Merge tag 'v6.4.11' into 6.4

This is the 6.4.11 stable release

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 4
-SUBLEVEL = 10
+SUBLEVEL = 11
 EXTRAVERSION =
 NAME = Hurr durr I'ma ninja sloth
 

arch/alpha/kernel/setup.c

@@ -385,8 +385,7 @@ setup_memory(void *kernel_end)
 #endif /* CONFIG_BLK_DEV_INITRD */
 }
 
-int __init
-page_is_ram(unsigned long pfn)
+int page_is_ram(unsigned long pfn)
 {
 	struct memclust_struct * cluster;
 	struct memdesc_struct * memdesc;

arch/arm64/kvm/arm.c

@@ -1800,8 +1800,6 @@ static void _kvm_arch_hardware_enable(void *discard)
 
 int kvm_arch_hardware_enable(void)
 {
-	int was_enabled;
-
 	/*
 	 * Most calls to this function are made with migration
 	 * disabled, but not with preemption disabled. The former is
@@ -1810,13 +1808,10 @@ int kvm_arch_hardware_enable(void)
 	 */
 	preempt_disable();
 
-	was_enabled = __this_cpu_read(kvm_arm_hardware_enabled);
 	_kvm_arch_hardware_enable(NULL);
 
-	if (!was_enabled) {
-		kvm_vgic_cpu_up();
-		kvm_timer_cpu_up();
-	}
+	kvm_vgic_cpu_up();
+	kvm_timer_cpu_up();
 
 	preempt_enable();
 
@@ -1833,10 +1828,8 @@ static void _kvm_arch_hardware_disable(void *discard)
 
 void kvm_arch_hardware_disable(void)
 {
-	if (__this_cpu_read(kvm_arm_hardware_enabled)) {
-		kvm_timer_cpu_down();
-		kvm_vgic_cpu_down();
-	}
+	kvm_timer_cpu_down();
+	kvm_vgic_cpu_down();
 
 	if (!is_protected_kvm_enabled())
 		_kvm_arch_hardware_disable(NULL);

arch/parisc/Kconfig.debug

@@ -2,7 +2,7 @@
 #
 config LIGHTWEIGHT_SPINLOCK_CHECK
 	bool "Enable lightweight spinlock checks"
-	depends on SMP && !DEBUG_SPINLOCK
+	depends on DEBUG_KERNEL && SMP && !DEBUG_SPINLOCK
 	default y
 	help
 	  Add checks with low performance impact to the spinlock functions

arch/parisc/include/asm/spinlock.h

@@ -7,8 +7,6 @@
 #include <asm/processor.h>
 #include <asm/spinlock_types.h>
 
-#define SPINLOCK_BREAK_INSN	0x0000c006	/* break 6,6 */
-
 static inline void arch_spin_val_check(int lock_val)
 {
 	if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK))

arch/parisc/include/asm/spinlock_types.h

@@ -4,6 +4,10 @@
 
 #define __ARCH_SPIN_LOCK_UNLOCKED_VAL	0x1a46
 
+#define SPINLOCK_BREAK_INSN	0x0000c006	/* break 6,6 */
+
+#ifndef __ASSEMBLY__
+
 typedef struct {
 #ifdef CONFIG_PA20
 	volatile unsigned int slock;
@@ -27,6 +31,8 @@ typedef struct {
 	volatile unsigned int	counter;
 } arch_rwlock_t;
 
+#endif /* __ASSEMBLY__ */
+
 #define __ARCH_RW_LOCK_UNLOCKED__       0x01000000
 #define __ARCH_RW_LOCK_UNLOCKED         { .lock_mutex = __ARCH_SPIN_LOCK_UNLOCKED, \
 					.counter = __ARCH_RW_LOCK_UNLOCKED__ }

arch/parisc/kernel/sys_parisc.c

@@ -26,17 +26,12 @@
 #include <linux/compat.h>
 
 /*
- * Construct an artificial page offset for the mapping based on the virtual
+ * Construct an artificial page offset for the mapping based on the physical
  * address of the kernel file mapping variable.
- * If filp is zero the calculated pgoff value aliases the memory of the given
- * address. This is useful for io_uring where the mapping shall alias a kernel
- * address and a userspace adress where both the kernel and the userspace
- * access the same memory region.
  */
-#define GET_FILP_PGOFF(filp, addr)		\
-	((filp ? (((unsigned long) filp->f_mapping) >> 8)	\
-		 & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL)	\
-	  + (addr >> PAGE_SHIFT))
+#define GET_FILP_PGOFF(filp)		\
+	(filp ? (((unsigned long) filp->f_mapping) >> 8)	\
+		 & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL)
 
 static unsigned long shared_align_offset(unsigned long filp_pgoff,
 					 unsigned long pgoff)
@@ -116,7 +111,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	do_color_align = 0;
 	if (filp || (flags & MAP_SHARED))
 		do_color_align = 1;
-	filp_pgoff = GET_FILP_PGOFF(filp, addr);
+	filp_pgoff = GET_FILP_PGOFF(filp);
 
 	if (flags & MAP_FIXED) {
 		/* Even MAP_FIXED mappings must reside within TASK_SIZE */

arch/parisc/kernel/syscall.S

@@ -39,6 +39,7 @@ registers).
 #include <asm/assembly.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
+#include <asm/spinlock_types.h>
 
 #include <linux/linkage.h>
 
@@ -66,6 +67,16 @@ registers).
 	stw	\reg1, 0(%sr2,\reg2)
 	.endm
 
+	/* raise exception if spinlock content is not zero or
+	 * __ARCH_SPIN_LOCK_UNLOCKED_VAL */
+	.macro	spinlock_check spin_val,tmpreg
+#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK
+	ldi	__ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmpreg
+	andcm,=	\spin_val, \tmpreg, %r0
+	.word	SPINLOCK_BREAK_INSN
+#endif
+	.endm
+
 	.text
 
 	.import syscall_exit,code
@@ -508,7 +519,8 @@ lws_start:
 
 lws_exit_noerror:
 	lws_pagefault_enable	%r1,%r21
-	stw,ma	%r20, 0(%sr2,%r20)
+	ldi	__ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21
+	stw,ma	%r21, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	b	lws_exit
 	copy	%r0, %r21
@@ -521,7 +533,8 @@ lws_wouldblock:
 
 lws_pagefault:
 	lws_pagefault_enable	%r1,%r21
-	stw,ma	%r20, 0(%sr2,%r20)
+	ldi	__ARCH_SPIN_LOCK_UNLOCKED_VAL, %r21
+	stw,ma	%r21, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	3(%r0),%r28
 	b	lws_exit
@@ -619,6 +632,7 @@ lws_compare_and_swap:
 
 	/* Try to acquire the lock */
 	LDCW	0(%sr2,%r20), %r28
+	spinlock_check	%r28, %r21
 	comclr,<>	%r0, %r28, %r0
 	b,n	lws_wouldblock
 
@@ -772,6 +786,7 @@ cas2_lock_start:
 
 	/* Try to acquire the lock */
 	LDCW	0(%sr2,%r20), %r28
+	spinlock_check	%r28, %r21
 	comclr,<>	%r0, %r28, %r0
 	b,n	lws_wouldblock
 
@@ -1001,6 +1016,7 @@ atomic_xchg_start:
 
 	/* Try to acquire the lock */
 	LDCW	0(%sr2,%r20), %r28
+	spinlock_check	%r28, %r21
 	comclr,<>	%r0, %r28, %r0
 	b,n	lws_wouldblock
 
@@ -1199,6 +1215,7 @@ atomic_store_start:
 
 	/* Try to acquire the lock */
 	LDCW	0(%sr2,%r20), %r28
+	spinlock_check	%r28, %r21
 	comclr,<>	%r0, %r28, %r0
 	b,n	lws_wouldblock
 
@@ -1330,7 +1347,7 @@ ENTRY(lws_lock_start)
 	/* lws locks */
 	.rept 256
 	/* Keep locks aligned at 16-bytes */
-	.word 1
+	.word __ARCH_SPIN_LOCK_UNLOCKED_VAL
 	.word 0 
 	.word 0
 	.word 0

arch/riscv/include/asm/mmio.h

@@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  * Relaxed I/O memory access primitives. These follow the Device memory
  * ordering rules but do not guarantee any ordering relative to Normal memory
  * accesses.  These are defined to order the indicated access (either a read or
- * write) with all other I/O memory accesses. Since the platform specification
- * defines that all I/O regions are strongly ordered on channel 2, no explicit
- * fences are required to enforce this ordering.
+ * write) with all other I/O memory accesses to the same peripheral. Since the
+ * platform specification defines that all I/O regions are strongly ordered on
+ * channel 0, no explicit fences are required to enforce this ordering.
  */
 /* FIXME: These are now the same as asm-generic */
 #define __io_rbr()		do {} while (0)
@@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
- * I/O memory access primitives. Reads are ordered relative to any
- * following Normal memory access. Writes are ordered relative to any prior
- * Normal memory access.  The memory barriers here are necessary as RISC-V
+ * I/O memory access primitives.  Reads are ordered relative to any following
+ * Normal memory read and delay() loop.  Writes are ordered relative to any
+ * prior Normal memory write.  The memory barriers here are necessary as RISC-V
  * doesn't define any ordering between the memory space and the I/O space.
  */
 #define __io_br()	do {} while (0)
-#define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory")
-#define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory")
+#define __io_ar(v)	({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); })
+#define __io_bw()	({ __asm__ __volatile__ ("fence w,o" : : : "memory"); })
 #define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })

arch/riscv/include/asm/pgtable.h

@@ -188,6 +188,8 @@ extern struct pt_alloc_ops pt_ops __initdata;
 #define PAGE_KERNEL_IO		__pgprot(_PAGE_IOREMAP)
 
 extern pgd_t swapper_pg_dir[];
+extern pgd_t trampoline_pg_dir[];
+extern pgd_t early_pg_dir[];
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_present(pmd_t pmd)

arch/riscv/kernel/elf_kexec.c

@@ -281,7 +281,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		kbuf.buffer = initrd;
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
-		kbuf.top_down = false;
+		kbuf.top_down = true;
 		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
@@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		 * sym, instead of searching the whole relsec.
 		 */
 		case R_RISCV_PCREL_HI20:
+		case R_RISCV_CALL_PLT:
 		case R_RISCV_CALL:
 			*(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) |
 				 ENCODE_UJTYPE_IMM(val - addr);

arch/riscv/mm/init.c

@@ -26,12 +26,13 @@
 #include <linux/kfence.h>
 
 #include <asm/fixmap.h>
-#include <asm/tlbflush.h>
-#include <asm/sections.h>
-#include <asm/soc.h>
 #include <asm/io.h>
-#include <asm/ptdump.h>
 #include <asm/numa.h>
+#include <asm/pgtable.h>
+#include <asm/ptdump.h>
+#include <asm/sections.h>
+#include <asm/soc.h>
+#include <asm/tlbflush.h>
 
 #include "../kernel/head.h"
 
@@ -214,8 +215,13 @@ static void __init setup_bootmem(void)
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
 	phys_ram_end = memblock_end_of_DRAM();
+
+	/*
+	 * Make sure we align the start of the memory on a PMD boundary so that
+	 * at worst, we map the linear mapping with PMD mappings.
+	 */
 	if (!IS_ENABLED(CONFIG_XIP_KERNEL))
-		phys_ram_base = memblock_start_of_DRAM();
+		phys_ram_base = memblock_start_of_DRAM() & PMD_MASK;
 
 	/*
 	 * In 64-bit, any use of __va/__pa before this point is wrong as we

arch/riscv/mm/kasan_init.c

@@ -22,7 +22,6 @@
  * region is not and then we have to go down to the PUD level.
  */
 
-extern pgd_t early_pg_dir[PTRS_PER_PGD];
 pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss;
 pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss;

arch/x86/boot/compressed/idt_64.c

@@ -63,7 +63,14 @@ void load_stage2_idt(void)
 	set_idt_entry(X86_TRAP_PF, boot_page_fault);
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
-	set_idt_entry(X86_TRAP_VC, boot_stage2_vc);
+	/*
+	 * Clear the second stage #VC handler in case guest types
+	 * needing #VC have not been detected.
+	 */
+	if (sev_status & BIT(1))
+		set_idt_entry(X86_TRAP_VC, boot_stage2_vc);
+	else
+		set_idt_entry(X86_TRAP_VC, NULL);
 #endif
 
 	load_boot_idt(&boot_idt_desc);

arch/x86/boot/compressed/sev.c

@@ -352,21 +352,54 @@ void sev_enable(struct boot_params *bp)
 	if (bp)
 		bp->cc_blob_address = 0;
 
+	/*
+	 * Do an initial SEV capability check before snp_init() which
+	 * loads the CPUID page and the same checks afterwards are done
+	 * without the hypervisor and are trustworthy.
+	 *
+	 * If the HV fakes SEV support, the guest will crash'n'burn
+	 * which is good enough.
+	 */
+
+	/* Check for the SME/SEV support leaf */
+	eax = 0x80000000;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+	if (eax < 0x8000001f)
+		return;
+
+	/*
+	 * Check for the SME/SEV feature:
+	 *   CPUID Fn8000_001F[EAX]
+	 *   - Bit 0 - Secure Memory Encryption support
+	 *   - Bit 1 - Secure Encrypted Virtualization support
+	 *   CPUID Fn8000_001F[EBX]
+	 *   - Bits 5:0 - Pagetable bit position used to indicate encryption
+	 */
+	eax = 0x8000001f;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+	/* Check whether SEV is supported */
+	if (!(eax & BIT(1)))
+		return;
+
 	/*
 	 * Setup/preliminary detection of SNP. This will be sanity-checked
 	 * against CPUID/MSR values later.
 	 */
 	snp = snp_init(bp);
 
-	/* Check for the SME/SEV support leaf */
+	/* Now repeat the checks with the SNP CPUID table. */
+
+	/* Recheck the SME/SEV support leaf */
 	eax = 0x80000000;
 	ecx = 0;
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 	if (eax < 0x8000001f)
 		return;
 
 	/*
-	 * Check for the SME/SEV feature:
+	 * Recheck for the SME/SEV feature:
 	 *   CPUID Fn8000_001F[EAX]
 	 *   - Bit 0 - Secure Memory Encryption support
 	 *   - Bit 1 - Secure Encrypted Virtualization support

arch/x86/entry/vdso/vma.c

@@ -299,8 +299,8 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 
 	/* Round the lowest possible end address up to a PMD boundary. */
 	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
-	if (end >= TASK_SIZE_MAX)
-		end = TASK_SIZE_MAX;
+	if (end >= DEFAULT_MAP_WINDOW)
+		end = DEFAULT_MAP_WINDOW;
 	end -= len;
 
 	if (end > start) {