.mailmap

@@ -88,7 +88,6 @@ Antonio Quartulli <antonio@mandelbit.com> <antonio@open-mesh.com>
 Antonio Quartulli <antonio@mandelbit.com> <antonio.quartulli@open-mesh.com>
 Antonio Quartulli <antonio@mandelbit.com> <ordex@autistici.org>
 Antonio Quartulli <antonio@mandelbit.com> <ordex@ritirata.org>
-Antonio Quartulli <antonio@mandelbit.com> <antonio@openvpn.net>
 Antonio Quartulli <antonio@mandelbit.com> <a@unstable.cc>
 Anup Patel <anup@brainfault.org> <anup.patel@wdc.com>
 Archit Taneja <archit@ti.com>
@@ -692,6 +691,7 @@ Subbaraman Narayanamurthy <quic_subbaram@quicinc.com> <subbaram@codeaurora.org>
 Subhash Jadavani <subhashj@codeaurora.org>
 Sudarshan Rajagopalan <quic_sudaraja@quicinc.com> <sudaraja@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+Sumit Garg <sumit.garg@kernel.org> <sumit.garg@linaro.org>
 Sumit Semwal <sumit.semwal@ti.com>
 Surabhi Vishnoi <quic_svishnoi@quicinc.com> <svishnoi@codeaurora.org>
 Sven Eckelmann <sven@narfation.org> <seckelmann@datto.com>

Documentation/admin-guide/README.rst

@@ -176,7 +176,7 @@ Configuring the kernel
                         values without prompting.
 
      "make defconfig"   Create a ./.config file by using the default
-                        symbol values from either arch/$ARCH/defconfig
+                        symbol values from either arch/$ARCH/configs/defconfig
                         or arch/$ARCH/configs/${PLATFORM}_defconfig,
                         depending on the architecture.
 

Documentation/admin-guide/sysctl/kernel.rst

@@ -212,6 +212,17 @@ pid>/``).
 This value defaults to 0.
 
 
+core_sort_vma
+=============
+
+The default coredump writes VMAs in address order. By setting
+``core_sort_vma`` to 1, VMAs will be written from smallest size
+to largest size. This is known to break at least elfutils, but
+can be handy when dealing with very large (and truncated)
+coredumps where the more useful debugging details are included
+in the smaller VMAs.
+
+
 core_uses_pid
 =============
 

Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml

@@ -146,6 +146,7 @@ properties:
     maxItems: 2
 
   pwm-names:
+    minItems: 1
     items:
       - const: convst1
       - const: convst2

Documentation/filesystems/idmappings.rst

@@ -63,8 +63,8 @@ what id ``k11000`` corresponds to in the second or third idmapping. The
 straightforward algorithm to use is to apply the inverse of the first idmapping,
 mapping ``k11000`` up to ``u1000``. Afterwards, we can map ``u1000`` down using
 either the second idmapping mapping or third idmapping mapping. The second
-idmapping would map ``u1000`` down to ``21000``. The third idmapping would map
-``u1000`` down to ``u31000``.
+idmapping would map ``u1000`` down to ``k21000``. The third idmapping would map
+``u1000`` down to ``k31000``.
 
 If we were given the same task for the following three idmappings::
 

Documentation/scheduler/sched-rt-group.rst

@@ -102,6 +102,9 @@ The system wide settings are configured under the /proc virtual file system:
   * sched_rt_period_us takes values from 1 to INT_MAX.
   * sched_rt_runtime_us takes values from -1 to sched_rt_period_us.
   * A run time of -1 specifies runtime == period, ie. no limit.
+  * sched_rt_runtime_us/sched_rt_period_us > 0.05 inorder to preserve
+    bandwidth for fair dl_server. For accurate value check average of
+    runtime/period in /sys/kernel/debug/sched/fair_server/cpuX/
 
 
 2.2 Default behaviour

MAINTAINERS

@@ -5775,6 +5775,7 @@ X:	drivers/clk/clkdev.c
 COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3)
 M:	Steve French <sfrench@samba.org>
+M:	Steve French <smfrench@gmail.com>
 R:	Paulo Alcantara <pc@manguebit.com> (DFS, global name space)
 R:	Ronnie Sahlberg <ronniesahlberg@gmail.com> (directory leases, sparse files)
 R:	Shyam Prasad N <sprasad@microsoft.com> (multichannel)
@@ -9442,14 +9443,11 @@ F:	include/linux/fscrypt.h
 F:	include/uapi/linux/fscrypt.h
 FSI SUBSYSTEM
-M:	Jeremy Kerr <jk@ozlabs.org>
-M:	Joel Stanley <joel@jms.id.au>
-R:	Alistar Popple <alistair@popple.id.au>
-R:	Eddie James <eajames@linux.ibm.com>
+M:	Eddie James <eajames@linux.ibm.com>
+R:	Ninad Palsule <ninad@linux.ibm.com>
 L:	linux-fsi@lists.ozlabs.org
 S:	Supported
 Q:	http://patchwork.ozlabs.org/project/linux-fsi/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joel/fsi.git
 F:	drivers/fsi/
 F:	include/linux/fsi*.h
 F:	include/trace/events/fsi*.h
@@ -12655,7 +12653,9 @@ F:	tools/testing/selftests/
 KERNEL SMB3 SERVER (KSMBD)
 M:	Namjae Jeon <linkinjeon@kernel.org>
+M:	Namjae Jeon <linkinjeon@samba.org>
 M:	Steve French <sfrench@samba.org>
+M:	Steve French <smfrench@gmail.com>
 R:	Sergey Senozhatsky <senozhatsky@chromium.org>
 R:	Tom Talpey <tom@talpey.com>
 L:	linux-cifs@vger.kernel.org
@@ -12872,7 +12872,7 @@ F:	include/keys/trusted_dcp.h
 F:	security/keys/trusted-keys/trusted_dcp.c
 KEYS-TRUSTED-TEE
-M:	Sumit Garg <sumit.garg@linaro.org>
+M:	Sumit Garg <sumit.garg@kernel.org>
 L:	linux-integrity@vger.kernel.org
 L:	keyrings@vger.kernel.org
 S:	Supported
@@ -17672,7 +17672,7 @@ F:	Documentation/ABI/testing/sysfs-bus-optee-devices
 F:	drivers/tee/optee/
 OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER
-M:	Sumit Garg <sumit.garg@linaro.org>
+M:	Sumit Garg <sumit.garg@kernel.org>
 L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
@@ -23285,7 +23285,7 @@ F:	include/media/i2c/tw9910.h
 TEE SUBSYSTEM
 M:	Jens Wiklander <jens.wiklander@linaro.org>
-R:	Sumit Garg <sumit.garg@linaro.org>
+R:	Sumit Garg <sumit.garg@kernel.org>
 L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-tee

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
@@ -1123,6 +1123,11 @@ endif
 KBUILD_USERCFLAGS  += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
+# userspace programs are linked via the compiler, use the correct linker
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_LD_IS_LLD),yy)
+KBUILD_USERLDFLAGS += --ld-path=$(LD)
+endif
+
 # make the checker run with the right architecture
 CHECKFLAGS += --arch=$(ARCH)
 

arch/arm/mm/fault-armv.c

@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -141,6 +141,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	 */
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
+		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
 		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}

arch/arm64/include/asm/el2_setup.h

@@ -16,6 +16,32 @@
 #include <asm/sysreg.h>
 #include <linux/irqchip/arm-gic-v3.h>
 
+.macro init_el2_hcr	val
+	mov_q	x0, \val
+
+	/*
+	 * Compliant CPUs advertise their VHE-onlyness with
+	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
+	 * can reset into an UNKNOWN state and might not read as 1 until it has
+	 * been initialized explicitly.
+	 *
+	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+	 * don't advertise it (they predate this relaxation).
+	 *
+	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * indicating whether the CPU is running in E2H mode.
+	 */
+	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
+	sbfx	x1, x1, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
+	cmp	x1, #0
+	b.ge	.LnVHE_\@
+
+	orr	x0, x0, #HCR_E2H
+.LnVHE_\@:
+	msr	hcr_el2, x0
+	isb
+.endm
+
 .macro __init_el2_sctlr
 	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
 	msr	sctlr_el2, x0
@@ -244,11 +270,6 @@
 .Lskip_gcs_\@:
 .endm
 
-.macro __init_el2_nvhe_prepare_eret
-	mov	x0, #INIT_PSTATE_EL1
-	msr	spsr_el2, x0
-.endm
-
 .macro __init_el2_mpam
 	/* Memory Partitioning And Monitoring: disable EL2 traps */
 	mrs	x1, id_aa64pfr0_el1

arch/arm64/kernel/head.S

@@ -298,25 +298,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el2, x0
 	isb
 0:
-	mov_q	x0, HCR_HOST_NVHE_FLAGS
-
-	/*
-	 * Compliant CPUs advertise their VHE-onlyness with
-	 * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
-	 * RES1 in that case. Publish the E2H bit early so that
-	 * it can be picked up by the init_el2_state macro.
-	 *
-	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
-	 * don't advertise it (they predate this relaxation).
-	 */
-	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
-	tbz	x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
-	orr	x0, x0, #HCR_E2H
-1:
-	msr	hcr_el2, x0
-	isb
 
+	init_el2_hcr	HCR_HOST_NVHE_FLAGS
 	init_el2_state
 
 	/* Hypervisor stub */
@@ -339,7 +322,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 3:
-	__init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
 
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2

arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -73,8 +73,12 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+/*
+ * Initialize EL2 CPU state to sane values.
+ *
+ * HCR_EL2.E2H must have been initialized already.
+ */
 SYM_CODE_START_LOCAL(__kvm_init_el2_state)
-	/* Initialize EL2 CPU state to sane values. */
 	init_el2_state				// Clobbers x0..x2
 	finalise_el2_state
 	ret
@@ -206,9 +210,9 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
-	bl	__kvm_init_el2_state
+	init_el2_hcr	0
 
-	__init_el2_nvhe_prepare_eret
+	bl	__kvm_init_el2_state
 
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28

arch/arm64/kvm/hyp/nvhe/psci-relay.c

@@ -218,6 +218,9 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	if (is_cpu_on)
 		release_boot_args(boot_args);
 
+	write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR);
+	write_sysreg(INIT_PSTATE_EL1, SPSR_EL2);
+
 	__host_enter(host_ctxt);
 }
 

arch/loongarch/kernel/acpi.c

@@ -249,18 +249,6 @@ static __init int setup_node(int pxm)
 	return acpi_map_pxm_to_node(pxm);
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-unsigned int numa_distance_cnt;
-
-static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
-{
-	return slit->locality_count;
-}
-
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) {

arch/loongarch/kernel/machine_kexec.c

@@ -126,14 +126,14 @@ void kexec_reboot(void)
 	/* All secondary cpus go to kexec_smp_wait */
 	if (smp_processor_id() > 0) {
 		relocated_kexec_smp_wait(NULL);
-		unreachable();
+		BUG();
 	}
 #endif
 
 	do_kexec = (void *)reboot_code_buffer;
 	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
 
-	unreachable();
+	BUG();
 }
 
 

arch/loongarch/kernel/setup.c

@@ -387,6 +387,9 @@ static void __init check_kernel_sections_mem(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	/* Recalculate max_low_pfn for "mem=xxx" */
+	max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
+
 	if (usermem)
 		pr_info("User-defined physical RAM map overwrite\n");
 

arch/loongarch/kernel/smp.c

@@ -19,6 +19,7 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/time.h>
 #include <linux/tracepoint.h>
@@ -423,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu)
 	mb();
 }
 
-void __noreturn arch_cpu_idle_dead(void)
+static void __noreturn idle_play_dead(void)
 {
 	register uint64_t addr;
 	register void (*init_fn)(void);
@@ -447,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void)
 	BUG();
 }
 
+#ifdef CONFIG_HIBERNATION
+static void __noreturn poll_play_dead(void)
+{
+	register uint64_t addr;
+	register void (*init_fn)(void);
+
+	idle_task_exit();
+	__this_cpu_write(cpu_state, CPU_DEAD);
+
+	__smp_mb();
+	do {
+		__asm__ __volatile__("nop\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
+
+	init_fn();
+	BUG();
+}
+#endif
+
+static void (*play_dead)(void) = idle_play_dead;
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	play_dead();
+	BUG(); /* play_dead() doesn't return */
+}
+
+#ifdef CONFIG_HIBERNATION
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	int ret;
+
+	play_dead = poll_play_dead;
+	ret = suspend_disable_secondary_cpus();
+	play_dead = idle_play_dead;
+
+	return ret;
+}
+#endif
+
 #endif
 
 /*

arch/loongarch/kvm/exit.c

@@ -669,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write)
 	struct kvm_run *run = vcpu->run;
 	unsigned long badv = vcpu->arch.badv;
 
+	/* Inject ADE exception if exceed max GPA size */
+	if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) {
+		kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM);
+		return RESUME_GUEST;
+	}
+
 	ret = kvm_handle_mm_fault(vcpu, badv, write);
 	if (ret) {
 		/* Treat as MMIO */

arch/loongarch/kvm/main.c

@@ -317,6 +317,13 @@ int kvm_arch_enable_virtualization_cpu(void)
 	kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx",
 		  read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc());
 
+	/*
+	 * HW Guest CSR registers are lost after CPU suspend and resume.
+	 * Clear last_vcpu so that Guest CSR registers forced to reload
+	 * from vCPU SW state.
+	 */
+	this_cpu_ptr(vmcs)->last_vcpu = NULL;
+
 	return 0;
 }
 

arch/loongarch/kvm/vcpu.c

@@ -311,7 +311,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int ret = RESUME_GUEST;
 	unsigned long estat = vcpu->arch.host_estat;
-	u32 intr = estat & 0x1fff; /* Ignore NMI */
+	u32 intr = estat & CSR_ESTAT_IS;
 	u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;