIZE;
-#endif
+
return limit;
}
@@ -721,17 +718,8 @@
if (!xen_is_e820_reserved(start, size))
return;
-#ifdef CONFIG_X86_32
- /*
- * Relocating the p2m on 32 bit system to an arbitrary virtual address
- * is not supported, so just give up.
- */
- xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n");
- BUG();
-#else
xen_relocate_p2m();
memblock_free(start, size);
-#endif
}
/**
@@ -803,17 +791,10 @@
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
- * factor the base size. On non-highmem systems, the base
- * size is the full initial memory allocation; on highmem it
- * is limited to the max size of lowmem, so that it doesn't
- * get completely filled.
+ * factor the base size.
*
* Make sure we have no memory above max_pages, as this area
* isn't handled by the p2m management.
- *
- * In principle there could be a problem in lowmem systems if
- * the initial memory is also very large with respect to
- * lowmem, but we won't try to deal with that here.
*/
extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages, max_pages - max_pfn);
@@ -920,20 +901,6 @@
return "Xen";
}
-/*
- * Set the bit indicating "nosegneg" library variants should be used.
- * We only need to bother in pure 32-bit mode; compat 32-bit processes
- * can have un-truncated segments, so wrapping around is allowed.
- */
-static void __init fiddle_vdso(void)
-{
-#ifdef CONFIG_X86_32
- u32 *mask = vdso_image_32.data +
- vdso_image_32.sym_VDSO32_NOTE_MASK;
- *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
-#endif
-}
-
static int register_callback(unsigned type, const void *func)
{
struct callback_register callback = {
@@ -950,11 +917,7 @@
int ret;
unsigned sysenter_feature;
-#ifdef CONFIG_X86_32
- sysenter_feature = X86_FEATURE_SEP;
-#else
sysenter_feature = X86_FEATURE_SYSENTER32;
-#endif
if (!boot_cpu_has(sysenter_feature))
return;
@@ -966,7 +929,6 @@
void xen_enable_syscall(void)
{
-#ifdef CONFIG_X86_64
int ret;
ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target);
@@ -982,10 +944,9 @@
if (ret != 0)
setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
}
-#endif /* CONFIG_X86_64 */
}
-void __init xen_pvmmu_arch_setup(void)
+static void __init xen_pvmmu_arch_setup(void)
{
HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
@@ -993,7 +954,8 @@
HYPERVISOR_vm_assist(VMASST_CMD_enable,
VMASST_TYPE_pae_extended_cr3);
- if (register_callback(CALLBACKTYPE_event, xen_hypervisor_callback) ||
+ if (register_callback(CALLBACKTYPE_event,
+ xen_asm_exc_xen_hypervisor_callback) ||
register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))
BUG();
@@ -1022,7 +984,6 @@
disable_cpuidle();
disable_cpufreq();
WARN_ON(xen_set_default_idle());
- fiddle_vdso();
#ifdef CONFIG_NUMA
numa_off = 1;
#endif
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7a43b2a..c1b2f76 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -88,14 +88,17 @@
per_cpu(xen_callfunc_irq, cpu).irq = rc;
per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
- debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
- rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
- IRQF_PERCPU | IRQF_NOBALANCING,
- debug_name, NULL);
- if (rc < 0)
- goto fail;
- per_cpu(xen_debug_irq, cpu).irq = rc;
- per_cpu(xen_debug_irq, cpu).name = debug_name;
+ if (!xen_fifo_events) {
+ debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+ rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
+ xen_debug_interrupt,
+ IRQF_PERCPU | IRQF_NOBALANCING,
+ debug_name, NULL);
+ if (rc < 0)
+ goto fail;
+ per_cpu(xen_debug_irq, cpu).irq = rc;
+ per_cpu(xen_debug_irq, cpu).name = debug_name;
+ }
callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
@@ -132,7 +135,7 @@
if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS)
continue;
- rc = cpu_down(cpu);
+ rc = remove_cpu(cpu);
if (rc == 0) {
/*
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f8d3944..6ff3c88 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/thread_info.h>
#include <asm/smp.h>
#include <xen/events.h>
@@ -32,9 +33,11 @@
int cpu;
native_smp_prepare_cpus(max_cpus);
- WARN_ON(xen_smp_intr_init(0));
- xen_init_lock_cpu(0);
+ if (xen_have_vector_callback) {
+ WARN_ON(xen_smp_intr_init(0));
+ xen_init_lock_cpu(0);
+ }
for_each_possible_cpu(cpu) {
if (cpu == 0)
@@ -49,9 +52,11 @@
static void xen_hvm_cpu_die(unsigned int cpu)
{
if (common_cpu_die(cpu) == 0) {
- xen_smp_intr_free(cpu);
- xen_uninit_lock_cpu(cpu);
- xen_teardown_timer(cpu);
+ if (xen_have_vector_callback) {
+ xen_smp_intr_free(cpu);
+ xen_uninit_lock_cpu(cpu);
+ xen_teardown_timer(cpu);
+ }
}
}
#else
@@ -63,14 +68,19 @@
void __init xen_hvm_smp_init(void)
{
- if (!xen_have_vector_callback)
- return;
-
+ smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
- smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
+ smp_ops.smp_cpus_done = xen_smp_cpus_done;
smp_ops.cpu_die = xen_hvm_cpu_die;
+
+ if (!xen_have_vector_callback) {
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+ nopvspin = true;
+#endif
+ return;
+ }
+
+ smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
- smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
- smp_ops.smp_cpus_done = xen_smp_cpus_done;
}
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 0cebe5d..8f9e7e2 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -23,11 +23,13 @@
#include <linux/nmi.h>
#include <linux/cpuhotplug.h>
#include <linux/stackprotector.h>
+#include <linux/pgtable.h>
#include <asm/paravirt.h>
+#include <asm/idtentry.h>
#include <asm/desc.h>
-#include <asm/pgtable.h>
#include <asm/cpu.h>
+#include <asm/io_apic.h>
#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>
@@ -53,6 +55,7 @@
static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };
static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
+void asm_cpu_bringup_and_idle(void);
static void cpu_bringup(void)
{
@@ -90,9 +93,7 @@
asmlinkage __visible void cpu_bringup_and_idle(void)
{
cpu_bringup();
- boot_init_stack_canary();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
- prevent_tail_call_optimization();
}
void xen_smp_intr_free_pv(unsigned int cpu)
@@ -148,28 +149,12 @@
return rc;
}
-static void __init xen_fill_possible_map(void)
-{
- int i, rc;
-
- if (xen_initial_domain())
- return;
-
- for (i = 0; i < nr_cpu_ids; i++) {
- rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
- if (rc >= 0) {
- num_processors++;
- set_cpu_possible(i, true);
- }
- }
-}
-
-static void __init xen_filter_cpu_maps(void)
+static void __init _get_smp_config(unsigned int early)
{
int i, rc;
unsigned int subtract = 0;
- if (!xen_initial_domain())
+ if (early)
return;
num_processors = 0;
@@ -210,16 +195,6 @@
* sure the old memory can be recycled. */
make_lowmem_page_readwrite(xen_initial_gdt);
-#ifdef CONFIG_X86_32
- /*
- * Xen starts us with XEN_FLAT_RING1_DS, but linux code
- * expects __USER_DS
- */
- loadsegment(ds, __USER_DS);
- loadsegment(es, __USER_DS);
-#endif
-
- xen_filter_cpu_maps();
xen_setup_vcpu_info_placement();
/*
@@ -299,10 +274,6 @@
gdt = get_cpu_gdt_rw(cpu);
-#ifdef CONFIG_X86_32
- ctxt->user_regs.fs = __KERNEL_PERCPU;
- ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
-#endif
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
/*
@@ -310,7 +281,7 @@
* pointing just below where pt_regs would be if it were a normal
* kernel entry.
*/
- ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
+ ctxt->user_regs.eip = (unsigned long)asm_cpu_bringup_and_idle;
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __USER_DS;
@@ -340,14 +311,9 @@
ctxt->kernel_ss = __KERNEL_DS;
ctxt->kernel_sp = task_top_of_stack(idle);
-#ifdef CONFIG_X86_32
- ctxt->event_callback_cs = __KERNEL_CS;
- ctxt->failsafe_callback_cs = __KERNEL_CS;
-#else
ctxt->gs_base_kernel = per_cpu_offset(cpu);
-#endif
ctxt->event_callback_eip =
- (unsigned long)xen_hypervisor_callback;
+ (unsigned long)xen_asm_exc_xen_hypervisor_callback;
ctxt->failsafe_callback_eip =
(unsigned long)xen_failsafe_callback;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
@@ -508,5 +474,8 @@
void __init xen_smp_init(void)
{
smp_ops = xen_smp_ops;
- xen_fill_possible_map();
+
+ /* Avoid searching for BIOS MP tables */
+ x86_init.mpparse.find_smp_config = x86_init_noop;
+ x86_init.mpparse.get_smp_config = _get_smp_config;
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index d817b7c..043c73d 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -124,9 +124,8 @@
*/
void __init xen_init_spinlocks(void)
{
-
/* Don't need to use pvqspinlock code if there is only 1 vCPU. */
- if (num_possible_cpus() == 1)
+ if (num_possible_cpus() == 1 || nopvspin)
xen_pvspin = false;
if (!xen_pvspin) {
@@ -147,6 +146,7 @@
static __init int xen_parse_nopvspin(char *arg)
{
+ pr_notice("\"xen_nopvspin\" is deprecated, please use \"nopvspin\" instead\n");
xen_pvspin = false;
return 0;
}
diff --git a/arch/x86/xen/suspend_hvm.c b/arch/x86/xen/suspend_hvm.c
index e666b61..9d548b0 100644
--- a/arch/x86/xen/suspend_hvm.c
+++ b/arch/x86/xen/suspend_hvm.c
@@ -2,6 +2,7 @@
#include <linux/types.h>
#include <xen/xen.h>
+#include <xen/hvm.h>
#include <xen/features.h>
#include <xen/interface/features.h>
@@ -13,6 +14,6 @@
xen_hvm_init_shared_info();
xen_vcpu_restore();
}
- xen_callback_vector();
+ xen_setup_callback_vector();
xen_unplug_emulated_devices();
}
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index 8303b58..cae9660 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/types.h>
-#include <asm/fixmap.h>
-
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
+#include <asm/fixmap.h>
+
#include "xen-ops.h"
void xen_pv_pre_suspend(void)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index befbdd8..91f5b33 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -39,6 +39,7 @@
struct pvclock_vcpu_time_info *info =
&HYPERVISOR_shared_info->vcpu_info[0].time;
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
return pvclock_tsc_khz(info);
}
@@ -145,12 +146,19 @@
.notifier_call = xen_pvclock_gtod_notify,
};
+static int xen_cs_enable(struct clocksource *cs)
+{
+ vclocks_set_used(VDSO_CLOCKMODE_PVCLOCK);
+ return 0;
+}
+
static struct clocksource xen_clocksource __read_mostly = {
- .name = "xen",
- .rating = 400,
- .read = xen_clocksource_get_cycles,
- .mask = ~0,
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ .name = "xen",
+ .rating = 400,
+ .read = xen_clocksource_get_cycles,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ .enable = xen_cs_enable,
};
/*
@@ -412,12 +420,13 @@
ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
/*
- * We don't disable VCLOCK_PVCLOCK entirely if it fails to register the
- * secondary time info with Xen or if we migrated to a host without the
- * necessary flags. On both of these cases what happens is either
- * process seeing a zeroed out pvti or seeing no PVCLOCK_TSC_STABLE_BIT
- * bit set. Userspace checks the latter and if 0, it discards the data
- * in pvti and fallbacks to a system call for a reliable timestamp.
+ * We don't disable VDSO_CLOCKMODE_PVCLOCK entirely if it fails to
+ * register the secondary time info with Xen or if we migrated to a
+ * host without the necessary flags. On both of these cases what
+ * happens is either process seeing a zeroed out pvti or seeing no
+ * PVCLOCK_TSC_STABLE_BIT bit set. Userspace checks the latter and
+ * if 0, it discards the data in pvti and fallbacks to a system
+ * call for a reliable timestamp.
*/
if (ret != 0)
pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
@@ -443,7 +452,7 @@
ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t);
if (ret) {
- pr_notice("xen: VCLOCK_PVCLOCK not supported (err %d)\n", ret);
+ pr_notice("xen: VDSO_CLOCKMODE_PVCLOCK not supported (err %d)\n", ret);
free_page((unsigned long)ti);
return;
}
@@ -460,14 +469,14 @@
if (!ret)
free_page((unsigned long)ti);
- pr_notice("xen: VCLOCK_PVCLOCK not supported (tsc unstable)\n");
+ pr_notice("xen: VDSO_CLOCKMODE_PVCLOCK not supported (tsc unstable)\n");
return;
}
xen_clock = ti;
pvclock_set_pvti_cpu0_va(xen_clock);
- xen_clocksource.archdata.vclock_mode = VCLOCK_PVCLOCK;
+ xen_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
}
static void __init xen_time_init(void)
diff --git a/arch/x86/xen/vdso.h b/arch/x86/xen/vdso.h
deleted file mode 100644
index 873c54c..0000000
--- a/arch/x86/xen/vdso.h
+++ /dev/null
@@ -1,6 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/* Bit used for the pseudo-hwcap for non-negative segments. We use
- bit 1 to avoid bugs in some versions of glibc when bit 0 is
- used; the choice is otherwise arbitrary. */
-#define VDSO_NOTE_NONEGSEG_BIT 1
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index be104ee..011ec64 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -6,20 +6,27 @@
* operations here; the indirect forms are better handled in C.
*/
+#include <asm/errno.h>
#include <asm/asm-offsets.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
-#include <asm/frame.h>
+#include <asm/segment.h>
+#include <asm/thread_info.h>
#include <asm/asm.h>
+#include <asm/frame.h>
+#include <xen/interface/xen.h>
+
+#include <linux/init.h>
#include <linux/linkage.h>
+#include <../entry/calling.h>
/*
* Enable events. This clears the event mask and tests the pending
* event status with one and operation. If there are pending events,
* then enter the hypervisor to get them handled.
*/
-ENTRY(xen_irq_enable_direct)
+SYM_FUNC_START(xen_irq_enable_direct)
FRAME_BEGIN
/* Unmask events */
movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
@@ -38,17 +45,17 @@
1:
FRAME_END
ret
- ENDPROC(xen_irq_enable_direct)
+SYM_FUNC_END(xen_irq_enable_direct)
/*
* Disabling events is simply a matter of making the event mask
* non-zero.
*/
-ENTRY(xen_irq_disable_direct)
+SYM_FUNC_START(xen_irq_disable_direct)
movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
ret
-ENDPROC(xen_irq_disable_direct)
+SYM_FUNC_END(xen_irq_disable_direct)
/*
* (xen_)save_fl is used to get the current interrupt enable status.
@@ -59,12 +66,12 @@
* undefined. We need to toggle the state of the bit, because Xen and
* x86 use opposite senses (mask vs enable).
*/
-ENTRY(xen_save_fl_direct)
+SYM_FUNC_START(xen_save_fl_direct)
testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
setz %ah
addb %ah, %ah
ret
- ENDPROC(xen_save_fl_direct)
+SYM_FUNC_END(xen_save_fl_direct)
/*
@@ -74,13 +81,9 @@
* interrupt mask state, it checks for unmasked pending events and
* enters the hypervisor to get them delivered if so.
*/
-ENTRY(xen_restore_fl_direct)
+SYM_FUNC_START(xen_restore_fl_direct)
FRAME_BEGIN
-#ifdef CONFIG_X86_64
testw $X86_EFLAGS_IF, %di
-#else
- testb $X86_EFLAGS_IF>>8, %ah
-#endif
setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
/*
* Preempt here doesn't matter because that will deal with any
@@ -95,24 +98,15 @@
1:
FRAME_END
ret
- ENDPROC(xen_restore_fl_direct)
+SYM_FUNC_END(xen_restore_fl_direct)
/*
* Force an event check by making a hypercall, but preserve regs
* before making the call.
*/
-ENTRY(check_events)
+SYM_FUNC_START(check_events)
FRAME_BEGIN
-#ifdef CONFIG_X86_32
- push %eax
- push %ecx
- push %edx
- call xen_force_evtchn_callback
- pop %edx
- pop %ecx
- pop %eax
-#else
push %rax
push %rcx
push %rdx
@@ -132,22 +126,213 @@
pop %rdx
pop %rcx
pop %rax
-#endif
FRAME_END
ret
-ENDPROC(check_events)
+SYM_FUNC_END(check_events)
-ENTRY(xen_read_cr2)
+SYM_FUNC_START(xen_read_cr2)
FRAME_BEGIN
_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
FRAME_END
ret
- ENDPROC(xen_read_cr2);
+SYM_FUNC_END(xen_read_cr2);
-ENTRY(xen_read_cr2_direct)
+SYM_FUNC_START(xen_read_cr2_direct)
FRAME_BEGIN
_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
FRAME_END
ret
- ENDPROC(xen_read_cr2_direct);
+SYM_FUNC_END(xen_read_cr2_direct);
+
+.macro xen_pv_trap name
+SYM_CODE_START(xen_\name)
+ pop %rcx
+ pop %r11
+ jmp \name
+SYM_CODE_END(xen_\name)
+_ASM_NOKPROBE(xen_\name)
+.endm
+
+xen_pv_trap asm_exc_divide_error
+xen_pv_trap asm_xenpv_exc_debug
+xen_pv_trap asm_exc_int3
+xen_pv_trap asm_xenpv_exc_nmi
+xen_pv_trap asm_exc_overflow
+xen_pv_trap asm_exc_bounds
+xen_pv_trap asm_exc_invalid_op
+xen_pv_trap asm_exc_device_not_available
+xen_pv_trap asm_exc_double_fault
+xen_pv_trap asm_exc_coproc_segment_overrun
+xen_pv_trap asm_exc_invalid_tss
+xen_pv_trap asm_exc_segment_not_present
+xen_pv_trap asm_exc_stack_segment
+xen_pv_trap asm_exc_general_protection
+xen_pv_trap asm_exc_page_fault
+xen_pv_trap asm_exc_spurious_interrupt_bug
+xen_pv_trap asm_exc_coprocessor_error
+xen_pv_trap asm_exc_alignment_check
+#ifdef CONFIG_X86_MCE
+xen_pv_trap asm_exc_machine_check
+#endif /* CONFIG_X86_MCE */
+xen_pv_trap asm_exc_simd_coprocessor_error
+#ifdef CONFIG_IA32_EMULATION
+xen_pv_trap entry_INT80_compat
+#endif
+xen_pv_trap asm_exc_xen_unknown_trap
+xen_pv_trap asm_exc_xen_hypervisor_callback
+
+ __INIT
+SYM_CODE_START(xen_early_idt_handler_array)
+ i = 0
+ .rept NUM_EXCEPTION_VECTORS
+ pop %rcx
+ pop %r11
+ jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
+ i = i + 1
+ .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
+ .endr
+SYM_CODE_END(xen_early_idt_handler_array)
+ __FINIT
+
+hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
+/*
+ * Xen64 iret frame:
+ *
+ * ss
+ * rsp
+ * rflags
+ * cs
+ * rip <-- standard iret frame
+ *
+ * flags
+ *
+ * rcx }
+ * r11 }<-- pushed by hypercall page
+ * rsp->rax }
+ */
+SYM_CODE_START(xen_iret)
+ pushq $0
+ jmp hypercall_iret
+SYM_CODE_END(xen_iret)
+
+SYM_CODE_START(xen_sysret64)
+ /*
+ * We're already on the usermode stack at this point, but
+ * still with the kernel gs, so we can easily switch back.
+ *
+ * tss.sp2 is scratch space.
+ */
+ movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ pushq $__USER_DS
+ pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
+ pushq %r11
+ pushq $__USER_CS
+ pushq %rcx
+
+ pushq $VGCF_in_syscall
+ jmp hypercall_iret
+SYM_CODE_END(xen_sysret64)
+
+/*
+ * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is
+ * also the kernel stack. Reusing swapgs_restore_regs_and_return_to_usermode()
+ * in XEN pv would cause %rsp to move up to the top of the kernel stack and
+ * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI
+ * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET
+ * frame at the same address is useless.
+ */
+SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode)
+ UNWIND_HINT_REGS
+ POP_REGS
+
+ /* stackleak_erase() can work safely on the kernel stack. */
+ STACKLEAK_ERASE_NOCLOBBER
+
+ addq $8, %rsp /* skip regs->orig_ax */
+ jmp xen_iret
+SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)
+
+/*
+ * Xen handles syscall callbacks much like ordinary exceptions, which
+ * means we have:
+ * - kernel gs
+ * - kernel rsp
+ * - an iret-like stack frame on the stack (including rcx and r11):
+ * ss
+ * rsp
+ * rflags
+ * cs
+ * rip
+ * r11
+ * rsp->rcx
+ */
+
+/* Normal 64-bit system call target */
+SYM_FUNC_START(xen_syscall_target)
+ popq %rcx
+ popq %r11
+
+ /*
+ * Neither Xen nor the kernel really knows what the old SS and
+ * CS were. The kernel expects __USER_DS and __USER_CS, so
+ * report those values even though Xen will guess its own values.
+ */
+ movq $__USER_DS, 4*8(%rsp)
+ movq $__USER_CS, 1*8(%rsp)
+
+ jmp entry_SYSCALL_64_after_hwframe
+SYM_FUNC_END(xen_syscall_target)
+
+#ifdef CONFIG_IA32_EMULATION
+
+/* 32-bit compat syscall target */
+SYM_FUNC_START(xen_syscall32_target)
+ popq %rcx
+ popq %r11
+
+ /*
+ * Neither Xen nor the kernel really knows what the old SS and
+ * CS were. The kernel expects __USER32_DS and __USER32_CS, so
+ * report those values even though Xen will guess its own values.
+ */
+ movq $__USER32_DS, 4*8(%rsp)
+ movq $__USER32_CS, 1*8(%rsp)
+
+ jmp entry_SYSCALL_compat_after_hwframe
+SYM_FUNC_END(xen_syscall32_target)
+
+/* 32-bit compat sysenter target */
+SYM_FUNC_START(xen_sysenter_target)
+ /*
+ * NB: Xen is polite and clears TF from EFLAGS for us. This means
+ * that we don't need to guard against single step exceptions here.
+ */
+ popq %rcx
+ popq %r11
+
+ /*
+ * Neither Xen nor the kernel really knows what the old SS and
+ * CS were. The kernel expects __USER32_DS and __USER32_CS, so
+ * report those values even though Xen will guess its own values.
+ */
+ movq $__USER32_DS, 4*8(%rsp)
+ movq $__USER32_CS, 1*8(%rsp)
+
+ jmp entry_SYSENTER_compat_after_hwframe
+SYM_FUNC_END(xen_sysenter_target)
+
+#else /* !CONFIG_IA32_EMULATION */
+
+SYM_FUNC_START_ALIAS(xen_syscall32_target)
+SYM_FUNC_START(xen_sysenter_target)
+ lea 16(%rsp), %rsp /* strip %rcx, %r11 */
+ mov $-ENOSYS, %rax
+ pushq $0
+ jmp hypercall_iret
+SYM_FUNC_END(xen_sysenter_target)
+SYM_FUNC_END_ALIAS(xen_syscall32_target)
+
+#endif /* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
deleted file mode 100644
index 2712e91..0000000
--- a/arch/x86/xen/xen-asm_32.S
+++ /dev/null
@@ -1,183 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Asm versions of Xen pv-ops, suitable for direct use.
- *
- * We only bother with direct forms (ie, vcpu in pda) of the
- * operations here; the indirect forms are better handled in C.
- */
-
-#include <asm/thread_info.h>
-#include <asm/processor-flags.h>
-#include <asm/segment.h>
-#include <asm/asm.h>
-
-#include <xen/interface/xen.h>
-
-#include <linux/linkage.h>
-
-/* Pseudo-flag used for virtual NMI, which we don't implement yet */
-#define XEN_EFLAGS_NMI 0x80000000
-
-/*
- * This is run where a normal iret would be run, with the same stack setup:
- * 8: eflags
- * 4: cs
- * esp-> 0: eip
- *
- * This attempts to make sure that any pending events are dealt with
- * on return to usermode, but there is a small window in which an
- * event can happen just before entering usermode. If the nested
- * interrupt ends up setting one of the TIF_WORK_MASK pending work
- * flags, they will not be tested again before returning to
- * usermode. This means that a process can end up with pending work,
- * which will be unprocessed until the process enters and leaves the
- * kernel again, which could be an unbounded amount of time. This
- * means that a pending signal or reschedule event could be
- * indefinitely delayed.
- *
- * The fix is to notice a nested interrupt in the critical window, and
- * if one occurs, then fold the nested interrupt into the current
- * interrupt stack frame, and re-process it iteratively rather than
- * recursively. This means that it will exit via the normal path, and
- * all pending work will be dealt with appropriately.
- *
- * Because the nested interrupt handler needs to deal with the current
- * stack state in whatever form its in, we keep things simple by only
- * using a single register which is pushed/popped on the stack.
- */
-
-.macro POP_FS
-1:
- popw %fs
-.pushsection .fixup, "ax"
-2: movw $0, (%esp)
- jmp 1b
-.popsection
- _ASM_EXTABLE(1b,2b)
-.endm
-
-SYM_CODE_START(xen_iret)
- /* test eflags for special cases */
- testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
- jnz hyper_iret
-
- push %eax
- ESP_OFFSET=4 # bytes pushed onto stack
-
- /* Store vcpu_info pointer for easy access */
-#ifdef CONFIG_SMP
- pushw %fs
- movl $(__KERNEL_PERCPU), %eax
- movl %eax, %fs
- movl %fs:xen_vcpu, %eax
- POP_FS
-#else
- movl %ss:xen_vcpu, %eax
-#endif
-
- /* check IF state we're restoring */
- testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp)
-
- /*
- * Maybe enable events. Once this happens we could get a
- * recursive event, so the critical region starts immediately
- * afterwards. However, if that happens we don't end up
- * resuming the code, so we don't have to be worried about
- * being preempted to another CPU.
- */
- setz %ss:XEN_vcpu_info_mask(%eax)
-xen_iret_start_crit:
-
- /* check for unmasked and pending */
- cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax)
-
- /*
- * If there's something pending, mask events again so we can
- * jump back into xen_hypervisor_callback. Otherwise do not
- * touch XEN_vcpu_info_mask.
- */
- jne 1f
- movb $1, %ss:XEN_vcpu_info_mask(%eax)
-
-1: popl %eax
-
- /*
- * From this point on the registers are restored and the stack
- * updated, so we don't need to worry about it if we're
- * preempted
- */
-iret_restore_end:
-
- /*
- * Jump to hypervisor_callback after fixing up the stack.
- * Events are masked, so jumping out of the critical region is
- * OK.
- */
- je xen_hypervisor_callback
-
-1: iret
-xen_iret_end_crit:
- _ASM_EXTABLE(1b, iret_exc)
-
-hyper_iret:
- /* put this out of line since its very rarely used */
- jmp hypercall_page + __HYPERVISOR_iret * 32
-SYM_CODE_END(xen_iret)
-
- .globl xen_iret_start_crit, xen_iret_end_crit
-
-/*
- * This is called by xen_hypervisor_callback in entry_32.S when it sees
- * that the EIP at the time of interrupt was between
- * xen_iret_start_crit and xen_iret_end_crit.
- *
- * The stack format at this point is:
- * ----------------
- * ss : (ss/esp may be present if we came from usermode)
- * esp :
- * eflags } outer exception info
- * cs }
- * eip }
- * ----------------
- * eax : outer eax if it hasn't been restored
- * ----------------
- * eflags }
- * cs } nested exception info
- * eip }
- * return address : (into xen_hypervisor_callback)
- *
- * In order to deliver the nested exception properly, we need to discard the
- * nested exception frame such that when we handle the exception, we do it
- * in the context of the outer exception rather than starting a new one.
- *
- * The only caveat is that if the outer eax hasn't been restored yet (i.e.
- * it's still on stack), we need to restore its value here.
- */
-SYM_CODE_START(xen_iret_crit_fixup)
- /*
- * Paranoia: Make sure we're really coming from kernel space.
- * One could imagine a case where userspace jumps into the
- * critical range address, but just before the CPU delivers a
- * PF, it decides to deliver an interrupt instead. Unlikely?
- * Definitely. Easy to avoid? Yes.
- */
- testb $2, 2*4(%esp) /* nested CS */
- jnz 2f
-
- /*
- * If eip is before iret_restore_end then stack
- * hasn't been restored yet.
- */
- cmpl $iret_restore_end, 1*4(%esp)
- jae 1f
-
- movl 4*4(%esp), %eax /* load outer EAX */
- ret $4*4 /* discard nested EIP, CS, and EFLAGS as
- * well as the just restored EAX */
-
-1:
- ret $3*4 /* discard nested EIP, CS, and EFLAGS */
-
-2:
- ret
-SYM_CODE_END(xen_iret_crit_fixup)
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
deleted file mode 100644
index ebf610b..0000000
--- a/arch/x86/xen/xen-asm_64.S
+++ /dev/null
@@ -1,179 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Asm versions of Xen pv-ops, suitable for direct use.
- *
- * We only bother with direct forms (ie, vcpu in pda) of the
- * operations here; the indirect forms are better handled in C.
- */
-
-#include <asm/errno.h>
-#include <asm/percpu.h>
-#include <asm/processor-flags.h>
-#include <asm/segment.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
-#include <xen/interface/xen.h>
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-
-.macro xen_pv_trap name
-ENTRY(xen_\name)
- pop %rcx
- pop %r11
- jmp \name
-END(xen_\name)
-_ASM_NOKPROBE(xen_\name)
-.endm
-
-xen_pv_trap divide_error
-xen_pv_trap debug
-xen_pv_trap xendebug
-xen_pv_trap int3
-xen_pv_trap xennmi
-xen_pv_trap overflow
-xen_pv_trap bounds
-xen_pv_trap invalid_op
-xen_pv_trap device_not_available
-xen_pv_trap double_fault
-xen_pv_trap coprocessor_segment_overrun
-xen_pv_trap invalid_TSS
-xen_pv_trap segment_not_present
-xen_pv_trap stack_segment
-xen_pv_trap general_protection
-xen_pv_trap page_fault
-xen_pv_trap spurious_interrupt_bug
-xen_pv_trap coprocessor_error
-xen_pv_trap alignment_check
-#ifdef CONFIG_X86_MCE
-xen_pv_trap machine_check
-#endif /* CONFIG_X86_MCE */
-xen_pv_trap simd_coprocessor_error
-#ifdef CONFIG_IA32_EMULATION
-xen_pv_trap entry_INT80_compat
-#endif
-xen_pv_trap hypervisor_callback
-
- __INIT
-ENTRY(xen_early_idt_handler_array)
- i = 0
- .rept NUM_EXCEPTION_VECTORS
- pop %rcx
- pop %r11
- jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
- i = i + 1
- .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
- .endr
-END(xen_early_idt_handler_array)
- __FINIT
-
-hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
-/*
- * Xen64 iret frame:
- *
- * ss
- * rsp
- * rflags
- * cs
- * rip <-- standard iret frame
- *
- * flags
- *
- * rcx }
- * r11 }<-- pushed by hypercall page
- * rsp->rax }
- */
-ENTRY(xen_iret)
- pushq $0
- jmp hypercall_iret
-
-ENTRY(xen_sysret64)
- /*
- * We're already on the usermode stack at this point, but
- * still with the kernel gs, so we can easily switch back.
- *
- * tss.sp2 is scratch space.
- */
- movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
- movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
- pushq $__USER_DS
- pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
- pushq %r11
- pushq $__USER_CS
- pushq %rcx
-
- pushq $VGCF_in_syscall
- jmp hypercall_iret
-
-/*
- * Xen handles syscall callbacks much like ordinary exceptions, which
- * means we have:
- * - kernel gs
- * - kernel rsp
- * - an iret-like stack frame on the stack (including rcx and r11):
- * ss
- * rsp
- * rflags
- * cs
- * rip
- * r11
- * rsp->rcx
- */
-
-/* Normal 64-bit system call target */
-ENTRY(xen_syscall_target)
- popq %rcx
- popq %r11
-
- /*
- * Neither Xen nor the kernel really knows what the old SS and
- * CS were. The kernel expects __USER_DS and __USER_CS, so
- * report those values even though Xen will guess its own values.
- */
- movq $__USER_DS, 4*8(%rsp)
- movq $__USER_CS, 1*8(%rsp)
-
- jmp entry_SYSCALL_64_after_hwframe
-ENDPROC(xen_syscall_target)
-
-#ifdef CONFIG_IA32_EMULATION
-
-/* 32-bit compat syscall target */
-ENTRY(xen_syscall32_target)
- popq %rcx
- popq %r11
-
- /*
- * Neither Xen nor the kernel really knows what the old SS and
- * CS were. The kernel expects __USER32_DS and __USER32_CS, so
- * report those values even though Xen will guess its own values.
- */
- movq $__USER32_DS, 4*8(%rsp)
- movq $__USER32_CS, 1*8(%rsp)
-
- jmp entry_SYSCALL_compat_after_hwframe
-ENDPROC(xen_syscall32_target)
-
-/* 32-bit compat sysenter target */
-ENTRY(xen_sysenter_target)
- mov 0*8(%rsp), %rcx
- mov 1*8(%rsp), %r11
- mov 5*8(%rsp), %rsp
- jmp entry_SYSENTER_compat
-ENDPROC(xen_sysenter_target)
-
-#else /* !CONFIG_IA32_EMULATION */
-
-ENTRY(xen_syscall32_target)
-ENTRY(xen_sysenter_target)
- lea 16(%rsp), %rsp /* strip %rcx, %r11 */
- mov $-ENOSYS, %rax
- pushq $0
- jmp hypercall_iret
-ENDPROC(xen_syscall32_target)
-ENDPROC(xen_sysenter_target)
-
-#endif /* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index c1d8b90..2d7c8f3 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -22,7 +22,7 @@
#ifdef CONFIG_XEN_PV
__INIT
-ENTRY(startup_xen)
+SYM_CODE_START(startup_xen)
UNWIND_HINT_EMPTY
cld
@@ -35,9 +35,8 @@
rep __ASM_SIZE(stos)
mov %_ASM_SI, xen_start_info
- mov $init_thread_union+THREAD_SIZE, %_ASM_SP
+ mov initial_stack(%rip), %rsp
-#ifdef CONFIG_X86_64
/* Set up %gs.
*
* The base of %gs always points to fixed_percpu_data. If the
@@ -49,16 +48,25 @@
movq $INIT_PER_CPU_VAR(fixed_percpu_data),%rax
cdq
wrmsr
-#endif
- jmp xen_start_kernel
-END(startup_xen)
+ call xen_start_kernel
+SYM_CODE_END(startup_xen)
__FINIT
+
+#ifdef CONFIG_XEN_PV_SMP
+.pushsection .text
+SYM_CODE_START(asm_cpu_bringup_and_idle)
+ UNWIND_HINT_EMPTY
+
+ call cpu_bringup_and_idle
+SYM_CODE_END(asm_cpu_bringup_and_idle)
+.popsection
+#endif
#endif
.pushsection .text
.balign PAGE_SIZE
-ENTRY(hypercall_page)
+SYM_CODE_START(hypercall_page)
.rept (PAGE_SIZE / 32)
UNWIND_HINT_EMPTY
.skip 32
@@ -69,7 +77,7 @@
.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
#include <asm/xen-hypercalls.h>
#undef HYPERCALL
-END(hypercall_page)
+SYM_CODE_END(hypercall_page)
.popsection
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 45a441c..9546c33 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -8,7 +8,6 @@
#include <xen/xen-ops.h>
/* These are code, but not functions. Defined in entry.S */
-extern const char xen_hypervisor_callback[];
extern const char xen_failsafe_callback[];
void xen_sysenter_target(void);
@@ -30,11 +29,12 @@
extern struct shared_info xen_dummy_shared_info;
extern struct shared_info *HYPERVISOR_shared_info;
+extern bool xen_fifo_events;
+
void xen_setup_mfn_list_list(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
-void xen_reserve_top(void);
void __init xen_reserve_special_pages(void);
void __init xen_pt_check_e820(void);
@@ -55,7 +55,6 @@
void xen_enable_syscall(void);
void xen_vcpu_restore(void);
-void xen_callback_vector(void);
void xen_hvm_init_shared_info(void);
void xen_unplug_emulated_devices(void);