aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/head64.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/head64.c')
-rw-r--r--arch/x86/kernel/head64.c236
1 files changed, 191 insertions, 45 deletions
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 206a4b6144c2..6a3cfaf6b72a 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -19,14 +19,14 @@
#include <linux/start_kernel.h>
#include <linux/io.h>
#include <linux/memblock.h>
-#include <linux/mem_encrypt.h>
+#include <linux/cc_platform.h>
+#include <linux/pgtable.h>
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/setup.h>
#include <asm/desc.h>
-#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
@@ -36,6 +36,11 @@
#include <asm/microcode.h>
#include <asm/kasan.h>
#include <asm/fixmap.h>
+#include <asm/realmode.h>
+#include <asm/extable.h>
+#include <asm/trapnr.h>
+#include <asm/sev.h>
+#include <asm/tdx.h>
/*
* Manage page tables very early on.
@@ -61,7 +66,25 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
EXPORT_SYMBOL(vmemmap_base);
#endif
-#define __head __section(.head.text)
+/*
+ * GDT used on the boot CPU before switching to virtual addresses.
+ */
+static struct desc_struct startup_gdt[GDT_ENTRIES] = {
+ [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
+ [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
+};
+
+/*
+ * Address needs to be set at runtime because it references the startup_gdt
+ * while the kernel still uses a direct mapping.
+ */
+static struct desc_ptr startup_gdt_descr = {
+ .size = sizeof(startup_gdt),
+ .address = 0,
+};
+
+#define __head __section(".head.text")
static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
{
@@ -82,7 +105,7 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
static bool __head check_la57_support(unsigned long physaddr)
{
/*
- * 5-level paging is detected and enabled at kernel decomression
+ * 5-level paging is detected and enabled at kernel decompression
* stage. Only check if it has been enabled there.
*/
if (!(native_read_cr4() & X86_CR4_LA57))
@@ -104,6 +127,49 @@ static bool __head check_la57_support(unsigned long physaddr)
}
#endif
+static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
+{
+ unsigned long vaddr, vaddr_end;
+ int i;
+
+ /* Encrypt the kernel and related (if SME is active) */
+ sme_encrypt_kernel(bp);
+
+ /*
+ * Clear the memory encryption mask from the .bss..decrypted section.
+ * The bss section will be memset to zero later in the initialization so
+ * there is no need to zero it after changing the memory encryption
+ * attribute.
+ */
+ if (sme_get_me_mask()) {
+ vaddr = (unsigned long)__start_bss_decrypted;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+
+ for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+ /*
+ * On SNP, transition the page to shared in the RMP table so that
+ * it is consistent with the page table attribute change.
+ *
+ * __start_bss_decrypted has a virtual address in the high range
+ * mapping (kernel .text). PVALIDATE, by way of
+ * early_snp_set_memory_shared(), requires a valid virtual
+ * address but the kernel is currently running off of the identity
+ * mapping so use __pa() to get a *currently* valid virtual address.
+ */
+ early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD);
+
+ i = pmd_index(vaddr);
+ pmd[i] -= sme_get_me_mask();
+ }
+ }
+
+ /*
+ * Return the SME encryption mask (if SME is active) to be used as a
+ * modifier for the initial pgdir entry programmed into CR3.
+ */
+ return sme_get_me_mask();
+}
+
/* Code in __startup_64() can be relocated during execution, but the compiler
* doesn't have to generate PC-relative relocations when accessing globals from
* that function. Clang actually does not generate them, which leads to
@@ -113,7 +179,6 @@ static bool __head check_la57_support(unsigned long physaddr)
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
- unsigned long vaddr, vaddr_end;
unsigned long load_delta, *p;
unsigned long pgtable_flags;
pgdval_t *pgd;
@@ -141,9 +206,6 @@ unsigned long __head __startup_64(unsigned long physaddr,
if (load_delta & ~PMD_PAGE_MASK)
for (;;);
- /* Activate Secure Memory Encryption (SME) if supported and enabled */
- sme_enable(bp);
-
/* Include the SME encryption mask in the fixup value */
load_delta += sme_get_me_mask();
@@ -254,38 +316,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
*/
*fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask();
- /* Encrypt the kernel and related (if SME is active) */
- sme_encrypt_kernel(bp);
-
- /*
- * Clear the memory encryption mask from the .bss..decrypted section.
- * The bss section will be memset to zero later in the initialization so
- * there is no need to zero it after changing the memory encryption
- * attribute.
- */
- if (mem_encrypt_active()) {
- vaddr = (unsigned long)__start_bss_decrypted;
- vaddr_end = (unsigned long)__end_bss_decrypted;
- for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
- i = pmd_index(vaddr);
- pmd[i] -= sme_get_me_mask();
- }
- }
-
- /*
- * Return the SME encryption mask (if SME is active) to be used as a
- * modifier for the initial pgdir entry programmed into CR3.
- */
- return sme_get_me_mask();
-}
-
-unsigned long __startup_secondary_64(void)
-{
- /*
- * Return the SME encryption mask (if SME is active) to be used as a
- * modifier for the initial pgdir entry programmed into CR3.
- */
- return sme_get_me_mask();
+ return sme_postprocess_startup(bp, pmd);
}
/* Wipe all early page tables except for the kernel symbol map */
@@ -297,7 +328,7 @@ static void __init reset_early_page_tables(void)
}
/* Create a new PMD entry */
-int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
+bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
{
unsigned long physaddr = address - __PAGE_OFFSET;
pgdval_t pgd, *pgd_p;
@@ -307,7 +338,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
/* Invalid address or early pgt is done ? */
if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt))
- return -1;
+ return false;
again:
pgd_p = &early_top_pgt[pgd_index(address)].pgd;
@@ -364,10 +395,10 @@ again:
}
pmd_p[pmd_index(address)] = pmd;
- return 0;
+ return true;
}
-int __init early_make_pgtable(unsigned long address)
+static bool __init early_make_pgtable(unsigned long address)
{
unsigned long physaddr = address - __PAGE_OFFSET;
pmdval_t pmd;
@@ -377,12 +408,30 @@ int __init early_make_pgtable(unsigned long address)
return __early_make_pgtable(address, pmd);
}
+void __init do_early_exception(struct pt_regs *regs, int trapnr)
+{
+ if (trapnr == X86_TRAP_PF &&
+ early_make_pgtable(native_read_cr2()))
+ return;
+
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT) &&
+ trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs))
+ return;
+
+ if (trapnr == X86_TRAP_VE && tdx_early_handle_ve(regs))
+ return;
+
+ early_fixup_exception(regs, trapnr);
+}
+
/* Don't add a printk in there. printk relies on the PDA which is not initialized
yet. */
-static void __init clear_bss(void)
+void __init clear_bss(void)
{
memset(__bss_start, 0,
(unsigned long) __bss_stop - (unsigned long) __bss_start);
+ memset(__brk_base, 0,
+ (unsigned long) __brk_limit - (unsigned long) __brk_base);
}
static unsigned long get_cmd_line_ptr(void)
@@ -445,6 +494,10 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
clear_bss();
+ /*
+ * This needs to happen *before* kasan_early_init() because latter maps stuff
+ * into that page.
+ */
clear_page(init_top_pgt);
/*
@@ -456,8 +509,21 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
kasan_early_init();
+ /*
+ * Flush global TLB entries which could be left over from the trampoline page
+ * table.
+ *
+ * This needs to happen *after* kasan_early_init() as KASAN-enabled .configs
+ * instrument native_write_cr4() so KASAN must be initialized for that
+ * instrumentation to work.
+ */
+ __native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));
+
idt_setup_early_handler();
+ /* Needed before cc_platform_has() can be used for TDX */
+ tdx_early_init();
+
copy_bootdata(__va(real_mode_data));
/*
@@ -489,3 +555,83 @@ void __init x86_64_start_reservations(char *real_mode_data)
start_kernel();
}
+
+/*
+ * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
+ * used until the idt_table takes over. On the boot CPU this happens in
+ * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
+ * this happens in the functions called from head_64.S.
+ *
+ * The idt_table can't be used that early because all the code modifying it is
+ * in idt.c and can be instrumented by tracing or KASAN, which both don't work
+ * during early CPU bringup. Also the idt_table has the runtime vectors
+ * configured which require certain CPU state to be setup already (like TSS),
+ * which also hasn't happened yet in early CPU bringup.
+ */
+static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
+
+static struct desc_ptr bringup_idt_descr = {
+ .size = (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1,
+ .address = 0, /* Set at runtime */
+};
+
+static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler)
+{
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ struct idt_data data;
+ gate_desc desc;
+
+ init_idt_data(&data, n, handler);
+ idt_init_desc(&desc, &data);
+ native_write_idt_entry(idt, n, &desc);
+#endif
+}
+
+/* This runs while still in the direct mapping */
+static void startup_64_load_idt(unsigned long physbase)
+{
+ struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase);
+ gate_desc *idt = fixup_pointer(bringup_idt_table, physbase);
+
+
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+ void *handler;
+
+ /* VMM Communication Exception */
+ handler = fixup_pointer(vc_no_ghcb, physbase);
+ set_bringup_idt_handler(idt, X86_TRAP_VC, handler);
+ }
+
+ desc->address = (unsigned long)idt;
+ native_load_idt(desc);
+}
+
+/* This is used when running on kernel addresses */
+void early_setup_idt(void)
+{
+ /* VMM Communication Exception */
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+ setup_ghcb();
+ set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb);
+ }
+
+ bringup_idt_descr.address = (unsigned long)bringup_idt_table;
+ native_load_idt(&bringup_idt_descr);
+}
+
+/*
+ * Setup boot CPU state needed before kernel switches to virtual addresses.
+ */
+void __head startup_64_setup_env(unsigned long physbase)
+{
+ /* Load GDT */
+ startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase);
+ native_load_gdt(&startup_gdt_descr);
+
+ /* New GDT is live - reload data segment registers */
+ asm volatile("movl %%eax, %%ds\n"
+ "movl %%eax, %%ss\n"
+ "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
+
+ startup_64_load_idt(physbase);
+}