x86: SMP Support for x86 UEFI Tests
Subsystems (2)
Sean Christopherson
reviewerv4 cover x86: SMP Support for x86 UEFI Tests
This is Varad's series to bring multi-vcpu support to UEFI tests on x86, with some relatively minor massaging by me. The only change I made that I suspect might be controversial is squashing start16.S and start32.S into a single trampolines.S.
Most of the necessary AP bringup code already exists within kvm-unit-tests' cstart64.S, and has now been either rewritten in C or moved to a common location to be shared between EFI and non-EFI test builds.
A call gate is used to transition from 16-bit to 32-bit mode, since EFI may not load the 32-bit entrypoint low enough to be reachable from the SIPI vector.
v4:
- Add an explict magic string in dummy.c for probing.
- Reduce #ifdefs via macros
- Consolidate final "AP online" code.
- Misc tweaks, e.g. to adhere to preferred style.
v3:
- Unbreak i386 build, ingest seanjc's reviews from v2.a
- https://lore.kernel.org/all/[email protected]
v2: https://lore.kernel.org/kvm/[email protected]/
Sean Christopherson (3):
x86: Use an explicit magic string to detect that dummy.efi passes
x86: Rename ap_init() to bringup_aps()
x86: Add ap_online() to consolidate final "AP is alive!" code
Varad Gautam (10):
x86: Share realmode trampoline between i386 and x86_64
x86: Move ap_init() to smp.c
x86: Move load_idt() to desc.c
x86: desc: Split IDT entry setup into a generic helper
x86: Move load_gdt_tss() to desc.c
x86: efi: Provide a stack within testcase memory
x86: efi: Provide percpu storage
x86: Move 32-bit => 64-bit transition code to trampolines.S
x86: efi, smp: Transition APs from 16-bit to 32-bit mode
x86: Provide a common 64-bit AP entrypoint for EFI and non-EFI
lib/alloc_page.h | 3 + lib/x86/apic.c | 2 - lib/x86/asm/setup.h | 3 + lib/x86/desc.c | 38 ++++++++-- lib/x86/desc.h | 4 + lib/x86/setup.c | 82 +++++++++++++++++---- lib/x86/smp.c | 150 +++++++++++++++++++++++++++++++++++++- lib/x86/smp.h | 11 +++ scripts/runtime.bash | 2 +- x86/cstart.S | 48 ++---------- x86/cstart64.S | 125 +------------------------------ x86/dummy.c | 8 ++ x86/efi/crt0-efi-x86_64.S | 3 + x86/efi/efistart64.S | 79 ++++++++++++-------- x86/svm_tests.c | 10 +-- x86/trampolines.S | 129 ++++++++++++++++++++++++++++++++ 16 files changed, 470 insertions(+), 227 deletions(-) create mode 100644 x86/trampolines.S
base-commit: 610c15284a537484682adfb4b6d6313991ab954f
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 1/13 x86: Use an explicit magic string to detect that dummy.efi passes
Print an explicit "Dummy Hello World!" from the dummy "test" that is used by x86 EFI to probe the basic setup. Relying on the last line to match an arbitrary, undocumented string in x86's boot flow is evil and fragile, e.g. a future patch to share boot code between EFI and !EFI will print something AP bringup info after the "enabling apic" line.
--- scripts/runtime.bash | 2 +- x86/dummy.c | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-)
scripts/runtime.bash +1 -1
@@ -132,7 +132,7 @@ function run() last_line=$(premature_failure > >(tail -1)) && { skip=true - if [ "${CONFIG_EFI}" == "y" ] && [[ "${last_line}" =~ "enabling apic" ]]; then + if [ "${CONFIG_EFI}" == "y" ] && [[ "${last_line}" =~ "Dummy Hello World!" ]]; then skip=false fi if [ ${skip} == true ]; then
x86/dummy.c +8 -0
@@ -1,4 +1,12 @@ +#include "libcflat.h" +int main (int argc,char **argv) { +/* +* scripts/runtime.bash uses this test as a canary to determine if the +* basic setup is functional. Print a magic string to let runtime.bash +* know that all is well. +*/ +printf ("Dummy Hello World!" );return 0 ; }
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 2/13 x86: Share realmode trampoline between i386 and x86_64
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
i386 and x86_64 each maintain their own copy of the realmode trampoline (sipi_entry). Move the 16-bit SIPI vector and GDT to a new trampolines.S to be shared by both. The common trampoline file will also be used to shared 32-bit to 64-bit trampoline code.
--- x86/cstart.S | 20 ++++---------------- x86/cstart64.S | 21 ++++----------------- x86/trampolines.S | 30 ++++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+), 33 deletions(-) create mode 100644 x86/trampolines.S
x86/cstart.S +4 -16
@@ -126,10 +126,10 @@ start32: ap_init: cld - sgdtl ap_gdt_descr // must be close to sipi_entry for real mode access to work - lea sipi_entry, %esi + sgdtl ap_rm_gdt_descr // must be close to rm_trampoline for real mode access to work + lea rm_trampoline, %esi xor %edi, %edi - mov $(sipi_end - sipi_entry), %ecx + mov $(rm_trampoline_end - rm_trampoline), %ecx rep movsb mov $APIC_DEFAULT_PHYS_BASE, %eax movl $(APIC_DEST_ALLBUT | APIC_DEST_PHYSICAL | APIC_DM_INIT | APIC_INT_ASSERT), APIC_ICR(%eax)
@@ -146,16 +146,4 @@ online_cpus: .align 2 cpu_online_count: .word 1 -.code16 -sipi_entry: - mov %cr0, %eax - or $1, %eax - mov %eax, %cr0 - lgdtl ap_gdt_descr - sipi_entry - ljmpl $8, $ap_start32 - -ap_gdt_descr: - .word 0 - .long 0 - -sipi_end: +#include "trampolines.S"
x86/cstart64.S +4 -17
@@ -45,8 +45,9 @@ mb_boot_info: .quad 0 pt_root: .quad ptl4 +#include "trampolines.S" + .section .init - .code32 mb_magic = 0x1BADB002
@@ -156,20 +157,6 @@ gdt32: .quad 0x00cf93000000ffff // flat 32-bit data segment gdt32_end: -.code16 -sipi_entry: - mov %cr0, %eax - or $1, %eax - mov %eax, %cr0 - lgdtl gdt32_descr - sipi_entry - ljmpl $8, $ap_start32 - -gdt32_descr: - .word gdt32_end - gdt32 - 1 - .long gdt32 - -sipi_end: - .code32 ap_start32: setup_segments
@@ -243,9 +230,9 @@ online_cpus: ap_init: cld - lea sipi_entry, %rsi + lea rm_trampoline, %rsi xor %rdi, %rdi - mov $(sipi_end - sipi_entry), %rcx + mov $(rm_trampoline_end - rm_trampoline), %rcx rep movsb mov $APIC_DEFAULT_PHYS_BASE, %eax movl $(APIC_DEST_ALLBUT | APIC_DEST_PHYSICAL | APIC_DM_INIT | APIC_INT_ASSERT), APIC_ICR(%rax)
x86/trampolines.S new file +30 -0
@@ -0,0 +1,30 @@ +/* Common bootstrapping code to transition from 16-bit to 32-bit code. */ + +/* EFI provides it's own SIPI sequence to handle relocation. */ +#ifndef CONFIG_EFI +.code16 +.globl rm_trampoline +rm_trampoline: + +/* Store SIPI vector code at the beginning of trampoline. */ +sipi_entry: + mov %cr0, %eax + or $1, %eax + mov %eax, %cr0 + lgdtl ap_rm_gdt_descr - sipi_entry + ljmpl $8, $ap_start32 +sipi_end: + +.globl ap_rm_gdt_descr +ap_rm_gdt_descr: +#ifdef __i386__ + .word 0 + .long 0 +#else + .word gdt32_end - gdt32 - 1 + .long gdt32 +#endif + +.globl rm_trampoline_end +rm_trampoline_end: +#endif
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 3/13 x86: Move ap_init() to smp.c
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
ap_init() copies the SIPI vector to lowmem, sends INIT/SIPI to APs and waits on the APs to come up.
Port this routine to C from asm and move it to smp.c to allow sharing this functionality between the EFI (-fPIC) and non-EFI builds.
Call ap_init() from the EFI setup path to reset the APs to a known location.
--- lib/alloc_page.h | 3 ++ lib/x86/setup.c | 1 + lib/x86/smp.c | 72 ++++++++++++++++++++++++++++++++++++++++++-- lib/x86/smp.h | 5 +++ x86/cstart.S | 19 ------------ x86/cstart64.S | 19 ------------ x86/efi/efistart64.S | 15 +++++++++ x86/svm_tests.c | 10 +++--- 8 files changed, 98 insertions(+), 46 deletions(-)
lib/alloc_page.h +3 -0
@@ -13,6 +13,9 @@#define AREA_ANY_NUMBER 0xff +/* The realmode trampoline gets relocated here during bootup. */ +#define RM_TRAMPOLINE_ADDR 0 +#define AREA_ANY 0x00000#define AREA_MASK 0x0ffff
lib/x86/setup.c +1 -0
@@ -323,6 +323,7 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo)load_idt ();mask_pic_interrupts ();enable_apic (); +ap_init ();enable_x2apic ();smp_init ();setup_page_table ();
lib/x86/smp.c +70 -2
98 lines not on this page · raw message
lib/x86/smp.h +5 -0
@@ -3,6 +3,8 @@#include <stddef.h> #include <asm/spinlock.h> +#include "libcflat.h" +#include "atomic.h" /* Offsets into the per-cpu page. */ struct percpu_data {
@@ -78,5 +80,8 @@ void on_cpu(int cpu, void (*function)(void *data), void *data);void on_cpu_async (int cpu,void (*function)(void *data),void *data);void on_cpus (void (*function)(void *data),void *data);void smp_reset_apic (void ); +void ap_init (void ); + +extern atomic_t cpu_online_count;#endif
x86/cstart.S +0 -19
@@ -124,26 +124,7 @@ start32: push %eax call exit -ap_init: - cld - sgdtl ap_rm_gdt_descr // must be close to rm_trampoline for real mode access to work - lea rm_trampoline, %esi - xor %edi, %edi - mov $(rm_trampoline_end - rm_trampoline), %ecx - rep movsb - mov $APIC_DEFAULT_PHYS_BASE, %eax - movl $(APIC_DEST_ALLBUT | APIC_DEST_PHYSICAL | APIC_DM_INIT | APIC_INT_ASSERT), APIC_ICR(%eax) - movl $(APIC_DEST_ALLBUT | APIC_DEST_PHYSICAL | APIC_DM_STARTUP), APIC_ICR(%eax) - call fwcfg_get_nb_cpus -1: pause - cmpw %ax, cpu_online_count - jne 1b - ret - online_cpus: .fill (max_cpus + 7) / 8, 1, 0 -.align 2 -cpu_online_count: .word 1 - #include "trampolines.S"
x86/cstart64.S +0 -19
@@ -2,7 +2,6 @@ #include "apic-defs.h" .globl online_cpus -.globl cpu_online_count ipi_vector = 0x20
@@ -227,21 +226,3 @@ lvl5: online_cpus: .fill (max_cpus + 7) / 8, 1, 0 - -ap_init: - cld - lea rm_trampoline, %rsi - xor %rdi, %rdi - mov $(rm_trampoline_end - rm_trampoline), %rcx - rep movsb - mov $APIC_DEFAULT_PHYS_BASE, %eax - movl $(APIC_DEST_ALLBUT | APIC_DEST_PHYSICAL | APIC_DM_INIT | APIC_INT_ASSERT), APIC_ICR(%rax) - movl $(APIC_DEST_ALLBUT | APIC_DEST_PHYSICAL | APIC_DM_STARTUP), APIC_ICR(%rax) - call fwcfg_get_nb_cpus -1: pause - cmpw %ax, cpu_online_count - jne 1b - ret - -.align 2 -cpu_online_count: .word 1
x86/efi/efistart64.S +15 -0
@@ -57,3 +57,18 @@ load_gdt_tss: pushq $0x08 /* 2nd entry in gdt64: 64-bit code segment */ pushq %rdi lretq + +.code16 + +.globl rm_trampoline +rm_trampoline: + +.globl sipi_entry +sipi_entry: + jmp sipi_entry + +.globl sipi_end +sipi_end: + +.globl rm_trampoline_end +rm_trampoline_end:
x86/svm_tests.c +4 -6
@@ -17,8 +17,6 @@ static void *scratch_page;#define LATENCY_RUNS 1000000 -extern u16 cpu_online_count; -u64 tsc_start;u64 tsc_end;
@@ -1955,20 +1953,20 @@ static void init_startup_prepare(struct svm_test *test)on_cpu (1 , get_tss_entry, &tss_entry); - orig_cpu_count = cpu_online_count; + orig_cpu_count =atomic_read (&cpu_online_count);apic_icr_write (APIC_DEST_PHYSICAL |APIC_DM_INIT |APIC_INT_ASSERT , id_map[1 ]);delay (100000000ULL ); - --cpu_online_count; +atomic_dec (&cpu_online_count); tss_entry->type &= ~DESC_BUSY ;apic_icr_write (APIC_DEST_PHYSICAL |APIC_DM_STARTUP , id_map[1 ]); -for (i =0 ; i <5 && cpu_online_count < orig_cpu_count; i++) +for (i =0 ; i <5 &&atomic_read (&cpu_online_count) < orig_cpu_count; i++)delay (100000000ULL ); }
@@ -1979,7 +1977,7 @@ static bool init_startup_finished(struct svm_test *test)static bool init_startup_check (struct svm_test *test) { -return cpu_online_count == orig_cpu_count; +return atomic_read (&cpu_online_count) == orig_cpu_count; }static volatile bool init_intercept;
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 4/13 x86: Move load_idt() to desc.c
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
This allows sharing IDT setup code between EFI (-fPIC) and non-EFI builds.
--- lib/x86/desc.c | 5 +++++ lib/x86/desc.h | 1 + lib/x86/setup.c | 1 - x86/cstart.S | 2 +- x86/cstart64.S | 3 ++- x86/efi/efistart64.S | 5 ----- 6 files changed, 9 insertions(+), 8 deletions(-)
lib/x86/desc.c +5 -0
@@ -294,6 +294,11 @@ void setup_idt(void)handle_exception (13 , check_exception_table); } +void load_idt (void ) +{ +lidt (&idt_descr); +} +unsigned exception_vector (void ) {return this_cpu_read_exception_vector ();
lib/x86/desc.h +1 -0
@@ -4,6 +4,7 @@#include <setjmp.h> void setup_idt (void ); +void load_idt (void );void setup_alt_stack (void );struct ex_regs {
lib/x86/setup.c +0 -1
@@ -170,7 +170,6 @@ void setup_multiboot(struct mbi_bootinfo *bi)#ifdef CONFIG_EFI /* From x86/efi/efistart64.S */ -extern void load_idt (void );extern void load_gdt_tss (size_t tss_offset);static efi_status_t setup_memory_allocator (efi_bootinfo_t *efi_bootinfo)
x86/cstart.S +1 -1
@@ -35,7 +35,7 @@ mb_flags = 0x0 mb_cmdline = 16 .macro setup_tr_and_percpu - lidt idt_descr + call load_idt push %esp call setup_tss addl $4, %esp
x86/cstart64.S +2 -1
@@ -66,7 +66,6 @@ MSR_GS_BASE = 0xc0000101 .endm .macro load_tss - lidtq idt_descr movq %rsp, %rdi call setup_tss ltr %ax
@@ -175,6 +174,7 @@ save_id: ap_start64: call reset_apic + call load_idt load_tss call enable_apic call save_id
@@ -188,6 +188,7 @@ ap_start64: start64: call reset_apic + call load_idt load_tss call mask_pic_interrupts call enable_apic
x86/efi/efistart64.S +0 -5
@@ -26,11 +26,6 @@ ptl4: .code64 .text -.globl load_idt -load_idt: - lidtq idt_descr(%rip) - retq - .globl load_gdt_tss load_gdt_tss: /* Load GDT */
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 5/13 x86: desc: Split IDT entry setup into a generic helper
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
EFI bootstrapping code configures a call gate in a later commit to jump from 16-bit to 32-bit code.
Introduce a set_desc_entry() routine which can be used to fill both an interrupt descriptor and a call gate descriptor on x86.
--- lib/x86/desc.c | 27 +++++++++++++++++++++------ lib/x86/desc.h | 2 ++ 2 files changed, 23 insertions(+), 6 deletions(-)
lib/x86/desc.c +21 -6
@@ -57,22 +57,37 @@ __attribute__((regparm(1)))#endif void do_handle_exception (struct ex_regs *regs); -void set_idt_entry (int vec,void *addr,int dpl) +/* +* Fill an idt_entry_t or call gate entry, clearing e_sz bytes first. +* +* This can be used for both IDT entries and call gate entries, since the gate +* descriptor layout is identical to idt_entry_t, except for the absence of +* .offset2 and .reserved fields. To do so, pass in e_sz according to the gate +* descriptor size. +*/ +void set_desc_entry (idt_entry_t *e,size_t e_sz,void *addr, +u16 sel,u16 type,u16 dpl) { -idt_entry_t *e = &boot_idt[vec]; -memset (e,0 ,sizeof *e); +memset (e,0 , e_sz); e->offset0 = (unsigned long )addr; - e->selector =read_cs (); + e->selector = sel; e->ist =0 ; - e->type =14 ; + e->type = type; e->dpl = dpl; e->p =1 ; e->offset1 = (unsigned long )addr >>16 ;#ifdef __x86_64__ - e->offset2 = (unsigned long )addr >>32 ; +if (e_sz ==sizeof (*e)) + e->offset2 = (unsigned long )addr >>32 ;#endif } +void set_idt_entry (int vec,void *addr,int dpl) +{ +idt_entry_t *e = &boot_idt[vec]; +set_desc_entry (e,sizeof *e, addr,read_cs (),14 , dpl); +} +void set_idt_dpl (int vec,u16 dpl) {idt_entry_t *e = &boot_idt[vec];
lib/x86/desc.h +2 -0
@@ -217,6 +217,8 @@ unsigned exception_vector(void);int write_cr4_checking (unsigned long val);unsigned exception_error_code (void );bool exception_rflags_rf (void ); +void set_desc_entry (idt_entry_t *e,size_t e_sz,void *addr, +u16 sel,u16 type,u16 dpl);void set_idt_entry (int vec,void *addr,int dpl);void set_idt_sel (int vec,u16 sel);void set_idt_dpl (int vec,u16 dpl);
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 6/13 x86: Move load_gdt_tss() to desc.c
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
Split load_gdt_tss() functionality into:
1. Load gdt/tss
2. Setup segments in 64-bit mode and update %cs via far-return
and move load_gdt_tss() to desc.c to share this code between EFI and non-EFI tests.
Move the segment setup code specific to EFI into
setup.c:setup_segments64().
--- lib/x86/desc.c | 6 ++++++ lib/x86/desc.h | 1 + lib/x86/setup.c | 25 +++++++++++++++++++++++-- x86/efi/efistart64.S | 27 --------------------------- 4 files changed, 30 insertions(+), 29 deletions(-)
lib/x86/desc.c +6 -0
@@ -361,6 +361,12 @@ void set_gdt_entry(int sel, unsigned long base, u32 limit, u8 type, u8 flags)#endif } +void load_gdt_tss (size_t tss_offset) +{ +lgdt (&gdt_descr); +ltr (tss_offset); +} +#ifndef __x86_64__void set_gdt_task_gate (u16 sel,u16 tss_sel) {
lib/x86/desc.h +1 -0
@@ -223,6 +223,7 @@ void set_idt_entry(int vec, void *addr, int dpl);void set_idt_sel (int vec,u16 sel);void set_idt_dpl (int vec,u16 dpl);void set_gdt_entry (int sel,unsigned long base,u32 limit,u8 access,u8 gran); +void load_gdt_tss (size_t tss_offset);void set_intr_alt_stack (int e,void *fn);void print_current_tss_info (void );handler handle_exception (u8 v,handler fn);
lib/x86/setup.c +23 -2
@@ -169,8 +169,27 @@ void setup_multiboot(struct mbi_bootinfo *bi)#ifdef CONFIG_EFI -/* From x86/efi/efistart64.S */ -extern void load_gdt_tss (size_t tss_offset); +static void setup_segments64 (void ) +{ +/* Update data segments */ +write_ds (KERNEL_DS ); +write_es (KERNEL_DS ); +write_fs (KERNEL_DS ); +write_gs (KERNEL_DS ); +write_ss (KERNEL_DS ); + +/* +* Update the code segment by putting it on the stack before the return +* address, then doing a far return: this will use the new code segment +* along with the address. +*/ + asmvolatile ("pushq %1\n\t" +"lea 1f(%%rip), %0\n\t" +"pushq %0\n\t" +"lretq\n\t" +"1:" + ::"r" ((u64 )KERNEL_DS ),"i" (KERNEL_CS )); +}static efi_status_t setup_memory_allocator (efi_bootinfo_t *efi_bootinfo) {
@@ -275,6 +294,8 @@ static void setup_gdt_tss(void)/* 64-bit setup_tss does not use the stacktop argument. */ tss_offset =setup_tss (NULL );load_gdt_tss (tss_offset); + +setup_segments64 (); }efi_status_t setup_efi (efi_bootinfo_t *efi_bootinfo)
x86/efi/efistart64.S +0 -27
@@ -26,33 +26,6 @@ ptl4: .code64 .text -.globl load_gdt_tss -load_gdt_tss: - /* Load GDT */ - lgdt gdt_descr(%rip) - - /* Load TSS */ - mov %rdi, %rax - ltr %ax - - /* Update data segments */ - mov $0x10, %ax /* 3rd entry in gdt64: 32/64-bit data segment */ - mov %ax, %ds - mov %ax, %es - mov %ax, %fs - mov %ax, %gs - mov %ax, %ss - - /* - * Update the code segment by putting it on the stack before the return - * address, then doing a far return: this will use the new code segment - * along with the address. - */ - popq %rdi - pushq $0x08 /* 2nd entry in gdt64: 64-bit code segment */ - pushq %rdi - lretq - .code16 .globl rm_trampoline
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 7/13 x86: efi: Provide a stack within testcase memory
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
UEFI test builds currently use the stack pointer configured by the UEFI implementation.
Reserve stack space in .data for EFI testcases and switch %rsp to use this memory on early boot. This provides one 4K page per CPU to store its stack.
--- x86/efi/crt0-efi-x86_64.S | 3 +++ x86/efi/efistart64.S | 6 ++++++ 2 files changed, 9 insertions(+)
x86/efi/crt0-efi-x86_64.S +3 -0
@@ -58,6 +58,9 @@ _start: popq %rdi popq %rsi + /* Switch away from EFI stack. */ + lea stacktop(%rip), %rsp + call efi_main addq $8, %rsp
x86/efi/efistart64.S +6 -0
@@ -4,7 +4,13 @@ #include "asm-generic/page.h" #include "crt0-efi-x86_64.S" + +/* Reserve stack in .data */ .data +.align PAGE_SIZE + . = . + PAGE_SIZE * MAX_TEST_CPUS +.globl stacktop +stacktop: .align PAGE_SIZE .globl ptl2
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 8/13 x86: efi: Provide percpu storage
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
UEFI tests do not update MSR_GS_BASE during bringup, and continue using the GS_BASE set up by the UEFI implementation for percpu storage.
Update this MSR during setup_segments64() to allow storing percpu data at a sane location reserved by the testcase, and ensure that this happens before any operation that ends up storing to the percpu space.
Since apic_ops (touched by reset_apic()) is percpu, move reset_apic() to happen after setup_gdt_tss(). With this, ap_init() can now use percpu apic_ops via apic_icr_write().
--- lib/x86/setup.c | 7 ++++++- lib/x86/smp.c | 14 -------------- 2 files changed, 6 insertions(+), 15 deletions(-)
lib/x86/setup.c +6 -1
@@ -169,6 +169,8 @@ void setup_multiboot(struct mbi_bootinfo *bi)#ifdef CONFIG_EFI +static struct percpu_data __percpu_data[MAX_TEST_CPUS ]; +static void setup_segments64 (void ) {/* Update data segments */
@@ -178,6 +180,9 @@ static void setup_segments64(void)write_gs (KERNEL_DS );write_ss (KERNEL_DS ); +/* Setup percpu base */ +wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]); +/* * Update the code segment by putting it on the stack before the return * address, then doing a far return: this will use the new code segment
@@ -337,8 +342,8 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo)return status; } -reset_apic ();setup_gdt_tss (); +reset_apic ();setup_idt ();load_idt ();mask_pic_interrupts ();
lib/x86/smp.c +0 -14
@@ -184,25 +184,11 @@ void ap_init(void)setup_rm_gdt (); -#ifdef CONFIG_EFI -/* -* apic_icr_write() is unusable on CONFIG_EFI until percpu area gets set up. -* Use raw writes to APIC_ICR to send IPIs for time being. -*/ -volatile u32 *apic_icr = (volatile u32 *) (APIC_DEFAULT_PHYS_BASE +APIC_ICR ); - -/* INIT */ - *apic_icr =APIC_DEST_ALLBUT |APIC_DEST_PHYSICAL |APIC_DM_INIT |APIC_INT_ASSERT ; - -/* SIPI */ - *apic_icr =APIC_DEST_ALLBUT |APIC_DEST_PHYSICAL |APIC_DM_STARTUP ; -#else /* INIT */ apic_icr_write (APIC_DEST_ALLBUT |APIC_DEST_PHYSICAL |APIC_DM_INIT |APIC_INT_ASSERT ,0 );/* SIPI */ apic_icr_write (APIC_DEST_ALLBUT |APIC_DEST_PHYSICAL |APIC_DM_STARTUP ,0 ); -#endif _cpu_count =fwcfg_get_nb_cpus ();
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Re: [kvm-unit-tests PATCH v4 08/13] x86: efi: Provide percpu storage
Writing to MSR_IA32_APICBASE in reset_apic() is an
intercepted operation and causes #VC exception when the test is launched as an SEV-ES guest.
So calling reset_apic() before IDT is set up in setup_idt() and load_idt() might cause problems. Similarly if accessing _percpu_data array element in setup_segments64() results in a page fault, this will lead to a double fault.
Hence move reset_apic() call and percpu data setup after setup_idt() and load_idt().
--- lib/x86/setup.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
lib/x86/setup.c +5 -6
@@ -192,8 +192,6 @@ static void setup_segments64(void)write_gs (KERNEL_DS );write_ss (KERNEL_DS ); -/* Setup percpu base */ -wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]);/* * Update the code segment by putting it on the stack before the return
@@ -322,7 +320,7 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) }return status; } - + status =setup_rsdp (efi_bootinfo);if (status !=EFI_SUCCESS ) {printf ("Cannot find RSDP in EFI system table\n" );
@@ -344,14 +342,15 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) }setup_gdt_tss (); +setup_segments64 (); +setup_idt (); +load_idt ();/* * GS.base, which points at the per-vCPU data, must be configured prior * to resetting the APIC, which sets the per-vCPU APIC ops. */ -setup_segments64 (); +wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]);reset_apic (); -setup_idt (); -load_idt ();mask_pic_interrupts ();setup_page_table ();enable_apic ();
--
2.34.1
Sean Christopherson
reviewerRe: [kvm-unit-tests PATCH v4 08/13] x86: efi: Provide percpu storage
Please send a standalone patch (with a SOB), this series has already been merged.
Quoted 2 lines · Vasant Karasulli
Writing to
MSR_IA32_APICBASEinreset_apic()is an intercepted operation
Is _typically_ an intercepted operation, architecturally there's nothing that requires APICBASE to emulated.
Quoted 8 lines
and causes #VC exception when the test is launched as an SEV-ES guest.
So calling
reset_apic()before IDT is set up insetup_idt()andload_idt()might cause problems.Similarly if accessing
_percpu_dataarray element insetup_segments64()results in a page fault, this will lead to a double fault.
Well, yeah, but loading the IDT isn't going to magically fix the #PF. I suspect you're actually referring to the emulated MMIO #NPF=>#VC when accessing the xAPIC through MMIO?
Quoted 31 lines
Hence move
reset_apic()call and percpu data setup aftersetup_idt()andload_idt().--- lib/x86/setup.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)lib/x86/setup.c +1
-3@@ -192,8 +192,6 @@ static void setup_segments64(void)write_gs (KERNEL_DS );write_ss (KERNEL_DS ); -/* Setup percpu base */ -wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]);/* * Update the code segment by putting it on the stack before the return @@ -322,7 +320,7 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) }return status; } - + status =setup_rsdp (efi_bootinfo);if (status !=EFI_SUCCESS ) {printf ("Cannot find RSDP in EFI system table\n" );@@ -344,14 +342,15 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) }
lib/x86/setup.c efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) · line 352
Quoted 10 lines
lib/x86/setup.c +4
-1setup_gdt_tss (); +setup_segments64 (); +setup_idt (); +load_idt ();/* * GS.base, which points at the per-vCPU data, must be configured prior * to resetting the APIC, which sets the per-vCPU APIC ops. */ -setup_segments64 (); +wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]);
This absolutely needs a comment, otherwise someone will wonder why on earth GS.base isn't configured during setup_segments64(). Easist thing is probalby to split and reword the above comment, e.g.
/* * Load GS.base with the per-vCPU data. This must be done after loading * the IDT as reading the APIC ID may #VC when running as an SEV-ES guest. */ wrmsr(MSR_GS_BASE, (u64)&__percpu_data[pre_boot_apic_id()]); /* * Resetting the APIC sets the per-vCPU APIC ops and so must be done * after loading GS.base with the per-vCPU data. */ reset_apic();
Quoted 9 lines
lib/x86/setup.c +0
-3reset_apic (); -setup_idt (); -load_idt ();mask_pic_interrupts ();setup_page_table ();enable_apic (); --2.34.1
Re: [kvm-unit-tests PATCH v4 08/13] x86: efi: Provide percpu storage
Quoted 2 lines · Sean Christopherson
Please send a standalone patch (with a SOB), this series has already been merged.
Sorry, I will send a new patch.
Quoted 6 lines · Vasant Karasulli
Quoted 2 lines
Writing to
MSR_IA32_APICBASEinreset_apic()is an intercepted operationIs _typically_ an intercepted operation, architecturally there's nothing that requires APICBASE to emulated.
Right, I will improve the wording.
Quoted 7 lines
Quoted 6 lines
and causes #VC exception when the test is launched as an SEV-ES guest.
So calling
reset_apic()before IDT is set up insetup_idt()andload_idt()might cause problems.
Quoted 6 lines
Quoted 2 lines
Similarly if accessing
_percpu_dataarray element insetup_segments64()results in a page fault, this will lead to a double fault.Well, yeah, but loading the IDT isn't going to magically fix the #PF. I suspect you're actually referring to the emulated MMIO #NPF=>#VC when accessing the xAPIC through MMIO?
Damn, I overlooked the pre_boot_apic_id() call, thought just accessing the array element is the culprit. :(
Quoted 32 lines
Quoted 32 lines
Hence move
reset_apic()call and percpu data setup aftersetup_idt()andload_idt().--- lib/x86/setup.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)lib/x86/setup.c +1
-3@@ -192,8 +192,6 @@ static void setup_segments64(void)write_gs (KERNEL_DS );write_ss (KERNEL_DS ); -/* Setup percpu base */ -wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]);/* * Update the code segment by putting it on the stack before the return @@ -322,7 +320,7 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) }return status; } - + status =setup_rsdp (efi_bootinfo);if (status !=EFI_SUCCESS ) {printf ("Cannot find RSDP in EFI system table\n" );@@ -344,14 +342,15 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) }
Quoted 14 lines
lib/x86/setup.c efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo) · line 352
Quoted 10 lines
lib/x86/setup.c +4
-1setup_gdt_tss (); +setup_segments64 (); +setup_idt (); +load_idt ();/* * GS.base, which points at the per-vCPU data, must be configured prior * to resetting the APIC, which sets the per-vCPU APIC ops. */ -setup_segments64 (); +wrmsr (MSR_GS_BASE , (u64)&__percpu_data[pre_boot_apic_id ()]);This absolutely needs a comment, otherwise someone will wonder why on earth GS.base isn't configured during
setup_segments64(). Easist thing is probalby to split and reword the above comment, e.g.
Will do that. Thanks for the suggestion and the review.
Quoted 13 lines
/* * Load GS.base with the per-vCPU data. This must be done after loading * the IDT as reading the APIC ID may #VC when running as an SEV-ES guest. */ wrmsr(MSR_GS_BASE, (u64)&__percpu_data[pre_boot_apic_id()]); /* * Resetting the APIC sets the per-vCPU APIC ops and so must be done * after loading GS.base with the per-vCPU data. */ reset_apic();
Quoted 9 lines
Quoted 9 lines
lib/x86/setup.c +0
-3reset_apic (); -setup_idt (); -load_idt ();mask_pic_interrupts ();setup_page_table ();enable_apic (); --2.34.1
Thanks,
Vasant Karasulli
Kernel generalist
www.suse.com<http://www.suse.com>
[https://www.suse.com/assets/img/social-platforms-suse-logo.png]<http://www.suse.com/>
SUSE - Open Source Solutions for Enterprise Servers & Cloud<http://www.suse.com/>
Modernize your infrastructure with SUSE Linux Enterprise servers, cloud technology for IaaS, and SUSE's software-defined storage. www.suse.com
Sean Christopherson
reviewerPATCH v4 9/13 x86: Move 32-bit => 64-bit transition code to trampolines.S
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
Move the code for transitioning from unpaged 32-bit mode to paged 64-bit mode to trampoline.S, it can be shared across EFI and non-EFI builds.
Leave 5-level paging behind for the time being, EFI doesn't yet support support disabling paging, which is required to get from 4-level to 5-level paging.
--- x86/cstart64.S | 60 --------------------------------------- x86/trampolines.S | 71 +++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 69 insertions(+), 62 deletions(-)
x86/cstart64.S +0 -60
@@ -56,36 +56,12 @@ mb_flags = 0x0 .long mb_magic, mb_flags, 0 - (mb_magic + mb_flags) mb_cmdline = 16 -MSR_GS_BASE = 0xc0000101 - -.macro setup_percpu_area - lea -4096(%esp), %eax - mov $0, %edx - mov $MSR_GS_BASE, %ecx - wrmsr -.endm - .macro load_tss movq %rsp, %rdi call setup_tss ltr %ax .endm -.macro setup_segments - mov $MSR_GS_BASE, %ecx - rdmsr - - mov $0x10, %bx - mov %bx, %ds - mov %bx, %es - mov %bx, %fs - mov %bx, %gs - mov %bx, %ss - - /* restore MSR_GS_BASE */ - wrmsr -.endm - .globl start start: mov %ebx, mb_boot_info
@@ -118,33 +94,6 @@ switch_to_5level: call enter_long_mode jmpl $8, $lvl5 -prepare_64: - lgdt gdt_descr - setup_segments - - xor %eax, %eax - mov %eax, %cr4 - -enter_long_mode: - mov %cr4, %eax - bts $5, %eax // pae - mov %eax, %cr4 - - mov pt_root, %eax - mov %eax, %cr3 - -efer = 0xc0000080 - mov $efer, %ecx - rdmsr - bts $8, %eax - wrmsr - - mov %cr0, %eax - bts $0, %eax - bts $31, %eax - mov %eax, %cr0 - ret - smp_stacktop: .long stacktop - 4096 .align 16
@@ -155,15 +104,6 @@ gdt32: .quad 0x00cf93000000ffff // flat 32-bit data segment gdt32_end: -.code32 -ap_start32: - setup_segments - mov $-4096, %esp - lock xaddl %esp, smp_stacktop - setup_percpu_area - call prepare_64 - ljmpl $8, $ap_start64 - .code64 save_id: movl $(APIC_DEFAULT_PHYS_BASE + APIC_ID), %eax
x86/trampolines.S +69 -2
78 lines not on this page · raw message
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 10/13 x86: efi, smp: Transition APs from 16-bit to 32-bit mode
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
Sending INIT/SIPI to APs from ap_init() resets them into 16-bit mode to loop into sipi_entry().
To drive the APs into 32-bit mode, the SIPI vector needs:
1. A GDT descriptor reachable from 16-bit code (gdt32_descr).
2. A 32-bit entrypoint reachable from 16-bit code (ap_start32).
3. The locations of GDT and the 32-bit entrypoint.
Setting these up at compile time (like on non-EFI builds) is not possible since EFI builds with -shared -fPIC and efistart64.S cannot reference any absolute addresses.
Relative addressing is unavailable on 16-bit mode.
Moreover, EFI may not load the 32-bit entrypoint to be reachable from 16-bit mode.
To overcome these problems,
1. Fill the GDT descriptor at runtime after relocating [sipi_entry-sipi_end] to lowmem. Since sipi_entry does not know the address of this descriptor, use the last two bytes of SIPI page to communicate it.
2. Place a call gate in the GDT to point to ap_start32.
3. Popluate sipi_entry() to lcall to ap_start32.
With this, the APs can transition to 32-bit mode and loop at a known location.
--- lib/x86/setup.c | 2 +- lib/x86/smp.c | 81 +++++++++++++++++++++++++++++++++++++++++++- lib/x86/smp.h | 3 ++ x86/efi/efistart64.S | 35 ++++++++++++++++++- x86/trampolines.S | 38 +++++++++++++++++++-- 5 files changed, 153 insertions(+), 6 deletions(-)
lib/x86/setup.c +1 -1
@@ -347,11 +347,11 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo)setup_idt ();load_idt ();mask_pic_interrupts (); +setup_page_table ();enable_apic ();ap_init ();enable_x2apic ();smp_init (); -setup_page_table ();return EFI_SUCCESS ; }
lib/x86/smp.c +80 -1
102 lines not on this page · raw message
lib/x86/smp.h +3 -0
@@ -6,6 +6,9 @@#include "libcflat.h" #include "atomic.h" +/* Address where to store the address of realmode GDT descriptor. */ +#define REALMODE_GDT_LOWMEM (PAGE_SIZE - 2) +/* Offsets into the per-cpu page. */ struct percpu_data {uint32_t smp_id;
x86/efi/efistart64.S +34 -1
@@ -12,6 +12,9 @@ .globl stacktop stacktop: +.globl smp_stacktop +smp_stacktop: .long 0 + .align PAGE_SIZE .globl ptl2 ptl2:
@@ -33,16 +36,46 @@ ptl4: .text .code16 +REALMODE_GDT_LOWMEM = PAGE_SIZE - 2 .globl rm_trampoline rm_trampoline: .globl sipi_entry sipi_entry: - jmp sipi_entry + mov %cr0, %eax + or $1, %eax + mov %eax, %cr0 + + /* Retrieve relocated ap_rm_gdt_descr address at REALMODE_GDT_LOWMEM. */ + mov (REALMODE_GDT_LOWMEM), %ebx + lgdtl (%ebx) + + lcall $0x18, $0x0 + +.globl ap_rm_gdt +ap_rm_gdt: + .quad 0 + .quad 0x00cf9b000000ffff // flat 32-bit code segment + .quad 0x00cf93000000ffff // flat 32-bit data segment + .quad 0 // call gate to 32-bit AP entrypoint +.globl ap_rm_gdt_end +ap_rm_gdt_end: + +.globl ap_rm_gdt_descr +ap_rm_gdt_descr: + .word 0 + .long 0 .globl sipi_end sipi_end: .globl rm_trampoline_end rm_trampoline_end: + +#include "../trampolines.S" + +.code64: + +ap_start64: + jmp ap_start64
x86/trampolines.S +35 -3
@@ -36,6 +36,23 @@ rm_trampoline_end: #ifdef __x86_64__ .code32 +/* + * EFI builds with "-shared -fPIC" and so cannot directly reference any absolute + * address. In 64-bit mode, RIP-relative addressing neatly solves the problem, + * but 32-bit code doesn't have that luxury. Make a dummy CALL to get RIP into + * a GPR in order to emulate RIP-relative for 32-bit transition code. + */ +.macro load_absolute_addr, addr, reg +#ifdef CONFIG_EFI + call 1f +1: + pop \reg + add \addr - 1b, \reg +#else + mov \addr, \reg +#endif +.endm + MSR_GS_BASE = 0xc0000101 .macro setup_percpu_area
@@ -61,7 +78,9 @@ MSR_GS_BASE = 0xc0000101 .endm prepare_64: - lgdt gdt_descr + load_absolute_addr $gdt_descr, %edx + lgdtl (%edx) + setup_segments xor %eax, %eax
@@ -72,7 +91,12 @@ enter_long_mode: bts $5, %eax // pae mov %eax, %cr4 + /* Note, EFI doesn't yet support 5-level paging. */ +#ifdef CONFIG_EFI + load_absolute_addr $ptl4, %eax +#else mov pt_root, %eax +#endif mov %eax, %cr3 efer = 0xc0000080
@@ -87,11 +111,19 @@ efer = 0xc0000080 mov %eax, %cr0 ret +.globl ap_start32 ap_start32: setup_segments + + load_absolute_addr $smp_stacktop, %edx mov $-4096, %esp - lock xaddl %esp, smp_stacktop + lock xaddl %esp, (%edx) + setup_percpu_area call prepare_64 - ljmpl $8, $ap_start64 + + load_absolute_addr $ap_start64, %edx + pushl $0x08 + pushl %edx + lretl #endif
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 11/13 x86: Provide a common 64-bit AP entrypoint for EFI and non-EFI
In reply to Sean ChristophersonFrom: Varad Gautam <[email protected]>
ap_start64() currently serves as the 64-bit entrypoint for non-EFI tests.
Having ap_start64() and save_id() written in asm prevents sharing these routines between EFI and non-EFI tests.
Rewrite them in C and use ap_start64 as the 64-bit entrypoint in the EFI boot flow.
With this, EFI tests support -smp > 1. smptest.efi now passes.
--- lib/x86/apic.c | 2 -- lib/x86/asm/setup.h | 3 +++ lib/x86/setup.c | 53 +++++++++++++++++++++++++++++++++++--------- lib/x86/smp.c | 1 + lib/x86/smp.h | 2 ++ x86/cstart.S | 3 --- x86/cstart64.S | 26 ---------------------- x86/efi/efistart64.S | 5 ----- 8 files changed, 48 insertions(+), 47 deletions(-)
lib/x86/apic.c +0 -2
@@ -243,8 +243,6 @@ void mask_pic_interrupts(void)outb (0xff ,0xa1 ); } -extern unsigned char online_cpus[(MAX_TEST_CPUS +7 ) /8 ]; -void init_apic_map (void ) {unsigned int i, j =0 ;
lib/x86/asm/setup.h +3 -0
@@ -16,4 +16,7 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo);void setup_5level_page_table (void );#endif /* CONFIG_EFI */ +void save_id (void ); +void ap_start64 (void ); +#endif /* _X86_ASM_SETUP_H_ */
lib/x86/setup.c +42 -11
81 lines not on this page · raw message
lib/x86/smp.c +1 -0
@@ -37,6 +37,7 @@ extern u8 stacktop;/* The BSP is online from time zero. */ atomic_t cpu_online_count = { .counter =1 }; +unsigned char online_cpus[(MAX_TEST_CPUS +7 ) /8 ];static __attribute__((used))void ipi (void ) {
lib/x86/smp.h +2 -0
@@ -5,6 +5,7 @@#include <asm/spinlock.h> #include "libcflat.h" #include "atomic.h" +#include "apic-defs.h" /* Address where to store the address of realmode GDT descriptor. */ #define REALMODE_GDT_LOWMEM (PAGE_SIZE - 2)
@@ -86,5 +87,6 @@ void smp_reset_apic(void);void ap_init (void );extern atomic_t cpu_online_count; +extern unsigned char online_cpus[(MAX_TEST_CPUS +7 ) /8 ];#endif
x86/cstart.S +0 -3
@@ -124,7 +124,4 @@ start32: push %eax call exit -online_cpus: - .fill (max_cpus + 7) / 8, 1, 0 - #include "trampolines.S"
x86/cstart64.S +0 -26
@@ -1,8 +1,6 @@ #include "apic-defs.h" -.globl online_cpus - ipi_vector = 0x20 max_cpus = MAX_TEST_CPUS
@@ -105,27 +103,6 @@ gdt32: gdt32_end: .code64 -save_id: - movl $(APIC_DEFAULT_PHYS_BASE + APIC_ID), %eax - movl (%rax), %eax - shrl $24, %eax - lock btsl %eax, online_cpus - retq - -ap_start64: - call reset_apic - call load_idt - load_tss - call enable_apic - call save_id - call enable_x2apic - sti - nop - lock incw cpu_online_count - -1: hlt - jmp 1b - start64: call reset_apic call load_idt
@@ -164,6 +141,3 @@ setup_5level_page_table: lretq lvl5: retq - -online_cpus: - .fill (max_cpus + 7) / 8, 1, 0
x86/efi/efistart64.S +0 -5
@@ -74,8 +74,3 @@ sipi_end: rm_trampoline_end: #include "../trampolines.S" - -.code64: - -ap_start64: - jmp ap_start64
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 12/13 x86: Rename ap_init() to bringup_aps()
In reply to Sean ChristophersonRename the helper that wakes and waits for APs to bringup_aps(), ap_init() is terribly confusing because it's called from the BSP, not APs.
--- lib/x86/setup.c | 2 +- lib/x86/smp.c | 2 +- lib/x86/smp.h | 2 +- x86/cstart.S | 2 +- x86/cstart64.S | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-)
lib/x86/setup.c +1 -1
@@ -357,7 +357,7 @@ efi_status_t setup_efi(efi_bootinfo_t *efi_bootinfo)setup_page_table ();enable_apic ();save_id (); -ap_init (); +bringup_aps ();enable_x2apic ();smp_init ();
lib/x86/smp.c +1 -1
@@ -242,7 +242,7 @@ static void setup_rm_gdt(void)#endif } -void ap_init (void ) +void bringup_aps (void ) {void *rm_trampoline_dst =RM_TRAMPOLINE_ADDR ;size_t rm_trampoline_size = (&rm_trampoline_end - &rm_trampoline) +1 ;
lib/x86/smp.h +1 -1
@@ -84,7 +84,7 @@ void on_cpu(int cpu, void (*function)(void *data), void *data);void on_cpu_async (int cpu,void (*function)(void *data),void *data);void on_cpus (void (*function)(void *data),void *data);void smp_reset_apic (void ); -void ap_init (void ); +void bringup_aps (void );extern atomic_t cpu_online_count;extern unsigned char online_cpus[(MAX_TEST_CPUS +7 ) /8 ];
x86/cstart.S +1 -1
@@ -114,7 +114,7 @@ start32: call save_id call mask_pic_interrupts call enable_apic - call ap_init + call bringup_aps call enable_x2apic call smp_init push $__environ
x86/cstart64.S +1 -1
@@ -118,7 +118,7 @@ start64: mov %rax, __args(%rip) call __setup_args - call ap_init + call bringup_aps call enable_x2apic call smp_init
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Sean Christopherson
reviewerPATCH v4 13/13 x86: Add ap_online() to consolidate final "AP is alive!" code
In reply to Sean ChristophersonAdd ap_online() to consolidate the last stage of onlining an AP CPU.
--- lib/x86/setup.c | 9 +-------- lib/x86/smp.c | 12 ++++++++++++ lib/x86/smp.h | 1 + x86/cstart.S | 8 +++----- 4 files changed, 17 insertions(+), 13 deletions(-)
lib/x86/setup.c +1 -8
@@ -393,12 +393,5 @@ void ap_start64(void)save_id ();enable_apic ();enable_x2apic (); -sti (); - asmvolatile ("nop" ); -printf ("setup: AP %d online\n" ,apic_id ()); -atomic_inc (&cpu_online_count); - -/* Only the BSP runs the test's main(), APs are given work via IPIs. */ -for (;;) - asmvolatile ("hlt" ); +ap_online (); }
lib/x86/smp.c +12 -0
@@ -82,6 +82,18 @@ static void setup_smp_id(void *data)this_cpu_write_smp_id (apic_id ()); } +void ap_online (void ) +{ +irq_enable (); + +printf ("setup: CPU %d online\n" ,apic_id ()); +atomic_inc (&cpu_online_count); + +/* Only the BSP runs the test's main(), APs are given work via IPIs. */ +for (;;) + asmvolatile ("hlt" ); +} +static void __on_cpu (int cpu,void (*function)(void *data),void *data,int wait) {const u32 ipi_icr =APIC_INT_ASSERT |APIC_DEST_PHYSICAL |APIC_DM_FIXED |IPI_VECTOR ;
lib/x86/smp.h +1 -0
@@ -85,6 +85,7 @@ void on_cpu_async(int cpu, void (*function)(void *data), void *data);void on_cpus (void (*function)(void *data),void *data);void smp_reset_apic (void );void bringup_aps (void ); +void ap_online (void );extern atomic_t cpu_online_count;extern unsigned char online_cpus[(MAX_TEST_CPUS +7 ) /8 ];
x86/cstart.S +3 -5
@@ -101,12 +101,10 @@ ap_start32: call save_id call enable_apic call enable_x2apic - sti - nop - lock incw cpu_online_count + call ap_online -1: hlt - jmp 1b + /* ap_online() should never return */ + ud2 start32: setup_tr_and_percpu
Signature · 1 line
2.36.1.476.g0c4daa206d-goog
Hi all,
I ran the tests on these patches and I see 8/11 subtests ofvmware_backdoors.c test fail.
But this failure is because I couldn't figure out the check parameter /sys/module/kvm/parameters/enable_vmware_backdoor on my test machine specified in the unittests.cfg. So this test fails also without the patch.
Rest of the tests look fine.
Thanks,
Vasant