kernel-hacking-2024-linux-s.../arch/x86/xen/xen-ops.h
Olaf Hering 00e37bdb01 xen PVonHVM: move shared_info to MMIO before kexec
Currently kexec in a PVonHVM guest fails with a triple fault because the
new kernel overwrites the shared info page. The exact failure depends on
the size of the kernel image. This patch moves the pfn from RAM into
MMIO space before the kexec boot.

The pfn containing the shared_info is located somewhere in RAM. This
will cause trouble if the current kernel is doing a kexec boot into a
new kernel. The new kernel (and its startup code) can not know where the
pfn is, so it can not reserve the page. The hypervisor will continue to
update the pfn, and as a result memory corruption occours in the new
kernel.

One way to work around this issue is to allocate a page in the
xen-platform pci device's BAR memory range. But pci init is done very
late and the shared_info page is already in use very early to read the
pvclock. So moving the pfn from RAM to MMIO is racy because some code
paths on other vcpus could access the pfn during the small   window when
the old pfn is moved to the new pfn. There is even a  small window were
the old pfn is not backed by a mfn, and during that time all reads
return -1.

Because it is not known upfront where the MMIO region is located it can
not be used right from the start in xen_hvm_init_shared_info.

To minimise trouble the move of the pfn is done shortly before kexec.
This does not eliminate the race because all vcpus are still online when
the syscore_ops will be called. But hopefully there is no work pending
at this point in time. Also the syscore_op is run last which reduces the
risk further.

Signed-off-by: Olaf Hering <olaf@aepfle.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-07-19 15:52:05 -04:00

126 lines
3.2 KiB
C

#ifndef XEN_OPS_H
#define XEN_OPS_H
#include <linux/init.h>
#include <linux/clocksource.h>
#include <linux/irqreturn.h>
#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[];
extern void *xen_initial_gdt;
struct trap_info;
void xen_copy_trap_info(struct trap_info *traps);
DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info);
DECLARE_PER_CPU(unsigned long, xen_cr3);
DECLARE_PER_CPU(unsigned long, xen_current_cr3);
extern struct start_info *xen_start_info;
extern struct shared_info xen_dummy_shared_info;
extern struct shared_info *HYPERVISOR_shared_info;
void xen_setup_mfn_list_list(void);
void xen_setup_shared_info(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
void xen_reserve_top(void);
extern unsigned long xen_max_p2m_pfn;
void xen_set_pat(u64);
char * __init xen_memory_setup(void);
void __init xen_arch_setup(void);
void __init xen_init_IRQ(void);
void xen_enable_sysenter(void);
void xen_enable_syscall(void);
void xen_vcpu_restore(void);
void xen_callback_vector(void);
void xen_hvm_resume_shared_info(void);
void xen_unplug_emulated_devices(void);
void __init xen_build_dynamic_phys_to_machine(void);
void xen_init_irq_ops(void);
void xen_setup_timer(int cpu);
void xen_setup_runstate_info(int cpu);
void xen_teardown_timer(int cpu);
cycle_t xen_clocksource_read(void);
void xen_setup_cpu_clockevents(void);
void __init xen_init_time_ops(void);
void __init xen_hvm_init_time_ops(void);
irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
bool xen_vcpu_stolen(int vcpu);
void xen_setup_vcpu_info_placement(void);
#ifdef CONFIG_SMP
void xen_smp_init(void);
void __init xen_hvm_smp_init(void);
extern cpumask_var_t xen_cpu_initialized_map;
#else
static inline void xen_smp_init(void) {}
static inline void xen_hvm_smp_init(void) {}
#endif
#ifdef CONFIG_PARAVIRT_SPINLOCKS
void __init xen_init_spinlocks(void);
void __cpuinit xen_init_lock_cpu(int cpu);
void xen_uninit_lock_cpu(int cpu);
#else
static inline void xen_init_spinlocks(void)
{
}
static inline void xen_init_lock_cpu(int cpu)
{
}
static inline void xen_uninit_lock_cpu(int cpu)
{
}
#endif
struct dom0_vga_console_info;
#ifdef CONFIG_XEN_DOM0
void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
void __init xen_init_apic(void);
#else
static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
size_t size)
{
}
static inline void __init xen_init_apic(void)
{
}
#endif
/* Declare an asm function, along with symbols needed to make it
inlineable */
#define DECL_ASM(ret, name, ...) \
ret name(__VA_ARGS__); \
extern char name##_end[]; \
extern char name##_reloc[] \
DECL_ASM(void, xen_irq_enable_direct, void);
DECL_ASM(void, xen_irq_disable_direct, void);
DECL_ASM(unsigned long, xen_save_fl_direct, void);
DECL_ASM(void, xen_restore_fl_direct, unsigned long);
/* These are not functions, and cannot be called normally */
void xen_iret(void);
void xen_sysexit(void);
void xen_sysret32(void);
void xen_sysret64(void);
void xen_adjust_exception_frame(void);
extern int xen_panic_handler_init(void);
#endif /* XEN_OPS_H */