6.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kirill A. Shutemov kirill.shutemov@linux.intel.com
[ Upstream commit 22daa42294b419a0d8060a3870285e7a72aa63e4 ]
AMD SEV and Intel TDX guests allocate shared buffers for performing I/O. This is done by allocating pages normally from the buddy allocator and then converting them to shared using set_memory_decrypted().
On kexec, the second kernel is unaware of which memory has been converted in this manner. It only sees E820_TYPE_RAM. Accessing shared memory as private is fatal.
Therefore, the memory state must be reset to its original state before starting the new kernel with kexec.
The process of converting shared memory back to private occurs in two steps:
- enc_kexec_begin() stops new conversions.
- enc_kexec_finish() unshares all existing shared memory, reverting it back to private.
Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Reviewed-by: Nikolay Borisov nik.borisov@suse.com Reviewed-by: Kai Huang kai.huang@intel.com Tested-by: Tao Liu ltao@redhat.com Link: https://lore.kernel.org/r/20240614095904.1345461-11-kirill.shutemov@linux.in... Stable-dep-of: d4fc4d014715 ("x86/tdx: Fix "in-kernel MMIO" check") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/x86_init.h | 10 ++++++++++ arch/x86/kernel/crash.c | 12 ++++++++++++ arch/x86/kernel/reboot.c | 12 ++++++++++++ arch/x86/kernel/x86_init.c | 4 ++++ 4 files changed, 38 insertions(+)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 28ac3cb9b987b..213cf5379a5a6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -149,12 +149,22 @@ struct x86_init_acpi { * @enc_status_change_finish Notify HV after the encryption status of a range is changed * @enc_tlb_flush_required Returns true if a TLB flush is needed before changing page encryption status * @enc_cache_flush_required Returns true if a cache flush is needed before changing page encryption status + * @enc_kexec_begin Begin the two-step process of converting shared memory back + * to private. It stops the new conversions from being started + * and waits in-flight conversions to finish, if possible. + * @enc_kexec_finish Finish the two-step process of converting shared memory to + * private. All memory is private after the call when + * the function returns. + * It is called on only one CPU while the others are shut down + * and with interrupts disabled. */ struct x86_guest { int (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc); int (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc); bool (*enc_tlb_flush_required)(bool enc); bool (*enc_cache_flush_required)(void); + void (*enc_kexec_begin)(void); + void (*enc_kexec_finish)(void); };
/** diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index f06501445cd98..340af81556584 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -128,6 +128,18 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif + + /* + * Non-crash kexec calls enc_kexec_begin() while scheduling is still + * active. This allows the callback to wait until all in-flight + * shared<->private conversions are complete. In a crash scenario, + * enc_kexec_begin() gets called after all but one CPU have been shut + * down and interrupts have been disabled. This allows the callback to + * detect a race with the conversion and report it. + */ + x86_platform.guest.enc_kexec_begin(); + x86_platform.guest.enc_kexec_finish(); + crash_save_cpu(regs, safe_smp_processor_id()); }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f3130f762784a..bb7a44af7efd1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -12,6 +12,7 @@ #include <linux/delay.h> #include <linux/objtool.h> #include <linux/pgtable.h> +#include <linux/kexec.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -716,6 +717,14 @@ static void native_machine_emergency_restart(void)
void native_machine_shutdown(void) { + /* + * Call enc_kexec_begin() while all CPUs are still active and + * interrupts are enabled. This will allow all in-flight memory + * conversions to finish cleanly. + */ + if (kexec_in_progress) + x86_platform.guest.enc_kexec_begin(); + /* Stop the cpus and apics */ #ifdef CONFIG_X86_IO_APIC /* @@ -752,6 +761,9 @@ void native_machine_shutdown(void) #ifdef CONFIG_X86_64 x86_platform.iommu_shutdown(); #endif + + if (kexec_in_progress) + x86_platform.guest.enc_kexec_finish(); }
static void __machine_emergency_restart(int emergency) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3f95e32dd288e..0a2bbd674a6d9 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -139,6 +139,8 @@ static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static bool enc_tlb_flush_required_noop(bool enc) { return false; } static bool enc_cache_flush_required_noop(void) { return false; } +static void enc_kexec_begin_noop(void) {} +static void enc_kexec_finish_noop(void) {} static bool is_private_mmio_noop(u64 addr) {return false; }
struct x86_platform_ops x86_platform __ro_after_init = { @@ -162,6 +164,8 @@ struct x86_platform_ops x86_platform __ro_after_init = { .enc_status_change_finish = enc_status_change_finish_noop, .enc_tlb_flush_required = enc_tlb_flush_required_noop, .enc_cache_flush_required = enc_cache_flush_required_noop, + .enc_kexec_begin = enc_kexec_begin_noop, + .enc_kexec_finish = enc_kexec_finish_noop, }, };