Merge tag 'x86-mm-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm handling updates from Ingo Molnar:

 - Add new NX-stack self-test

 - Improve NUMA partial-CFMWS handling

 - Fix #VC handler bugs resulting in SEV-SNP boot failures

 - Drop the 4MB memory size restriction on minimal NUMA nodes

 - Reorganize headers a bit, in preparation to header dependency
   reduction efforts

 - Misc cleanups & fixes

* tag 'x86-mm-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Drop the 4 MB restriction on minimal NUMA node memory size
  selftests/x86/lam: Zero out buffer for readlink()
  x86/sev: Drop unneeded #include
  x86/sev: Move sev_setup_arch() to mem_encrypt.c
  x86/tdx: Replace deprecated strncpy() with strtomem_pad()
  selftests/x86/mm: Add new test that userspace stack is in fact NX
  x86/sev: Make boot_ghcb_page[] static
  x86/boot: Move x86_cache_alignment initialization to correct spot
  x86/sev-es: Set x86_virt_bits to the correct value straight away, instead of a two-phase approach
  x86/sev-es: Allow copy_from_kernel_nofault() in earlier boot
  x86_64: Show CR4.PSE on auxiliaries like on BSP
  x86/iommu/docs: Update AMD IOMMU specification document URL
  x86/sev/docs: Update document URL in amd-memory-encryption.rst
  x86/mm: Move arch_memory_failure() and arch_is_platform_page() definitions from <asm/processor.h> to <asm/pgtable.h>
  ACPI/NUMA: Apply SRAT proximity domain to entire CFMWS window
  x86/numa: Introduce numa_fill_memblks()

14 files changed, 168 insertions, 87 deletions

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 7816ff55025d..454acd7a2daf 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -25,7 +25,7 @@
 #include "error.h"
 #include "../msr.h"
 
-struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
+static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
 struct ghcb *boot_ghcb;
 
 /*
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 1d6b863c42b0..2e1be592c220 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -119,7 +119,7 @@ static void __noreturn tdx_panic(const char *msg)
 	} message;
 
 	/* VMM assumes '\0' in byte 65, if the message took all 64 bytes */
-	strncpy(message.str, msg, 64);
+	strtomem_pad(message.str, msg, '\0');
 
 	args.r8  = message.r8;
 	args.r9  = message.r9;
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 473b16d73b47..359ada486fa9 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -19,8 +19,10 @@
 
 #ifdef CONFIG_X86_MEM_ENCRYPT
 void __init mem_encrypt_init(void);
+void __init mem_encrypt_setup_arch(void);
 #else
 static inline void mem_encrypt_init(void) { }
+static inline void __init mem_encrypt_setup_arch(void) { }
 #endif
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -43,7 +45,6 @@ void __init sme_map_bootdata(char *real_mode_data);
 void __init sme_unmap_bootdata(char *real_mode_data);
 
 void __init sme_early_init(void);
-void __init sev_setup_arch(void);
 
 void __init sme_encrypt_kernel(struct boot_params *bp);
 void __init sme_enable(struct boot_params *bp);
@@ -73,7 +74,6 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { }
 static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
 
 static inline void __init sme_early_init(void) { }
-static inline void __init sev_setup_arch(void) { }
 
 static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
 static inline void __init sme_enable(struct boot_params *bp) { }
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index e3bae2b60a0d..ef2844d69173 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -12,13 +12,6 @@
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
 
-/*
- * Too small node sizes may confuse the VM badly. Usually they
- * result from BIOS bugs. So dont recognize nodes as standalone
- * NUMA entities that have less than this amount of RAM listed:
- */
-#define NODE_MIN_SIZE (4*1024*1024)
-
 extern int numa_off;
 
 /*
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index e02b179ec659..57bab91bbf50 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1716,6 +1716,14 @@ static inline bool pud_user_accessible_page(pud_t pud)
 }
 #endif
 
+#ifdef CONFIG_X86_SGX
+int arch_memory_failure(unsigned long pfn, int flags);
+#define arch_memory_failure arch_memory_failure
+
+bool arch_is_platform_page(u64 paddr);
+#define arch_is_platform_page arch_is_platform_page
+#endif
+
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6e30b27b1ebe..621ff0803b04 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -724,14 +724,6 @@ enum mds_mitigations {
 	MDS_MITIGATION_VMWERV,
 };
 
-#ifdef CONFIG_X86_SGX
-int arch_memory_failure(unsigned long pfn, int flags);
-#define arch_memory_failure arch_memory_failure
-
-bool arch_is_platform_page(u64 paddr);
-#define arch_is_platform_page arch_is_platform_page
-#endif
-
 extern bool gds_ucode_mitigated(void);
 
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 64df897c0ee3..1be13b2dfe8b 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -37,6 +37,8 @@ extern int phys_to_target_node(phys_addr_t start);
 #define phys_to_target_node phys_to_target_node
 extern int memory_add_physaddr_to_nid(u64 start);
 #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+extern int numa_fill_memblks(u64 start, u64 end);
+#define numa_fill_memblks numa_fill_memblks
 #endif
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0a3ea787ac51..3f8de9bce61a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1115,18 +1115,34 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
+	bool vp_bits_from_cpuid = true;
 
-	if (c->extended_cpuid_level >= 0x80000008) {
+	if (!cpu_has(c, X86_FEATURE_CPUID) ||
+	    (c->extended_cpuid_level < 0x80000008))
+		vp_bits_from_cpuid = false;
+
+	if (vp_bits_from_cpuid) {
 		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
 
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
+	} else {
+		if (IS_ENABLED(CONFIG_X86_64)) {
+			c->x86_clflush_size = 64;
+			c->x86_phys_bits = 36;
+			c->x86_virt_bits = 48;
+		} else {
+			c->x86_clflush_size = 32;
+			c->x86_virt_bits = 32;
+			c->x86_phys_bits = 32;
+
+			if (cpu_has(c, X86_FEATURE_PAE) ||
+			    cpu_has(c, X86_FEATURE_PSE36))
+				c->x86_phys_bits = 36;
+		}
 	}
-#ifdef CONFIG_X86_32
-	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
-		c->x86_phys_bits = 36;
-#endif
 	c->x86_cache_bits = c->x86_phys_bits;
+	c->x86_cache_alignment = c->x86_clflush_size;
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -1580,17 +1596,6 @@ static void __init cpu_parse_early_param(void)
  */
 static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_64
-	c->x86_clflush_size = 64;
-	c->x86_phys_bits = 36;
-	c->x86_virt_bits = 48;
-#else
-	c->x86_clflush_size = 32;
-	c->x86_phys_bits = 32;
-	c->x86_virt_bits = 32;
-#endif
-	c->x86_cache_alignment = c->x86_clflush_size;
-
 	memset(&c->x86_capability, 0, sizeof(c->x86_capability));
 	c->extended_cpuid_level = 0;
 
@@ -1602,7 +1607,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		cpu_detect(c);
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
-		get_cpu_address_sizes(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
 		cpu_parse_early_param();
 
@@ -1618,6 +1622,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
 	}
 
+	get_cpu_address_sizes(c);
+
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
 	cpu_set_bug_bits(c);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 6bbbef6586d1..086a2c3aaaa0 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -179,8 +179,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	movl	$0, %ecx
 #endif
 
-	/* Enable PAE mode, PGE and LA57 */
-	orl	$(X86_CR4_PAE | X86_CR4_PGE), %ecx
+	/* Enable PAE mode, PSE, PGE and LA57 */
+	orl	$(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
 #ifdef CONFIG_X86_5LEVEL
 	testl	$1, __pgtable_l5_enabled(%rip)
 	jz	1f
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3e05ecf8cf8d..ccd3ad29a1dc 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1120,7 +1120,7 @@ void __init setup_arch(char **cmdline_p)
 	 * Needs to run after memblock setup because it needs the physical
 	 * memory size.
 	 */
-	sev_setup_arch();
+	mem_encrypt_setup_arch();
 
 	efi_fake_memmap();
 	efi_find_mirror();
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 5a53c2cc169c..6993f026adec 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -9,12 +9,21 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 	unsigned long vaddr = (unsigned long)unsafe_src;
 
 	/*
-	 * Range covering the highest possible canonical userspace address
-	 * as well as non-canonical address range. For the canonical range
-	 * we also need to include the userspace guard page.
+	 * Do not allow userspace addresses.  This disallows
+	 * normal userspace and the userspace guard page:
 	 */
-	return vaddr >= TASK_SIZE_MAX + PAGE_SIZE &&
-	       __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
+	if (vaddr < TASK_SIZE_MAX + PAGE_SIZE)
+		return false;
+
+	/*
+	 * Allow everything during early boot before 'x86_virt_bits'
+	 * is initialized.  Needed for instruction decoding in early
+	 * exception handlers.
+	 */
+	if (!boot_cpu_data.x86_virt_bits)
+		return true;
+
+	return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
 }
 #else
 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9f27e14e185f..c290c55b632b 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 6faea41e99b6..a68f2dda0948 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>
@@ -215,40 +213,6 @@ 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 c79f12e449ea..4a17f663f949 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -12,6 +12,7 @@
 #include <linux/nodemask.h>
 #include <linux/sched.h>
 #include <linux/topology.h>
+#include <linux/sort.h>
 
 #include <asm/e820/api.h>
 #include <asm/proto.h>
@@ -602,13 +603,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 		if (start >= end)
 			continue;
 
-		/*
-		 * Don't confuse VM with a node that doesn't have the
-		 * minimum amount of memory:
-		 */
-		if (end && (end - start) < NODE_MIN_SIZE)
-			continue;
-
 		alloc_node_data(nid);
 	}
 
@@ -964,4 +958,83 @@ int memory_add_physaddr_to_nid(u64 start)
 	return nid;
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+
+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;
+}
+
+static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
+
+/**
+ * numa_fill_memblks - Fill gaps in numa_meminfo memblks
+ * @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.
+ *
+ * RETURNS:
+ * 0		  : Success
+ * NUMA_NO_MEMBLK : No memblk exists in @start-@end range
+ */
+
+int __init numa_fill_memblks(u64 start, u64 end)
+{
+	struct numa_memblk **blk = &numa_memblk_list[0];
+	struct numa_meminfo *mi = &numa_meminfo;
+	int count = 0;
+	u64 prev_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.
+	 */
+	for (int i = 0; i < mi->nr_blks; i++) {
+		struct numa_memblk *bi = &mi->blk[i];
+
+		if (start < bi->end && end >= bi->start) {
+			blk[count] = &mi->blk[i];
+			count++;
+		}
+	}
+	if (!count)
+		return NUMA_NO_MEMBLK;
+
+	/* Sort the list of pointers in memblk->start order */
+	sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL);
+
+	/* Make sure the first/last memblks include start/end */
+	blk[0]->start = min(blk[0]->start, start);
+	blk[count - 1]->end = max(blk[count - 1]->end, end);
+
+	/*
+	 * Fill any gaps by tracking the previous memblks
+	 * end address and backfilling to it if needed.
+	 */
+	prev_end = blk[0]->end;
+	for (int i = 1; i < count; i++) {
+		struct numa_memblk *curr = blk[i];
+
+		if (prev_end >= curr->start) {
+			if (prev_end < curr->end)
+				prev_end = curr->end;
+		} else {
+			curr->start = prev_end;
+			prev_end = curr->end;
+		}
+	}
+	return 0;
+}
+
 #endif