Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
Merge tag 'x86_urgent_for_v6.9_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Borislav Petkov:
- Make sure single object builds in arch/x86/virt/ ala
make ... arch/x86/virt/vmx/tdx/seamcall.o
work again
- Do not do ROM range scans and memory validation when the kernel is
running as a SEV-SNP guest as those can get problematic and, before
that, are not really needed in such a guest
- Exclude the build-time generated vdso-image-x32.o object from objtool
validation and in particular the return sites in there due to a
warning which fires when an unpatched return thunk is being used
- Improve the NMI CPUs stall message to show additional information
about the state of each CPU wrt the NMI handler
- Enable gcc named address spaces support only on !KCSAN configs due to
compiler options incompatibility
- Revert a change which was trying to use GB pages for mapping regions
only when the regions would be large enough but that change lead to
kexec failing
- A documentation fixlet
* tag 'x86_urgent_for_v6.9_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/build: Use obj-y to descend into arch/x86/virt/
x86/sev: Skip ROM range scans and validation for SEV-SNP guests
x86/vdso: Fix rethunk patching for vdso-image-x32.o too
x86/nmi: Upgrade NMI backtrace stall checks & messages
x86/percpu: Disable named address spaces for KCSAN
Revert "x86/mm/ident_map: Use gbpages only where full GB page should be mapped."
Documentation/x86: Fix title underline length
+64
-64
+1
-1
Documentation/arch/x86/resctrl.rst
+1
-1
Documentation/arch/x86/resctrl.rst
+1
-1
arch/x86/Kbuild
+1
-1
arch/x86/Kbuild
+2
arch/x86/Kconfig
+2
arch/x86/Kconfig
-2
arch/x86/Makefile
-2
arch/x86/Makefile
+1
arch/x86/entry/vdso/Makefile
+1
arch/x86/entry/vdso/Makefile
+2
-2
arch/x86/include/asm/sev.h
+2
-2
arch/x86/include/asm/sev.h
···
218
218
unsigned long npages);
219
219
void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
220
220
unsigned long npages);
221
-
void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
222
221
void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
223
222
void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
224
223
void snp_set_wakeup_secondary_cpu(void);
225
224
bool snp_init(struct boot_params *bp);
226
225
void __noreturn snp_abort(void);
226
+
void snp_dmi_setup(void);
227
227
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
228
228
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
229
229
u64 snp_get_unsupported_features(u64 status);
···
244
244
early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
245
245
static inline void __init
246
246
early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
247
-
static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
248
247
static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { }
249
248
static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { }
250
249
static inline void snp_set_wakeup_secondary_cpu(void) { }
251
250
static inline bool snp_init(struct boot_params *bp) { return false; }
252
251
static inline void snp_abort(void) { }
252
+
static inline void snp_dmi_setup(void) { }
253
253
static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
254
254
{
255
255
return -ENOTTY;
+2
-1
arch/x86/include/asm/x86_init.h
+2
-1
arch/x86/include/asm/x86_init.h
···
30
30
* @reserve_resources: reserve the standard resources for the
31
31
* platform
32
32
* @memory_setup: platform specific memory setup
33
-
*
33
+
* @dmi_setup: platform specific DMI setup
34
34
*/
35
35
struct x86_init_resources {
36
36
void (*probe_roms)(void);
37
37
void (*reserve_resources)(void);
38
38
char *(*memory_setup)(void);
39
+
void (*dmi_setup)(void);
39
40
};
40
41
41
42
/**
+2
-1
arch/x86/kernel/eisa.c
+2
-1
arch/x86/kernel/eisa.c
···
2
2
/*
3
3
* EISA specific code
4
4
*/
5
+
#include <linux/cc_platform.h>
5
6
#include <linux/ioport.h>
6
7
#include <linux/eisa.h>
7
8
#include <linux/io.h>
···
13
12
{
14
13
void __iomem *p;
15
14
16
-
if (xen_pv_domain() && !xen_initial_domain())
15
+
if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
17
16
return 0;
18
17
19
18
p = ioremap(0x0FFFD9, 4);
+14
-10
arch/x86/kernel/nmi.c
+14
-10
arch/x86/kernel/nmi.c
···
580
580
581
581
static char *nmi_check_stall_msg[] = {
582
582
/* */
583
-
/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */
583
+
/* +--------- nmi_seq & 0x1: CPU is currently in NMI handler. */
584
584
/* | +------ cpu_is_offline(cpu) */
585
585
/* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */
586
586
/* | | | NMI handler has been invoked. */
···
628
628
nmi_seq = READ_ONCE(nsp->idt_nmi_seq);
629
629
if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) {
630
630
msgp = "CPU entered NMI handler function, but has not exited";
631
-
} else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) {
632
-
msgp = "CPU is handling NMIs";
633
-
} else {
634
-
idx = ((nsp->idt_seq_snap & 0x1) << 2) |
631
+
} else if (nsp->idt_nmi_seq_snap == nmi_seq ||
632
+
nsp->idt_nmi_seq_snap + 1 == nmi_seq) {
633
+
idx = ((nmi_seq & 0x1) << 2) |
635
634
(cpu_is_offline(cpu) << 1) |
636
635
(nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls));
637
636
msgp = nmi_check_stall_msg[idx];
638
637
if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1))
639
638
modp = ", but OK because ignore_nmis was set";
640
-
if (nmi_seq & 0x1)
641
-
msghp = " (CPU currently in NMI handler function)";
642
-
else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
639
+
if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
643
640
msghp = " (CPU exited one NMI handler function)";
641
+
else if (nmi_seq & 0x1)
642
+
msghp = " (CPU currently in NMI handler function)";
643
+
else
644
+
msghp = " (CPU was never in an NMI handler function)";
645
+
} else {
646
+
msgp = "CPU is handling NMIs";
644
647
}
645
-
pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n",
646
-
__func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies));
648
+
pr_alert("%s: CPU %d: %s%s%s\n", __func__, cpu, msgp, modp, msghp);
649
+
pr_alert("%s: last activity: %lu jiffies ago.\n",
650
+
__func__, j - READ_ONCE(nsp->recv_jiffies));
647
651
}
648
652
}
649
653
-10
arch/x86/kernel/probe_roms.c
-10
arch/x86/kernel/probe_roms.c
···
203
203
unsigned char c;
204
204
int i;
205
205
206
-
/*
207
-
* The ROM memory range is not part of the e820 table and is therefore not
208
-
* pre-validated by BIOS. The kernel page table maps the ROM region as encrypted
209
-
* memory, and SNP requires encrypted memory to be validated before access.
210
-
* Do that here.
211
-
*/
212
-
snp_prep_memory(video_rom_resource.start,
213
-
((system_rom_resource.end + 1) - video_rom_resource.start),
214
-
SNP_PAGE_STATE_PRIVATE);
215
-
216
206
/* video rom */
217
207
upper = adapter_rom_resources[0].start;
218
208
for (start = video_rom_resource.start; start < upper; start += 2048) {
+1
-2
arch/x86/kernel/setup.c
+1
-2
arch/x86/kernel/setup.c
···
9
9
#include <linux/console.h>
10
10
#include <linux/crash_dump.h>
11
11
#include <linux/dma-map-ops.h>
12
-
#include <linux/dmi.h>
13
12
#include <linux/efi.h>
14
13
#include <linux/ima.h>
15
14
#include <linux/init_ohci1394_dma.h>
···
901
902
efi_init();
902
903
903
904
reserve_ibft_region();
904
-
dmi_setup();
905
+
x86_init.resources.dmi_setup();
905
906
906
907
/*
907
908
* VMware detection requires dmi to be available, so this
+12
-15
arch/x86/kernel/sev.c
+12
-15
arch/x86/kernel/sev.c
···
23
23
#include <linux/platform_device.h>
24
24
#include <linux/io.h>
25
25
#include <linux/psp-sev.h>
26
+
#include <linux/dmi.h>
26
27
#include <uapi/linux/sev-guest.h>
27
28
28
29
#include <asm/init.h>
···
794
793
795
794
/* Ask hypervisor to mark the memory pages shared in the RMP table. */
796
795
early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
797
-
}
798
-
799
-
void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op)
800
-
{
801
-
unsigned long vaddr, npages;
802
-
803
-
vaddr = (unsigned long)__va(paddr);
804
-
npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
805
-
806
-
if (op == SNP_PAGE_STATE_PRIVATE)
807
-
early_snp_set_memory_private(vaddr, paddr, npages);
808
-
else if (op == SNP_PAGE_STATE_SHARED)
809
-
early_snp_set_memory_shared(vaddr, paddr, npages);
810
-
else
811
-
WARN(1, "invalid memory op %d\n", op);
812
796
}
813
797
814
798
static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
···
2120
2134
void __head __noreturn snp_abort(void)
2121
2135
{
2122
2136
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
2137
+
}
2138
+
2139
+
/*
2140
+
* SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
2141
+
* enabled, as the alternative (fallback) logic for DMI probing in the legacy
2142
+
* ROM region can cause a crash since this region is not pre-validated.
2143
+
*/
2144
+
void __init snp_dmi_setup(void)
2145
+
{
2146
+
if (efi_enabled(EFI_CONFIG_TABLES))
2147
+
dmi_setup();
2123
2148
}
2124
2149
2125
2150
static void dump_cpuid_table(void)
+2
arch/x86/kernel/x86_init.c
+2
arch/x86/kernel/x86_init.c
···
3
3
*
4
4
* For licencing details see kernel-base/COPYING
5
5
*/
6
+
#include <linux/dmi.h>
6
7
#include <linux/init.h>
7
8
#include <linux/ioport.h>
8
9
#include <linux/export.h>
···
67
66
.probe_roms = probe_roms,
68
67
.reserve_resources = reserve_standard_io_resources,
69
68
.memory_setup = e820__memory_setup_default,
69
+
.dmi_setup = dmi_setup,
70
70
},
71
71
72
72
.mpparse = {
+5
-18
arch/x86/mm/ident_map.c
+5
-18
arch/x86/mm/ident_map.c
···
26
26
for (; addr < end; addr = next) {
27
27
pud_t *pud = pud_page + pud_index(addr);
28
28
pmd_t *pmd;
29
-
bool use_gbpage;
30
29
31
30
next = (addr & PUD_MASK) + PUD_SIZE;
32
31
if (next > end)
33
32
next = end;
34
33
35
-
/* if this is already a gbpage, this portion is already mapped */
36
-
if (pud_leaf(*pud))
37
-
continue;
38
-
39
-
/* Is using a gbpage allowed? */
40
-
use_gbpage = info->direct_gbpages;
41
-
42
-
/* Don't use gbpage if it maps more than the requested region. */
43
-
/* at the begining: */
44
-
use_gbpage &= ((addr & ~PUD_MASK) == 0);
45
-
/* ... or at the end: */
46
-
use_gbpage &= ((next & ~PUD_MASK) == 0);
47
-
48
-
/* Never overwrite existing mappings */
49
-
use_gbpage &= !pud_present(*pud);
50
-
51
-
if (use_gbpage) {
34
+
if (info->direct_gbpages) {
52
35
pud_t pudval;
53
36
37
+
if (pud_present(*pud))
38
+
continue;
39
+
40
+
addr &= PUD_MASK;
54
41
pudval = __pud((addr - info->offset) | info->page_flag);
55
42
set_pud(pud, pudval);
56
43
continue;
+18
arch/x86/mm/mem_encrypt_amd.c
+18
arch/x86/mm/mem_encrypt_amd.c
···
492
492
*/
493
493
if (sev_status & MSR_AMD64_SEV_ENABLED)
494
494
ia32_disable();
495
+
496
+
/*
497
+
* Override init functions that scan the ROM region in SEV-SNP guests,
498
+
* as this memory is not pre-validated and would thus cause a crash.
499
+
*/
500
+
if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
501
+
x86_init.mpparse.find_mptable = x86_init_noop;
502
+
x86_init.pci.init_irq = x86_init_noop;
503
+
x86_init.resources.probe_roms = x86_init_noop;
504
+
505
+
/*
506
+
* DMI setup behavior for SEV-SNP guests depends on
507
+
* efi_enabled(EFI_CONFIG_TABLES), which hasn't been
508
+
* parsed yet. snp_dmi_setup() will run after that
509
+
* parsing has happened.
510
+
*/
511
+
x86_init.resources.dmi_setup = snp_dmi_setup;
512
+
}
495
513
}
496
514
497
515
void __init mem_encrypt_free_decrypted_mem(void)