Adding upstream version 6.1.85.upstream/6.1.85

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 80 insertions, 69 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 1dbbad731..f20636510 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -818,15 +818,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 	show_opcodes(regs, loglvl);
 }
 
-/*
- * The (legacy) vsyscall page is the long page in the kernel portion
- * of the address space that has user-accessible permissions.
- */
-static bool is_vsyscall_vaddr(unsigned long vaddr)
-{
-	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
-}
-
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		       unsigned long address, u32 pkey, int si_code)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index f50cc210a..968d7005f 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
-		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		/* if this is already a gbpage, this portion is already mapped */
-		if (pud_large(*pud))
-			continue;
-
-		/* Is using a gbpage allowed? */
-		use_gbpage = info->direct_gbpages;
-
-		/* Don't use gbpage if it maps more than the requested region. */
-		/* at the begining: */
-		use_gbpage &= ((addr & ~PUD_MASK) == 0);
-		/* ... or at the end: */
-		use_gbpage &= ((next & ~PUD_MASK) == 0);
-
-		/* Never overwrite existing mappings */
-		use_gbpage &= !pud_present(*pud);
-
-		if (use_gbpage) {
+		if (info->direct_gbpages) {
 			pud_t pudval;
 
+			if (pud_present(*pud))
+				continue;
+
+			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 6993f026a..42115ac07 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -3,6 +3,8 @@
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 
+#include <asm/vsyscall.h>
+
 #ifdef CONFIG_X86_64
 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
@@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 		return false;
 
 	/*
+	 * Reading from the vsyscall page may cause an unhandled fault in
+	 * certain cases.  Though it is at an address above TASK_SIZE_MAX, it is
+	 * usually considered as a user space address.
+	 */
+	if (is_vsyscall_vaddr(vaddr))
+		return false;
+
+	/*
 	 * Allow everything during early boot before 'x86_virt_bits'
 	 * is initialized.  Needed for instruction decoding in early
 	 * exception handlers.
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 3e93af083..d4957eefe 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -513,6 +513,24 @@ void __init sme_early_init(void)
 	 */
 	if (sev_status & MSR_AMD64_SEV_ENABLED)
 		ia32_disable();
+
+	/*
+	 * Override init functions that scan the ROM region in SEV-SNP guests,
+	 * as this memory is not pre-validated and would thus cause a crash.
+	 */
+	if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+		x86_init.mpparse.find_smp_config = x86_init_noop;
+		x86_init.pci.init_irq = x86_init_noop;
+		x86_init.resources.probe_roms = x86_init_noop;
+
+		/*
+		 * DMI setup behavior for SEV-SNP guests depends on
+		 * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+		 * parsed yet. snp_dmi_setup() will run after that
+		 * parsing has happened.
+		 */
+		x86_init.resources.dmi_setup = snp_dmi_setup;
+	}
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index d94ebd8ac..06ccbd36e 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -97,7 +97,6 @@ static char sme_workarea[2 * PMD_PAGE_SIZE] __section(".init.scratch");
 
 static char sme_cmdline_arg[] __initdata = "mem_encrypt";
 static char sme_cmdline_on[]  __initdata = "on";
-static char sme_cmdline_off[] __initdata = "off";
 
 static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
 {
@@ -305,7 +304,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
 	 * function.
 	 */
-	if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED)
+	if (!sme_get_me_mask() ||
+	    RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED)
 		return;
 
 	/*
@@ -504,10 +504,9 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 
 void __init sme_enable(struct boot_params *bp)
 {
-	const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off;
+	const char *cmdline_ptr, *cmdline_arg, *cmdline_on;
 	unsigned int eax, ebx, ecx, edx;
 	unsigned long feature_mask;
-	bool active_by_default;
 	unsigned long me_mask;
 	char buffer[16];
 	bool snp;
@@ -543,11 +542,11 @@ void __init sme_enable(struct boot_params *bp)
 	me_mask = 1UL << (ebx & 0x3f);
 
 	/* Check the SEV MSR whether SEV or SME is enabled */
-	sev_status   = __rdmsr(MSR_AMD64_SEV);
-	feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
+	RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV);
+	feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
 
 	/* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */
-	if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+	if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED))
 		snp_abort();
 
 	/* Check if memory encryption is enabled */
@@ -573,7 +572,6 @@ void __init sme_enable(struct boot_params *bp)
 			return;
 	} else {
 		/* SEV state cannot be controlled by a command line option */
-		sme_me_mask = me_mask;
 		goto out;
 	}
 
@@ -588,31 +586,17 @@ void __init sme_enable(struct boot_params *bp)
 	asm ("lea sme_cmdline_on(%%rip), %0"
 	     : "=r" (cmdline_on)
 	     : "p" (sme_cmdline_on));
-	asm ("lea sme_cmdline_off(%%rip), %0"
-	     : "=r" (cmdline_off)
-	     : "p" (sme_cmdline_off));
-
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT))
-		active_by_default = true;
-	else
-		active_by_default = false;
 
 	cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
 				     ((u64)bp->ext_cmd_line_ptr << 32));
 
-	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0)
+	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 ||
+	    strncmp(buffer, cmdline_on, sizeof(buffer)))
 		return;
 
-	if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
-		sme_me_mask = me_mask;
-	else if (!strncmp(buffer, cmdline_off, sizeof(buffer)))
-		sme_me_mask = 0;
-	else
-		sme_me_mask = active_by_default ? me_mask : 0;
 out:
-	if (sme_me_mask) {
-		physical_mask &= ~sme_me_mask;
-		cc_set_vendor(CC_VENDOR_AMD);
-		cc_set_mask(sme_me_mask);
-	}
+	RIP_REL_REF(sme_me_mask) = me_mask;
+	physical_mask &= ~me_mask;
+	cc_vendor = CC_VENDOR_AMD;
+	cc_set_mask(me_mask);
 }
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 66a209f7e..d6fe9093e 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -997,6 +997,38 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 		memtype_free(paddr, paddr + size);
 }
 
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+		pgprot_t *pgprot)
+{
+	unsigned long prot;
+
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+	/*
+	 * We need the starting PFN and cachemode used for track_pfn_remap()
+	 * that covered the whole VMA. For most mappings, we can obtain that
+	 * information from the page tables. For COW mappings, we might now
+	 * suddenly have anon folios mapped and follow_phys() will fail.
+	 *
+	 * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+	 * detect the PFN. If we need the cachemode as well, we're out of luck
+	 * for now and have to fail fork().
+	 */
+	if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+		if (pgprot)
+			*pgprot = __pgprot(prot);
+		return 0;
+	}
+	if (is_cow_mapping(vma->vm_flags)) {
+		if (pgprot)
+			return -EINVAL;
+		*paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
 /*
  * track_pfn_copy is called when vma that is covering the pfnmap gets
  * copied through copy_page_range().
@@ -1007,20 +1039,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 int track_pfn_copy(struct vm_area_struct *vma)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (vma->vm_flags & VM_PAT) {
-		/*
-		 * reserve the whole chunk covered by vma. We need the
-		 * starting address and protection from pte.
-		 */
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, &pgprot))
 			return -EINVAL;
-		}
-		pgprot = __pgprot(prot);
+		/* reserve the whole chunk covered by vma. */
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
@@ -1095,7 +1120,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 		 unsigned long size)
 {
 	resource_size_t paddr;
-	unsigned long prot;
 
 	if (vma && !(vma->vm_flags & VM_PAT))
 		return;
@@ -1103,11 +1127,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	/* free the chunk starting from pfn or the whole chunk */
 	paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	if (!paddr && !size) {
-		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
-			WARN_ON_ONCE(1);
+		if (get_pat_info(vma, &paddr, NULL))
 			return;
-		}
-
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);