Merging upstream version 6.7.7.

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

7 files changed, 99 insertions, 85 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index ab778eac1..679b09cfe 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f..f50cc210a 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ 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 (info->direct_gbpages) {
-			pud_t pudval;
+		/* 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;
 
-			if (pud_present(*pud))
-				continue;
+		/* 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) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9f27e14e1..c290c55b6 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -12,6 +12,7 @@
 #include <linux/swiotlb.h>
 #include <linux/cc_platform.h>
 #include <linux/mem_encrypt.h>
+#include <linux/virtio_anchor.h>
 
 /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 bool force_dma_unencrypted(struct device *dev)
@@ -86,3 +87,36 @@ void __init mem_encrypt_init(void)
 
 	print_mem_encrypt_feature_info();
 }
+
+void __init mem_encrypt_setup_arch(void)
+{
+	phys_addr_t total_mem = memblock_phys_mem_size();
+	unsigned long size;
+
+	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return;
+
+	/*
+	 * For SEV and TDX, all DMA has to occur via shared/unencrypted pages.
+	 * Kernel uses SWIOTLB to make this happen without changing device
+	 * drivers. However, depending on the workload being run, the
+	 * default 64MB of SWIOTLB may not be enough and SWIOTLB may
+	 * run out of buffers for DMA, resulting in I/O errors and/or
+	 * performance degradation especially with high I/O workloads.
+	 *
+	 * Adjust the default size of SWIOTLB using a percentage of guest
+	 * memory for SWIOTLB buffers. Also, as the SWIOTLB bounce buffer
+	 * memory is allocated from low memory, ensure that the adjusted size
+	 * is within the limits of low available memory.
+	 *
+	 * The percentage of guest memory used here for SWIOTLB buffers
+	 * is more of an approximation of the static adjustment which
+	 * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
+	 */
+	size = total_mem * 6 / 100;
+	size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
+	swiotlb_adjust_size(size);
+
+	/* Set restricted memory access for virtio. */
+	virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
+}
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 45ff95264..70b91de2e 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -19,8 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/dma-mapping.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_anchor.h>
 #include <linux/cc_platform.h>
 
 #include <asm/tlbflush.h>
@@ -216,40 +214,6 @@ void __init sme_map_bootdata(char *real_mode_data)
 	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true);
 }
 
-void __init sev_setup_arch(void)
-{
-	phys_addr_t total_mem = memblock_phys_mem_size();
-	unsigned long size;
-
-	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		return;
-
-	/*
-	 * For SEV, all DMA has to occur via shared/unencrypted pages.
-	 * SEV uses SWIOTLB to make this happen without changing device
-	 * drivers. However, depending on the workload being run, the
-	 * default 64MB of SWIOTLB may not be enough and SWIOTLB may
-	 * run out of buffers for DMA, resulting in I/O errors and/or
-	 * performance degradation especially with high I/O workloads.
-	 *
-	 * Adjust the default size of SWIOTLB for SEV guests using
-	 * a percentage of guest memory for SWIOTLB buffers.
-	 * Also, as the SWIOTLB bounce buffer memory is allocated
-	 * from low memory, ensure that the adjusted size is within
-	 * the limits of low available memory.
-	 *
-	 * The percentage of guest memory used here for SWIOTLB buffers
-	 * is more of an approximation of the static adjustment which
-	 * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
-	 */
-	size = total_mem * 6 / 100;
-	size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
-	swiotlb_adjust_size(size);
-
-	/* Set restricted memory access for virtio. */
-	virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
-}
-
 static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
 {
 	unsigned long pfn = 0;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index aa39d678f..9d63cfff1 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -3,6 +3,7 @@
 #include <linux/acpi.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/of.h>
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
@@ -57,7 +58,7 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = {
 
 int numa_cpu_node(int cpu)
 {
-	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+	u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
 
 	if (apicid != BAD_APICID)
 		return __apicid_to_node[apicid];
@@ -727,6 +728,8 @@ void __init x86_numa_init(void)
 		if (!numa_init(amd_numa_init))
 			return;
 #endif
+		if (acpi_disabled && !numa_init(of_numa_init))
+			return;
 	}
 
 	numa_init(dummy_numa_init);
@@ -780,7 +783,7 @@ void __init init_gi_nodes(void)
 void __init init_cpu_to_node(void)
 {
 	int cpu;
-	u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+	u32 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
 
 	BUG_ON(cpu_to_apicid == NULL);
 
@@ -961,7 +964,7 @@ static int __init cmp_memblk(const void *a, const void *b)
 	const struct numa_memblk *ma = *(const struct numa_memblk **)a;
 	const struct numa_memblk *mb = *(const struct numa_memblk **)b;
 
-	return ma->start - mb->start;
+	return (ma->start > mb->start) - (ma->start < mb->start);
 }
 
 static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
@@ -971,14 +974,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
  * @start: address to begin fill
  * @end: address to end fill
  *
- * Find and extend numa_meminfo memblks to cover the @start-@end
- * physical address range, such that the first memblk includes
- * @start, the last memblk includes @end, and any gaps in between
- * are filled.
+ * Find and extend numa_meminfo memblks to cover the physical
+ * address range @start-@end
  *
  * RETURNS:
  * 0		  : Success
- * NUMA_NO_MEMBLK : No memblk exists in @start-@end range
+ * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end
  */
 
 int __init numa_fill_memblks(u64 start, u64 end)
@@ -990,17 +991,14 @@ int __init numa_fill_memblks(u64 start, u64 end)
 
 	/*
 	 * Create a list of pointers to numa_meminfo memblks that
-	 * overlap start, end. Exclude (start == bi->end) since
-	 * end addresses in both a CFMWS range and a memblk range
-	 * are exclusive.
-	 *
-	 * This list of pointers is used to make in-place changes
-	 * that fill out the numa_meminfo memblks.
+	 * overlap start, end. The list is used to make in-place
+	 * changes that fill out the numa_meminfo memblks.
 	 */
 	for (int i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *bi = &mi->blk[i];
 
-		if (start < bi->end && end >= bi->start) {
+		if (memblock_addrs_overlap(start, end - start, bi->start,
+					   bi->end - bi->start)) {
 			blk[count] = &mi->blk[i];
 			count++;
 		}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 9deadf517..0cbc1b8e8 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -76,6 +76,9 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
+	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
+	pagetable_pud_dtor(ptdesc);
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
 	paravirt_tlb_remove_table(tlb, virt_to_page(pud));
 }
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 78414c6d1..5dd733944 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -69,6 +69,7 @@ static void __init pti_print_if_secure(const char *reason)
 		pr_info("%s\n", reason);
 }
 
+/* Assume mode is auto unless overridden via cmdline below. */
 static enum pti_mode {
 	PTI_AUTO = 0,
 	PTI_FORCE_OFF,
@@ -77,50 +78,49 @@ static enum pti_mode {
 
 void __init pti_check_boottime_disable(void)
 {
-	char arg[5];
-	int ret;
-
-	/* Assume mode is auto unless overridden. */
-	pti_mode = PTI_AUTO;
-
 	if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
 		pti_mode = PTI_FORCE_OFF;
 		pti_print_if_insecure("disabled on XEN PV.");
 		return;
 	}
 
-	ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
-	if (ret > 0)  {
-		if (ret == 3 && !strncmp(arg, "off", 3)) {
-			pti_mode = PTI_FORCE_OFF;
-			pti_print_if_insecure("disabled on command line.");
-			return;
-		}
-		if (ret == 2 && !strncmp(arg, "on", 2)) {
-			pti_mode = PTI_FORCE_ON;
-			pti_print_if_secure("force enabled on command line.");
-			goto enable;
-		}
-		if (ret == 4 && !strncmp(arg, "auto", 4)) {
-			pti_mode = PTI_AUTO;
-			goto autosel;
-		}
-	}
-
-	if (cmdline_find_option_bool(boot_command_line, "nopti") ||
-	    cpu_mitigations_off()) {
+	if (cpu_mitigations_off())
 		pti_mode = PTI_FORCE_OFF;
+	if (pti_mode == PTI_FORCE_OFF) {
 		pti_print_if_insecure("disabled on command line.");
 		return;
 	}
 
-autosel:
-	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+	if (pti_mode == PTI_FORCE_ON)
+		pti_print_if_secure("force enabled on command line.");
+
+	if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
 		return;
-enable:
+
 	setup_force_cpu_cap(X86_FEATURE_PTI);
 }
 
+static int __init pti_parse_cmdline(char *arg)
+{
+	if (!strcmp(arg, "off"))
+		pti_mode = PTI_FORCE_OFF;
+	else if (!strcmp(arg, "on"))
+		pti_mode = PTI_FORCE_ON;
+	else if (!strcmp(arg, "auto"))
+		pti_mode = PTI_AUTO;
+	else
+		return -EINVAL;
+	return 0;
+}
+early_param("pti", pti_parse_cmdline);
+
+static int __init pti_parse_cmdline_nopti(char *arg)
+{
+	pti_mode = PTI_FORCE_OFF;
+	return 0;
+}
+early_param("nopti", pti_parse_cmdline_nopti);
+
 pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	/*