[GIT PULL] x86 fixes

From: Ingo Molnar
Date: Wed Jan 17 2018 - 10:41:47 EST

Linus,

Please pull the latest x86-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-urgent-for-linus

# HEAD: 45d55e7bac4028af93f5fa324e69958a0b868e96 x86/apic/vector: Fix off by one in error path

Misc fixes:

- A rather involved set of memory hardware encryption fixes to support the early
loading of microcode files via the initrd. These are larger than what we
normally take at such a late -rc stage, but there are two mitigating factors:
1) much of the changes are limited to the SME code itself 2) being able to
early load microcode has increased importance in the post-Meltdown/Spectre era.

- An IRQ vector allocator fix

- An Intel RDT driver use-after-free fix

- An APIC driver bug fix/revert to make certain older systems boot again

- A pkeys ABI fix

- TSC calibration fixes

- A kdump fix

out-of-topic modifications in x86-urgent-for-linus:
-----------------------------------------------------
include/linux/crash_core.h # 9f15b9120f56: kdump: Write the correct add
kernel/crash_core.c # 9f15b9120f56: kdump: Write the correct add

Thanks,

Ingo

------------------>
Andi Kleen (1):
x86/idt: Mark IDT tables __initconst

Eric W. Biederman (1):
x86/mm/pkeys: Fix fill_sig_info_pkey

Kirill A. Shutemov (1):
kdump: Write the correct address of mem_section into vmcoreinfo

Len Brown (3):
x86/tsc: Future-proof native_calibrate_tsc()
x86/tsc: Fix erroneous TSC rate on Skylake Xeon
x86/tsc: Print tsc_khz, when it differs from cpu_khz

Thomas Gleixner (2):
x86/intel_rdt/cqm: Prevent use after free
x86/apic/vector: Fix off by one in error path

Tom Lendacky (5):
x86/mm: Clean up register saving in the __enc_copy() assembly code
x86/mm: Use a struct to reduce parameters for SME PGD mapping
x86/mm: Centralize PMD flags in sme_encrypt_kernel()
x86/mm: Prepare sme_encrypt_kernel() for PAGE aligned encryption
x86/mm: Encrypt the initrd earlier for BSP microcode update

Ville Syrjälä (1):
Revert "x86/apic: Remove init_bsp_APIC()"


arch/x86/include/asm/apic.h | 1 +
arch/x86/include/asm/mem_encrypt.h | 4 +-
arch/x86/kernel/apic/apic.c | 49 +++++
arch/x86/kernel/apic/vector.c | 7 +-
arch/x86/kernel/cpu/intel_rdt.c | 8 +-
arch/x86/kernel/head64.c | 4 +-
arch/x86/kernel/idt.c | 12 +-
arch/x86/kernel/irqinit.c | 3 +
arch/x86/kernel/setup.c | 10 --
arch/x86/kernel/tsc.c | 9 +-
arch/x86/mm/fault.c | 7 +-
arch/x86/mm/mem_encrypt.c | 356 +++++++++++++++++++++++++++----------
arch/x86/mm/mem_encrypt_boot.S | 80 +++++----
include/linux/crash_core.h | 2 +
kernel/crash_core.c | 2 +-
15 files changed, 391 insertions(+), 163 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a9e57f08bfa6..98722773391d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -136,6 +136,7 @@ extern void disconnect_bsp_APIC(int virt_wire_setup);
extern void disable_local_APIC(void);
extern void lapic_shutdown(void);
extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
extern void apic_intr_mode_init(void);
extern void setup_local_APIC(void);
extern void init_apic_mappings(void);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c9459a4c3c68..22c5f3e6f820 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -39,7 +39,7 @@ void __init sme_unmap_bootdata(char *real_mode_data);

void __init sme_early_init(void);

-void __init sme_encrypt_kernel(void);
+void __init sme_encrypt_kernel(struct boot_params *bp);
void __init sme_enable(struct boot_params *bp);

int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
@@ -67,7 +67,7 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }

static inline void __init sme_early_init(void) { }

-static inline void __init sme_encrypt_kernel(void) { }
+static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
static inline void __init sme_enable(struct boot_params *bp) { }

static inline bool sme_active(void) { return false; }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 880441f24146..25ddf02598d2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1286,6 +1286,55 @@ static int __init apic_intr_mode_select(void)
return APIC_SYMMETRIC_IO;
}

+/*
+ * An initial setup of the virtual wire mode.
+ */
+void __init init_bsp_APIC(void)
+{
+ unsigned int value;
+
+ /*
+ * Don't do the setup now if we have a SMP BIOS as the
+ * through-I/O-APIC virtual wire mode might be active.
+ */
+ if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC))
+ return;
+
+ /*
+ * Do not trust the local APIC being empty at bootup.
+ */
+ clear_local_APIC();
+
+ /*
+ * Enable APIC.
+ */
+ value = apic_read(APIC_SPIV);
+ value &= ~APIC_VECTOR_MASK;
+ value |= APIC_SPIV_APIC_ENABLED;
+
+#ifdef CONFIG_X86_32
+ /* This bit is reserved on P4/Xeon and should be cleared */
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
+ (boot_cpu_data.x86 == 15))
+ value &= ~APIC_SPIV_FOCUS_DISABLED;
+ else
+#endif
+ value |= APIC_SPIV_FOCUS_DISABLED;
+ value |= SPURIOUS_APIC_VECTOR;
+ apic_write(APIC_SPIV, value);
+
+ /*
+ * Set up the virtual wire mode.
+ */
+ apic_write(APIC_LVT0, APIC_DM_EXTINT);
+ value = APIC_DM_NMI;
+ if (!lapic_is_integrated()) /* 82489DX */
+ value |= APIC_LVT_LEVEL_TRIGGER;
+ if (apic_extnmi == APIC_EXTNMI_NONE)
+ value |= APIC_LVT_MASKED;
+ apic_write(APIC_LVT1, value);
+}
+
/* Init the interrupt delivery mode for the BSP */
void __init apic_intr_mode_init(void)
{
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index f8b03bb8e725..3cc471beb50b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -542,14 +542,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,

err = assign_irq_vector_policy(irqd, info);
trace_vector_setup(virq + i, false, err);
- if (err)
+ if (err) {
+ irqd->chip_data = NULL;
+ free_apic_chip_data(apicd);
goto error;
+ }
}

return 0;

error:
- x86_vector_free_irqs(domain, virq, i + 1);
+ x86_vector_free_irqs(domain, virq, i);
return err;
}

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 88dcf8479013..99442370de40 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -525,10 +525,6 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
*/
if (static_branch_unlikely(&rdt_mon_enable_key))
rmdir_mondata_subdir_allrdtgrp(r, d->id);
- kfree(d->ctrl_val);
- kfree(d->rmid_busy_llc);
- kfree(d->mbm_total);
- kfree(d->mbm_local);
list_del(&d->list);
if (is_mbm_enabled())
cancel_delayed_work(&d->mbm_over);
@@ -545,6 +541,10 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
cancel_delayed_work(&d->cqm_limbo);
}

+ kfree(d->ctrl_val);
+ kfree(d->rmid_busy_llc);
+ kfree(d->mbm_total);
+ kfree(d->mbm_local);
kfree(d);
return;
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 6a5d757b9cfd..7ba5d819ebe3 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -157,8 +157,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
p = fixup_pointer(&phys_base, physaddr);
*p += load_delta - sme_get_me_mask();

- /* Encrypt the kernel (if SME is active) */
- sme_encrypt_kernel();
+ /* Encrypt the kernel and related (if SME is active) */
+ sme_encrypt_kernel(bp);

/*
* Return the SME encryption mask (if SME is active) to be used as a
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index d985cef3984f..56d99be3706a 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -56,7 +56,7 @@ struct idt_data {
* Early traps running on the DEFAULT_STACK because the other interrupt
* stacks work only after cpu_init().
*/
-static const __initdata struct idt_data early_idts[] = {
+static const __initconst struct idt_data early_idts[] = {
INTG(X86_TRAP_DB, debug),
SYSG(X86_TRAP_BP, int3),
#ifdef CONFIG_X86_32
@@ -70,7 +70,7 @@ static const __initdata struct idt_data early_idts[] = {
* the traps which use them are reinitialized with IST after cpu_init() has
* set up TSS.
*/
-static const __initdata struct idt_data def_idts[] = {
+static const __initconst struct idt_data def_idts[] = {
INTG(X86_TRAP_DE, divide_error),
INTG(X86_TRAP_NMI, nmi),
INTG(X86_TRAP_BR, bounds),
@@ -108,7 +108,7 @@ static const __initdata struct idt_data def_idts[] = {
/*
* The APIC and SMP idt entries
*/
-static const __initdata struct idt_data apic_idts[] = {
+static const __initconst struct idt_data apic_idts[] = {
#ifdef CONFIG_SMP
INTG(RESCHEDULE_VECTOR, reschedule_interrupt),
INTG(CALL_FUNCTION_VECTOR, call_function_interrupt),
@@ -150,7 +150,7 @@ static const __initdata struct idt_data apic_idts[] = {
* Early traps running on the DEFAULT_STACK because the other interrupt
* stacks work only after cpu_init().
*/
-static const __initdata struct idt_data early_pf_idts[] = {
+static const __initconst struct idt_data early_pf_idts[] = {
INTG(X86_TRAP_PF, page_fault),
};

@@ -158,7 +158,7 @@ static const __initdata struct idt_data early_pf_idts[] = {
* Override for the debug_idt. Same as the default, but with interrupt
* stack set to DEFAULT_STACK (0). Required for NMI trap handling.
*/
-static const __initdata struct idt_data dbg_idts[] = {
+static const __initconst struct idt_data dbg_idts[] = {
INTG(X86_TRAP_DB, debug),
INTG(X86_TRAP_BP, int3),
};
@@ -180,7 +180,7 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
* The exceptions which use Interrupt stacks. They are setup after
* cpu_init() when the TSS has been initialized.
*/
-static const __initdata struct idt_data ist_idts[] = {
+static const __initconst struct idt_data ist_idts[] = {
ISTG(X86_TRAP_DB, debug, DEBUG_STACK),
ISTG(X86_TRAP_NMI, nmi, NMI_STACK),
SISTG(X86_TRAP_BP, int3, DEBUG_STACK),
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 8da3e909e967..a539410c4ea9 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -61,6 +61,9 @@ void __init init_ISA_irqs(void)
struct irq_chip *chip = legacy_pic->chip;
int i;

+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+ init_bsp_APIC();
+#endif
legacy_pic->init(0);

for (i = 0; i < nr_legacy_irqs(); i++)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 145810b0edf6..68d7ab81c62f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -364,16 +364,6 @@ static void __init reserve_initrd(void)
!ramdisk_image || !ramdisk_size)
return; /* No initrd provided by bootloader */

- /*
- * If SME is active, this memory will be marked encrypted by the
- * kernel when it is accessed (including relocation). However, the
- * ramdisk image was loaded decrypted by the bootloader, so make
- * sure that it is encrypted before accessing it. For SEV the
- * ramdisk will already be encrypted, so only do this for SME.
- */
- if (sme_active())
- sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
-
initrd_start = 0;

mapped_size = memblock_mem_size(max_pfn_mapped);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8ea117f8142e..e169e85db434 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -602,7 +602,6 @@ unsigned long native_calibrate_tsc(void)
case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_ATOM_DENVERTON:
crystal_khz = 25000; /* 25.0 MHz */
break;
@@ -612,6 +611,8 @@ unsigned long native_calibrate_tsc(void)
}
}

+ if (crystal_khz == 0)
+ return 0;
/*
* TSC frequency determined by CPUID is a "hardware reported"
* frequency and is the most accurate one so far we have. This
@@ -1315,6 +1316,12 @@ void __init tsc_init(void)
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);

+ if (cpu_khz != tsc_khz) {
+ pr_info("Detected %lu.%03lu MHz TSC",
+ (unsigned long)tsc_khz / 1000,
+ (unsigned long)tsc_khz % 1000);
+ }
+
/* Sanitize TSC ADJUST before cyc2ns gets initialized */
tsc_store_and_check_tsc_adjust(true);

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 06fe3d51d385..b3e40773dce0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
* 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
* faulted on a pte with its pkey=4.
*/
-static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
+static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info,
+ u32 *pkey)
{
/* This is effectively an #ifdef */
if (!boot_cpu_has(X86_FEATURE_OSPKE))
return;

/* Fault not from Protection Keys: nothing to do */
- if (si_code != SEGV_PKUERR)
+ if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV))
return;
/*
* force_sig_info_fault() is called from a number of
@@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
lsb = PAGE_SHIFT;
info.si_addr_lsb = lsb;

- fill_sig_info_pkey(si_code, &info, pkey);
+ fill_sig_info_pkey(si_signo, si_code, &info, pkey);

force_sig_info(si_signo, &info, tsk);
}
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 391b13402e40..3ef362f598e3 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
}

-static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start,
- unsigned long end)
+struct sme_populate_pgd_data {
+ void *pgtable_area;
+ pgd_t *pgd;
+
+ pmdval_t pmd_flags;
+ pteval_t pte_flags;
+ unsigned long paddr;
+
+ unsigned long vaddr;
+ unsigned long vaddr_end;
+};
+
+static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
{
unsigned long pgd_start, pgd_end, pgd_size;
pgd_t *pgd_p;

- pgd_start = start & PGDIR_MASK;
- pgd_end = end & PGDIR_MASK;
+ pgd_start = ppd->vaddr & PGDIR_MASK;
+ pgd_end = ppd->vaddr_end & PGDIR_MASK;

- pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1);
- pgd_size *= sizeof(pgd_t);
+ pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);

- pgd_p = pgd_base + pgd_index(start);
+ pgd_p = ppd->pgd + pgd_index(ppd->vaddr);

memset(pgd_p, 0, pgd_size);
}

-#define PGD_FLAGS _KERNPG_TABLE_NOENC
-#define P4D_FLAGS _KERNPG_TABLE_NOENC
-#define PUD_FLAGS _KERNPG_TABLE_NOENC
-#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+#define PGD_FLAGS _KERNPG_TABLE_NOENC
+#define P4D_FLAGS _KERNPG_TABLE_NOENC
+#define PUD_FLAGS _KERNPG_TABLE_NOENC
+#define PMD_FLAGS _KERNPG_TABLE_NOENC
+
+#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
+
+#define PMD_FLAGS_DEC PMD_FLAGS_LARGE
+#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+ (_PAGE_PAT | _PAGE_PWT))
+
+#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC)
+
+#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)
+
+#define PTE_FLAGS_DEC PTE_FLAGS
+#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
+ (_PAGE_PAT | _PAGE_PWT))
+
+#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC)

-static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
- unsigned long vaddr, pmdval_t pmd_val)
+static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
{
pgd_t *pgd_p;
p4d_t *p4d_p;
pud_t *pud_p;
pmd_t *pmd_p;

- pgd_p = pgd_base + pgd_index(vaddr);
+ pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
if (native_pgd_val(*pgd_p)) {
if (IS_ENABLED(CONFIG_X86_5LEVEL))
p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
@@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
pgd_t pgd;

if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_p = pgtable_area;
+ p4d_p = ppd->pgtable_area;
memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
- pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;
+ ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;

pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
} else {
- pud_p = pgtable_area;
+ pud_p = ppd->pgtable_area;
memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
- pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+ ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;

pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
}
@@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area,
}

if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- p4d_p += p4d_index(vaddr);
+ p4d_p += p4d_index(ppd->vaddr);
if (native_p4d_val(*p4d_p)) {
pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
} else {
p4d_t p4d;

- pud_p = pgtable_area;
+ pud_p = ppd->pgtable_area;
memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
- pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;
+ ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;

p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
native_set_p4d(p4d_p, p4d);
}
}

- pud_p += pud_index(vaddr);
+ pud_p += pud_index(ppd->vaddr);
if (native_pud_val(*pud_p)) {
if (native_pud_val(*pud_p) & _PAGE_PSE)
- goto out;
+ return NULL;

pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
} else {
pud_t pud;

- pmd_p = pgtable_area;
+ pmd_p = ppd->pgtable_area;
memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
- pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;
+ ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;

pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
native_set_pud(pud_p, pud);
}

- pmd_p += pmd_index(vaddr);
+ return pmd_p;
+}
+
+static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+{
+ pmd_t *pmd_p;
+
+ pmd_p = sme_prepare_pgd(ppd);
+ if (!pmd_p)
+ return;
+
+ pmd_p += pmd_index(ppd->vaddr);
if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
- native_set_pmd(pmd_p, native_make_pmd(pmd_val));
+ native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
+}

-out:
- return pgtable_area;
+static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+{
+ pmd_t *pmd_p;
+ pte_t *pte_p;
+
+ pmd_p = sme_prepare_pgd(ppd);
+ if (!pmd_p)
+ return;
+
+ pmd_p += pmd_index(ppd->vaddr);
+ if (native_pmd_val(*pmd_p)) {
+ if (native_pmd_val(*pmd_p) & _PAGE_PSE)
+ return;
+
+ pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
+ } else {
+ pmd_t pmd;
+
+ pte_p = ppd->pgtable_area;
+ memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
+ ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;
+
+ pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
+ native_set_pmd(pmd_p, pmd);
+ }
+
+ pte_p += pte_index(ppd->vaddr);
+ if (!native_pte_val(*pte_p))
+ native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
+}
+
+static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+{
+ while (ppd->vaddr < ppd->vaddr_end) {
+ sme_populate_pgd_large(ppd);
+
+ ppd->vaddr += PMD_PAGE_SIZE;
+ ppd->paddr += PMD_PAGE_SIZE;
+ }
+}
+
+static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+{
+ while (ppd->vaddr < ppd->vaddr_end) {
+ sme_populate_pgd(ppd);
+
+ ppd->vaddr += PAGE_SIZE;
+ ppd->paddr += PAGE_SIZE;
+ }
+}
+
+static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+ pmdval_t pmd_flags, pteval_t pte_flags)
+{
+ unsigned long vaddr_end;
+
+ ppd->pmd_flags = pmd_flags;
+ ppd->pte_flags = pte_flags;
+
+ /* Save original end value since we modify the struct value */
+ vaddr_end = ppd->vaddr_end;
+
+ /* If start is not 2MB aligned, create PTE entries */
+ ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
+ __sme_map_range_pte(ppd);
+
+ /* Create PMD entries */
+ ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
+ __sme_map_range_pmd(ppd);
+
+ /* If end is not 2MB aligned, create PTE entries */
+ ppd->vaddr_end = vaddr_end;
+ __sme_map_range_pte(ppd);
+}
+
+static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
+}
+
+static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
+}
+
+static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+{
+ __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
}

static unsigned long __init sme_pgtable_calc(unsigned long len)
{
- unsigned long p4d_size, pud_size, pmd_size;
+ unsigned long p4d_size, pud_size, pmd_size, pte_size;
unsigned long total;

/*
* Perform a relatively simplistic calculation of the pagetable
- * entries that are needed. That mappings will be covered by 2MB
- * PMD entries so we can conservatively calculate the required
+ * entries that are needed. Those mappings will be covered mostly
+ * by 2MB PMD entries so we can conservatively calculate the required
* number of P4D, PUD and PMD structures needed to perform the
- * mappings. Incrementing the count for each covers the case where
- * the addresses cross entries.
+ * mappings. For mappings that are not 2MB aligned, PTE mappings
+ * would be needed for the start and end portion of the address range
+ * that fall outside of the 2MB alignment. This results in, at most,
+ * two extra pages to hold PTE entries for each range that is mapped.
+ * Incrementing the count for each covers the case where the addresses
+ * cross entries.
*/
if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
@@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
}
pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1;
pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
+ pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE;

- total = p4d_size + pud_size + pmd_size;
+ total = p4d_size + pud_size + pmd_size + pte_size;

/*
* Now calculate the added pagetable structures needed to populate
@@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
return total;
}

-void __init sme_encrypt_kernel(void)
+void __init sme_encrypt_kernel(struct boot_params *bp)
{
unsigned long workarea_start, workarea_end, workarea_len;
unsigned long execute_start, execute_end, execute_len;
unsigned long kernel_start, kernel_end, kernel_len;
+ unsigned long initrd_start, initrd_end, initrd_len;
+ struct sme_populate_pgd_data ppd;
unsigned long pgtable_area_len;
- unsigned long paddr, pmd_flags;
unsigned long decrypted_base;
- void *pgtable_area;
- pgd_t *pgd;

if (!sme_active())
return;

/*
- * Prepare for encrypting the kernel by building new pagetables with
- * the necessary attributes needed to encrypt the kernel in place.
+ * Prepare for encrypting the kernel and initrd by building new
+ * pagetables with the necessary attributes needed to encrypt the
+ * kernel in place.
*
* One range of virtual addresses will map the memory occupied
- * by the kernel as encrypted.
+ * by the kernel and initrd as encrypted.
*
* Another range of virtual addresses will map the memory occupied
- * by the kernel as decrypted and write-protected.
+ * by the kernel and initrd as decrypted and write-protected.
*
* The use of write-protect attribute will prevent any of the
* memory from being cached.
@@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void)
kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
kernel_len = kernel_end - kernel_start;

+ initrd_start = 0;
+ initrd_end = 0;
+ initrd_len = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+ initrd_len = (unsigned long)bp->hdr.ramdisk_size |
+ ((unsigned long)bp->ext_ramdisk_size << 32);
+ if (initrd_len) {
+ initrd_start = (unsigned long)bp->hdr.ramdisk_image |
+ ((unsigned long)bp->ext_ramdisk_image << 32);
+ initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
+ initrd_len = initrd_end - initrd_start;
+ }
+#endif
+
/* Set the encryption workarea to be immediately after the kernel */
workarea_start = kernel_end;

@@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void)
*/
pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
+ if (initrd_len)
+ pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;

/* PUDs and PMDs needed in the current pagetables for the workarea */
pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);

/*
* The total workarea includes the executable encryption area and
- * the pagetable area.
+ * the pagetable area. The start of the workarea is already 2MB
+ * aligned, align the end of the workarea on a 2MB boundary so that
+ * we don't try to create/allocate PTE entries from the workarea
+ * before it is mapped.
*/
workarea_len = execute_len + pgtable_area_len;
- workarea_end = workarea_start + workarea_len;
+ workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);

/*
* Set the address to the start of where newly created pagetable
@@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void)
* pagetables and when the new encrypted and decrypted kernel
* mappings are populated.
*/
- pgtable_area = (void *)execute_end;
+ ppd.pgtable_area = (void *)execute_end;

/*
* Make sure the current pagetable structure has entries for
* addressing the workarea.
*/
- pgd = (pgd_t *)native_read_cr3_pa();
- paddr = workarea_start;
- while (paddr < workarea_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr,
- paddr + PMD_FLAGS);
-
- paddr += PMD_PAGE_SIZE;
- }
+ ppd.pgd = (pgd_t *)native_read_cr3_pa();
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start;
+ ppd.vaddr_end = workarea_end;
+ sme_map_range_decrypted(&ppd);

/* Flush the TLB - no globals so cr3 is enough */
native_write_cr3(__native_read_cr3());

/*
* A new pagetable structure is being built to allow for the kernel
- * to be encrypted. It starts with an empty PGD that will then be
- * populated with new PUDs and PMDs as the encrypted and decrypted
- * kernel mappings are created.
+ * and initrd to be encrypted. It starts with an empty PGD that will
+ * then be populated with new PUDs and PMDs as the encrypted and
+ * decrypted kernel mappings are created.
*/
- pgd = pgtable_area;
- memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD);
- pgtable_area += sizeof(*pgd) * PTRS_PER_PGD;
-
- /* Add encrypted kernel (identity) mappings */
- pmd_flags = PMD_FLAGS | _PAGE_ENC;
- paddr = kernel_start;
- while (paddr < kernel_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr,
- paddr + pmd_flags);
-
- paddr += PMD_PAGE_SIZE;
- }
+ ppd.pgd = ppd.pgtable_area;
+ memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
+ ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;

/*
* A different PGD index/entry must be used to get different
@@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void)
* the base of the mapping.
*/
decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
+ if (initrd_len) {
+ unsigned long check_base;
+
+ check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
+ decrypted_base = max(decrypted_base, check_base);
+ }
decrypted_base <<= PGDIR_SHIFT;

+ /* Add encrypted kernel (identity) mappings */
+ ppd.paddr = kernel_start;
+ ppd.vaddr = kernel_start;
+ ppd.vaddr_end = kernel_end;
+ sme_map_range_encrypted(&ppd);
+
/* Add decrypted, write-protected kernel (non-identity) mappings */
- pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT);
- paddr = kernel_start;
- while (paddr < kernel_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr + decrypted_base,
- paddr + pmd_flags);
-
- paddr += PMD_PAGE_SIZE;
+ ppd.paddr = kernel_start;
+ ppd.vaddr = kernel_start + decrypted_base;
+ ppd.vaddr_end = kernel_end + decrypted_base;
+ sme_map_range_decrypted_wp(&ppd);
+
+ if (initrd_len) {
+ /* Add encrypted initrd (identity) mappings */
+ ppd.paddr = initrd_start;
+ ppd.vaddr = initrd_start;
+ ppd.vaddr_end = initrd_end;
+ sme_map_range_encrypted(&ppd);
+ /*
+ * Add decrypted, write-protected initrd (non-identity) mappings
+ */
+ ppd.paddr = initrd_start;
+ ppd.vaddr = initrd_start + decrypted_base;
+ ppd.vaddr_end = initrd_end + decrypted_base;
+ sme_map_range_decrypted_wp(&ppd);
}

/* Add decrypted workarea mappings to both kernel mappings */
- paddr = workarea_start;
- while (paddr < workarea_end) {
- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr,
- paddr + PMD_FLAGS);
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start;
+ ppd.vaddr_end = workarea_end;
+ sme_map_range_decrypted(&ppd);

- pgtable_area = sme_populate_pgd(pgd, pgtable_area,
- paddr + decrypted_base,
- paddr + PMD_FLAGS);
-
- paddr += PMD_PAGE_SIZE;
- }
+ ppd.paddr = workarea_start;
+ ppd.vaddr = workarea_start + decrypted_base;
+ ppd.vaddr_end = workarea_end + decrypted_base;
+ sme_map_range_decrypted(&ppd);

/* Perform the encryption */
sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
- kernel_len, workarea_start, (unsigned long)pgd);
+ kernel_len, workarea_start, (unsigned long)ppd.pgd);
+
+ if (initrd_len)
+ sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
+ initrd_len, workarea_start,
+ (unsigned long)ppd.pgd);

/*
* At this point we are running encrypted. Remove the mappings for
* the decrypted areas - all that is needed for this is to remove
* the PGD entry/entries.
*/
- sme_clear_pgd(pgd, kernel_start + decrypted_base,
- kernel_end + decrypted_base);
+ ppd.vaddr = kernel_start + decrypted_base;
+ ppd.vaddr_end = kernel_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+
+ if (initrd_len) {
+ ppd.vaddr = initrd_start + decrypted_base;
+ ppd.vaddr_end = initrd_end + decrypted_base;
+ sme_clear_pgd(&ppd);
+ }

- sme_clear_pgd(pgd, workarea_start + decrypted_base,
- workarea_end + decrypted_base);
+ ppd.vaddr = workarea_start + decrypted_base;
+ ppd.vaddr_end = workarea_end + decrypted_base;
+ sme_clear_pgd(&ppd);

/* Flush the TLB - no globals so cr3 is enough */
native_write_cr3(__native_read_cr3());
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 730e6d541df1..01f682cf77a8 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute)

/*
* Entry parameters:
- * RDI - virtual address for the encrypted kernel mapping
- * RSI - virtual address for the decrypted kernel mapping
- * RDX - length of kernel
+ * RDI - virtual address for the encrypted mapping
+ * RSI - virtual address for the decrypted mapping
+ * RDX - length to encrypt
* RCX - virtual address of the encryption workarea, including:
* - stack page (PAGE_SIZE)
* - encryption routine page (PAGE_SIZE)
@@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute)
addq $PAGE_SIZE, %rax /* Workarea encryption routine */

push %r12
- movq %rdi, %r10 /* Encrypted kernel */
- movq %rsi, %r11 /* Decrypted kernel */
- movq %rdx, %r12 /* Kernel length */
+ movq %rdi, %r10 /* Encrypted area */
+ movq %rsi, %r11 /* Decrypted area */
+ movq %rdx, %r12 /* Area length */

/* Copy encryption routine into the workarea */
movq %rax, %rdi /* Workarea encryption routine */
@@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute)
rep movsb

/* Setup registers for call */
- movq %r10, %rdi /* Encrypted kernel */
- movq %r11, %rsi /* Decrypted kernel */
+ movq %r10, %rdi /* Encrypted area */
+ movq %r11, %rsi /* Decrypted area */
movq %r8, %rdx /* Pagetables used for encryption */
- movq %r12, %rcx /* Kernel length */
+ movq %r12, %rcx /* Area length */
movq %rax, %r8 /* Workarea encryption routine */
addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */

@@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute)

ENTRY(__enc_copy)
/*
- * Routine used to encrypt kernel.
+ * Routine used to encrypt memory in place.
* This routine must be run outside of the kernel proper since
* the kernel will be encrypted during the process. So this
* routine is defined here and then copied to an area outside
@@ -79,19 +79,19 @@ ENTRY(__enc_copy)
* during execution.
*
* On entry the registers must be:
- * RDI - virtual address for the encrypted kernel mapping
- * RSI - virtual address for the decrypted kernel mapping
+ * RDI - virtual address for the encrypted mapping
+ * RSI - virtual address for the decrypted mapping
* RDX - address of the pagetables to use for encryption
- * RCX - length of kernel
+ * RCX - length of area
* R8 - intermediate copy buffer
*
* RAX - points to this routine
*
- * The kernel will be encrypted by copying from the non-encrypted
- * kernel space to an intermediate buffer and then copying from the
- * intermediate buffer back to the encrypted kernel space. The physical
- * addresses of the two kernel space mappings are the same which
- * results in the kernel being encrypted "in place".
+ * The area will be encrypted by copying from the non-encrypted
+ * memory space to an intermediate buffer and then copying from the
+ * intermediate buffer back to the encrypted memory space. The physical
+ * addresses of the two mappings are the same which results in the area
+ * being encrypted "in place".
*/
/* Enable the new page tables */
mov %rdx, %cr3
@@ -103,47 +103,55 @@ ENTRY(__enc_copy)
orq $X86_CR4_PGE, %rdx
mov %rdx, %cr4

+ push %r15
+ push %r12
+
+ movq %rcx, %r9 /* Save area length */
+ movq %rdi, %r10 /* Save encrypted area address */
+ movq %rsi, %r11 /* Save decrypted area address */
+
/* Set the PAT register PA5 entry to write-protect */
- push %rcx
movl $MSR_IA32_CR_PAT, %ecx
rdmsr
- push %rdx /* Save original PAT value */
+ mov %rdx, %r15 /* Save original PAT value */
andl $0xffff00ff, %edx /* Clear PA5 */
orl $0x00000500, %edx /* Set PA5 to WP */
wrmsr
- pop %rdx /* RDX contains original PAT value */
- pop %rcx
-
- movq %rcx, %r9 /* Save kernel length */
- movq %rdi, %r10 /* Save encrypted kernel address */
- movq %rsi, %r11 /* Save decrypted kernel address */

wbinvd /* Invalidate any cache entries */

- /* Copy/encrypt 2MB at a time */
+ /* Copy/encrypt up to 2MB at a time */
+ movq $PMD_PAGE_SIZE, %r12
1:
- movq %r11, %rsi /* Source - decrypted kernel */
+ cmpq %r12, %r9
+ jnb 2f
+ movq %r9, %r12
+
+2:
+ movq %r11, %rsi /* Source - decrypted area */
movq %r8, %rdi /* Dest - intermediate copy buffer */
- movq $PMD_PAGE_SIZE, %rcx /* 2MB length */
+ movq %r12, %rcx
rep movsb

movq %r8, %rsi /* Source - intermediate copy buffer */
- movq %r10, %rdi /* Dest - encrypted kernel */
- movq $PMD_PAGE_SIZE, %rcx /* 2MB length */
+ movq %r10, %rdi /* Dest - encrypted area */
+ movq %r12, %rcx
rep movsb

- addq $PMD_PAGE_SIZE, %r11
- addq $PMD_PAGE_SIZE, %r10
- subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */
+ addq %r12, %r11
+ addq %r12, %r10
+ subq %r12, %r9 /* Kernel length decrement */
jnz 1b /* Kernel length not zero? */

/* Restore PAT register */
- push %rdx /* Save original PAT value */
movl $MSR_IA32_CR_PAT, %ecx
rdmsr
- pop %rdx /* Restore original PAT value */
+ mov %r15, %rdx /* Restore original PAT value */
wrmsr

+ pop %r12
+ pop %r15
+
ret
.L__enc_copy_end:
ENDPROC(__enc_copy)
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 06097ef30449..b511f6d24b42 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -42,6 +42,8 @@ phys_addr_t paddr_vmcoreinfo_note(void);
vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
#define VMCOREINFO_SYMBOL(name) \
vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name)
+#define VMCOREINFO_SYMBOL_ARRAY(name) \
+ vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name)
#define VMCOREINFO_SIZE(name) \
vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
(unsigned long)sizeof(name))
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index b3663896278e..4f63597c824d 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -410,7 +410,7 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_SYMBOL(contig_page_data);
#endif
#ifdef CONFIG_SPARSEMEM
- VMCOREINFO_SYMBOL(mem_section);
+ VMCOREINFO_SYMBOL_ARRAY(mem_section);
VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
VMCOREINFO_STRUCT_SIZE(mem_section);
VMCOREINFO_OFFSET(mem_section, section_mem_map);