x86/kvm: fix FASTOP_SIZE when return thunks are enabled

stable inclusion
from stable-v5.10.133
commit 8e31dfd6306e7c6bb3758a459c2a6067be807886
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS
CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=8e31dfd6306e7c6bb3758a459c2a6067be807886

--------------------------------

commit 84e7051c upstream.

The return thunk call makes the fastop functions larger, just like IBT
does. Consider a 16-byte FASTOP_SIZE when CONFIG_RETHUNK is enabled.

Otherwise, functions will be incorrectly aligned and when computing their
position for differently sized operators, they will executed in the middle
or end of a function, which may as well be an int3, leading to a crash
like:

[   36.091116] int3: 0000 [#1] SMP NOPTI
[   36.091119] CPU: 3 PID: 1371 Comm: qemu-system-x86 Not tainted 5.15.0-41-generic #44
[   36.091120] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014
[   36.091121] RIP: 0010:xaddw_ax_dx+0x9/0x10 [kvm]
[   36.091185] Code: 00 0f bb d0 c3 cc cc cc cc 48 0f bb d0 c3 cc cc cc cc 0f 1f 80 00 00 00 00 0f c0 d0 c3 cc cc cc cc 66 0f c1 d0 c3 cc cc cc cc <0f> 1f 80 00 00 00 00 0f c1 d0 c3 cc cc cc cc 48 0f c1 d0 c3 cc cc
[   36.091186] RSP: 0018:ffffb1f541143c98 EFLAGS: 00000202
[   36.091188] RAX: 0000000089abcdef RBX: 0000000000000001 RCX: 0000000000000000
[   36.091188] RDX: 0000000076543210 RSI: ffffffffc073c6d0 RDI: 0000000000000200
[   36.091189] RBP: ffffb1f541143ca0 R08: ffff9f1803350a70 R09: 0000000000000002
[   36.091190] R10: ffff9f1803350a70 R11: 0000000000000000 R12: ffff9f1803350a70
[   36.091190] R13: ffffffffc077fee0 R14: 0000000000000000 R15: 0000000000000000
[   36.091191] FS:  00007efdfce8d640(0000) GS:ffff9f187dd80000(0000) knlGS:0000000000000000
[   36.091192] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   36.091192] CR2: 0000000000000000 CR3: 0000000009b62002 CR4: 0000000000772ee0
[   36.091195] PKRU: 55555554
[   36.091195] Call Trace:
[   36.091197]  <TASK>
[   36.091198]  ? fastop+0x5a/0xa0 [kvm]
[   36.091222]  x86_emulate_insn+0x7b8/0xe90 [kvm]
[   36.091244]  x86_emulate_instruction+0x2f4/0x630 [kvm]
[   36.091263]  ? kvm_arch_vcpu_load+0x7c/0x230 [kvm]
[   36.091283]  ? vmx_prepare_switch_to_host+0xf7/0x190 [kvm_intel]
[   36.091290]  complete_emulated_mmio+0x297/0x320 [kvm]
[   36.091310]  kvm_arch_vcpu_ioctl_run+0x32f/0x550 [kvm]
[   36.091330]  kvm_vcpu_ioctl+0x29e/0x6d0 [kvm]
[   36.091344]  ? kvm_vcpu_ioctl+0x120/0x6d0 [kvm]
[   36.091357]  ? __fget_files+0x86/0xc0
[   36.091362]  ? __fget_files+0x86/0xc0
[   36.091363]  __x64_sys_ioctl+0x92/0xd0
[   36.091366]  do_syscall_64+0x59/0xc0
[   36.091369]  ? syscall_exit_to_user_mode+0x27/0x50
[   36.091370]  ? do_syscall_64+0x69/0xc0
[   36.091371]  ? syscall_exit_to_user_mode+0x27/0x50
[   36.091372]  ? __x64_sys_writev+0x1c/0x30
[   36.091374]  ? do_syscall_64+0x69/0xc0
[   36.091374]  ? exit_to_user_mode_prepare+0x37/0xb0
[   36.091378]  ? syscall_exit_to_user_mode+0x27/0x50
[   36.091379]  ? do_syscall_64+0x69/0xc0
[   36.091379]  ? do_syscall_64+0x69/0xc0
[   36.091380]  ? do_syscall_64+0x69/0xc0
[   36.091381]  ? do_syscall_64+0x69/0xc0
[   36.091381]  entry_SYSCALL_64_after_hwframe+0x61/0xcb
[   36.091384] RIP: 0033:0x7efdfe6d1aff
[   36.091390] Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <41> 89 c0 3d 00 f0 ff ff 77 1f 48 8b 44 24 18 64 48 2b 04 25 28 00
[   36.091391] RSP: 002b:00007efdfce8c460 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[   36.091393] RAX: ffffffffffffffda RBX: 000000000000ae80 RCX: 00007efdfe6d1aff
[   36.091393] RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 000000000000000c
[   36.091394] RBP: 0000558f1609e220 R08: 0000558f13fb8190 R09: 00000000ffffffff
[   36.091394] R10: 0000558f16b5e950 R11: 0000000000000246 R12: 0000000000000000
[   36.091394] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
[   36.091396]  </TASK>
[   36.091397] Modules linked in: isofs nls_iso8859_1 kvm_intel joydev kvm input_leds serio_raw sch_fq_codel dm_multipath scsi_dh_rdac scsi_dh_emc scsi_dh_alua ipmi_devintf ipmi_msghandler drm msr ip_tables x_tables autofs4 btrfs blake2b_generic zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel virtio_net net_failover crypto_simd ahci xhci_pci cryptd psmouse virtio_blk libahci xhci_pci_renesas failover
[   36.123271] ---[ end trace db3c0ab5a48fabcc ]---
[   36.123272] RIP: 0010:xaddw_ax_dx+0x9/0x10 [kvm]
[   36.123319] Code: 00 0f bb d0 c3 cc cc cc cc 48 0f bb d0 c3 cc cc cc cc 0f 1f 80 00 00 00 00 0f c0 d0 c3 cc cc cc cc 66 0f c1 d0 c3 cc cc cc cc <0f> 1f 80 00 00 00 00 0f c1 d0 c3 cc cc cc cc 48 0f c1 d0 c3 cc cc
[   36.123320] RSP: 0018:ffffb1f541143c98 EFLAGS: 00000202
[   36.123321] RAX: 0000000089abcdef RBX: 0000000000000001 RCX: 0000000000000000
[   36.123321] RDX: 0000000076543210 RSI: ffffffffc073c6d0 RDI: 0000000000000200
[   36.123322] RBP: ffffb1f541143ca0 R08: ffff9f1803350a70 R09: 0000000000000002
[   36.123322] R10: ffff9f1803350a70 R11: 0000000000000000 R12: ffff9f1803350a70
[   36.123323] R13: ffffffffc077fee0 R14: 0000000000000000 R15: 0000000000000000
[   36.123323] FS:  00007efdfce8d640(0000) GS:ffff9f187dd80000(0000) knlGS:0000000000000000
[   36.123324] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   36.123325] CR2: 0000000000000000 CR3: 0000000009b62002 CR4: 0000000000772ee0
[   36.123327] PKRU: 55555554
[   36.123328] Kernel panic - not syncing: Fatal exception in interrupt
[   36.123410] Kernel Offset: 0x1400000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[   36.135305] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: aa3d4803 ("x86: Use return-thunk in asm code")
Signed-off-by: NThadeu Lima de Souza Cascardo <cascardo@canonical.com>
Co-developed-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reported-by: NLinux Kernel Functional Testing <lkft@linaro.org>
Message-Id: <20220713171241.184026-1-cascardo@canonical.com>
Tested-by: NJack Wang <jinpu.wang@ionos.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NLin Yujun <linyujun809@huawei.com>

[Backport] KVM: emulate: do not adjust size of fastop and setcc subroutines

stable inclusion
from stable-v5.10.133
commit 2ef1b06ceacfc6f96f6792126e107e75c0d7bd5d
category: bugfix
bugzilla: 187378

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=2ef1b06ceacfc6f96f6792126e107e75c0d7bd5d

--------------------------------

commit 79629181 upstream.

Instead of doing complicated calculations to find the size of the subroutines
(which are even more complicated because they need to be stringified into
an asm statement), just hardcode to 16.

It is less dense for a few combinations of IBT/SLS/retbleed, but it has
the advantage of being really simple.

Cc: stable@vger.kernel.org # 5.15.x: 84e7051c: x86/kvm: fix FASTOP_SIZE when return thunks are enabled
Cc: stable@vger.kernel.org
Suggested-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NLin Yujun <linyujun809@huawei.com>
Reviewed-by: NZhang Jianhua <chris.zjh@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

arch/x86/kvm/emulate.c

@@ -188,9 +188,6 @@
 #define X8(x...) X4(x), X4(x)
 #define X16(x...) X8(x), X8(x)
 
-#define NR_FASTOP (ilog2(sizeof(ulong)) + 1)
-#define FASTOP_SIZE 8
-
 struct opcode {
 	u64 flags : 56;
 	u64 intercept : 8;
@@ -304,9 +301,15 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
  * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
  * different operand sizes can be reached by calculation, rather than a jump
  * table (which would be bigger than the code).
+ *
+ * The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR
+ * and 1 for the straight line speculation INT3, leaves 7 bytes for the
+ * body of the function.  Currently none is larger than 4.
  */
 static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 
+#define FASTOP_SIZE	16
+
 #define __FOP_FUNC(name) \
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
@@ -438,11 +441,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
  * RET | JMP __x86_return_thunk	[1,5 bytes; CONFIG_RETHUNK]
  * INT3				[1 byte; CONFIG_SLS]
  */
-#define RET_LENGTH	(1 + (4 * IS_ENABLED(CONFIG_RETHUNK)) + \
-			 IS_ENABLED(CONFIG_SLS))
-#define SETCC_LENGTH	(3 + RET_LENGTH)
-#define SETCC_ALIGN	(4 << ((SETCC_LENGTH > 4) & 1) << ((SETCC_LENGTH > 8) & 1))
-static_assert(SETCC_LENGTH <= SETCC_ALIGN);
+#define SETCC_ALIGN	16
 
 #define FOP_SETCC(op) \
 	".align " __stringify(SETCC_ALIGN) " \n\t" \