Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-6.17-rc3).

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/ABI/stable/sysfs-block

@@ -731,7 +731,7 @@ Contact:	linux-block@vger.kernel.org
 Description:
 		[RW] If the device is registered for writeback throttling, then
 		this file shows the target minimum read latency. If this latency
-		is exceeded in a given window of time (see wb_window_usec), then
+		is exceeded in a given window of time (see curr_win_nsec), then
 		the writeback throttling will start scaling back writes. Writing
 		a value of '0' to this file disables the feature. Writing a
 		value of '-1' to this file resets the value to the default

Documentation/admin-guide/blockdev/zoned_loop.rst

@@ -79,7 +79,7 @@ zone_capacity_mb   Device zone capacity (must always be equal to or lower than
                    the zone size. Default: zone size.
 conv_zones         Total number of conventioanl zones starting from sector 0.
                    Default: 8.
-base_dir           Path to the base directoy where to create the directory
+base_dir           Path to the base directory where to create the directory
                    containing the zone files of the device.
                    Default=/var/local/zloop.
                    The device directory containing the zone files is always

Documentation/admin-guide/hw-vuln/attack_vector_controls.rst

@@ -214,7 +214,7 @@ Spectre_v1            X
 Spectre_v2            X                           X
 Spectre_v2_user                      X                           X            *       (Note 1)
 SRBDS                 X              X            X              X
-SRSO                  X                           X
+SRSO                  X              X            X              X
 SSB                                                                                   (Note 4)
 TAA                   X              X            X              X            *       (Note 2)
 TSA                   X              X            X              X

Documentation/core-api/symbol-namespaces.rst

@@ -76,20 +76,21 @@ unit as preprocessor statement. The above example would then read::
 within the corresponding compilation unit before the #include for
 <linux/export.h>. Typically it's placed before the first #include statement.
 
-Using the EXPORT_SYMBOL_GPL_FOR_MODULES() macro
------------------------------------------------
+Using the EXPORT_SYMBOL_FOR_MODULES() macro
+-------------------------------------------
 
 Symbols exported using this macro are put into a module namespace. This
-namespace cannot be imported.
+namespace cannot be imported. These exports are GPL-only as they are only
+intended for in-tree modules.
 
 The macro takes a comma separated list of module names, allowing only those
 modules to access this symbol. Simple tail-globs are supported.
 
 For example::
 
-  EXPORT_SYMBOL_GPL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*")
+  EXPORT_SYMBOL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*")
 
-will limit usage of this symbol to modules whoes name matches the given
+will limit usage of this symbol to modules whose name matches the given
 patterns.
 
 How to use Symbols exported in Namespaces

Documentation/networking/mptcp-sysctl.rst

@@ -12,6 +12,8 @@ add_addr_timeout - INTEGER (seconds)
 	resent to an MPTCP peer that has not acknowledged a previous
 	ADD_ADDR message.
 
+	Do not retransmit if set to 0.
+
 	The default value matches TCP_RTO_MAX. This is a per-namespace
 	sysctl.
 

MAINTAINERS

@@ -22183,7 +22183,7 @@ F:	arch/s390/mm
 
 S390 NETWORK DRIVERS
 M:	Alexandra Winter <wintera@linux.ibm.com>
-M:	Thorsten Winkler <twinkler@linux.ibm.com>
+R:	Aswin Karuvally <aswin@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/loongarch/Makefile

@@ -102,7 +102,13 @@ KBUILD_CFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)
 
 ifdef CONFIG_OBJTOOL
 ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP
+# The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled.
+# Ensure it is aware of linker with LTO, '--loongarch-annotate-tablejump' also needs to
+# be passed via '-mllvm' to ld.lld.
 KBUILD_CFLAGS			+= -mannotate-tablejump
+ifdef CONFIG_LTO_CLANG
+KBUILD_LDFLAGS			+= -mllvm --loongarch-annotate-tablejump
+endif
 else
 KBUILD_CFLAGS			+= -fno-jump-tables # keep compatibility with older compilers
 endif

arch/loongarch/include/asm/stackframe.h

@@ -58,7 +58,7 @@
 	.endm
 
 	.macro STACKLEAK_ERASE
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	bl	stackleak_erase_on_task_stack
 #endif
 	.endm

arch/loongarch/include/uapi/asm/setup.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_ASM_LOONGARCH_SETUP_H
+#define _UAPI_ASM_LOONGARCH_SETUP_H
+
+#define COMMAND_LINE_SIZE	4096
+
+#endif /* _UAPI_ASM_LOONGARCH_SETUP_H */

arch/loongarch/kernel/module-sections.c

@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/ftrace.h>
+#include <linux/sort.h>
 
 Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val)
 {
@@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v
 	return (Elf_Addr)&plt[nr];
 }
 
-static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
+#define cmp_3way(a, b)  ((a) < (b) ? -1 : (a) > (b))
+
+static int compare_rela(const void *x, const void *y)
 {
-	return x->r_info == y->r_info && x->r_addend == y->r_addend;
-}
+	int ret;
+	const Elf_Rela *rela_x = x, *rela_y = y;
 
-static bool duplicate_rela(const Elf_Rela *rela, int idx)
-{
-	int i;
+	ret = cmp_3way(rela_x->r_info, rela_y->r_info);
+	if (ret == 0)
+		ret = cmp_3way(rela_x->r_addend, rela_y->r_addend);
 
-	for (i = 0; i < idx; i++) {
-		if (is_rela_equal(&rela[i], &rela[idx]))
-			return true;
-	}
-
-	return false;
+	return ret;
 }
 
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int i, type;
+	unsigned int i;
+
+	sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL);
 
 	for (i = 0; i < num; i++) {
-		type = ELF_R_TYPE(relas[i].r_info);
-		switch (type) {
+		if (i && !compare_rela(&relas[i-1], &relas[i]))
+			continue;
+
+		switch (ELF_R_TYPE(relas[i].r_info)) {
 		case R_LARCH_SOP_PUSH_PLT_PCREL:
 		case R_LARCH_B26:
-			if (!duplicate_rela(relas, i))
-				(*plts)++;
+			(*plts)++;
 			break;
 		case R_LARCH_GOT_PC_HI20:
-			if (!duplicate_rela(relas, i))
-				(*gots)++;
+			(*gots)++;
 			break;
 		default:
 			break; /* Do nothing. */

arch/loongarch/kernel/signal.c

@@ -677,6 +677,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	for (i = 1; i < 32; i++)
 		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx->lbt.addr)
+		err |= protected_save_lbt_context(extctx);
+#endif
+
 	if (extctx->lasx.addr)
 		err |= protected_save_lasx_context(extctx);
 	else if (extctx->lsx.addr)
@@ -684,11 +689,6 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	else if (extctx->fpu.addr)
 		err |= protected_save_fpu_context(extctx);
 
-#ifdef CONFIG_CPU_HAS_LBT
-	if (extctx->lbt.addr)
-		err |= protected_save_lbt_context(extctx);
-#endif
-
 	/* Set the "end" magic */
 	info = (struct sctx_info *)extctx->end.addr;
 	err |= __put_user(0, &info->magic);

arch/loongarch/kernel/time.c

@@ -5,6 +5,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/clockchips.h>
+#include <linux/cpuhotplug.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
@@ -102,6 +103,23 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev
 	return 0;
 }
 
+static int arch_timer_starting(unsigned int cpu)
+{
+	set_csr_ecfg(ECFGF_TIMER);
+
+	return 0;
+}
+
+static int arch_timer_dying(unsigned int cpu)
+{
+	constant_set_state_shutdown(this_cpu_ptr(&constant_clockevent_device));
+
+	/* Clear Timer Interrupt */
+	write_csr_tintclear(CSR_TINTCLR_TI);
+
+	return 0;
+}
+
 static unsigned long get_loops_per_jiffy(void)
 {
 	unsigned long lpj = (unsigned long)const_clock_freq;
@@ -172,6 +190,10 @@ int constant_clockevent_init(void)
 	lpj_fine = get_loops_per_jiffy();
 	pr_info("Constant clock event device register\n");
 
+	cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
+			  "clockevents/loongarch/timer:starting",
+			  arch_timer_starting, arch_timer_dying);
+
 	return 0;
 }
 

arch/loongarch/kvm/intc/eiointc.c

@@ -45,7 +45,12 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 	}
 
 	cpu = s->sw_coremap[irq];
-	vcpu = kvm_get_vcpu(s->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(s->kvm, cpu);
+	if (unlikely(vcpu == NULL)) {
+		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
+		return;
+	}
+
 	if (level) {
 		/* if not enable return false */
 		if (!test_bit(irq, (unsigned long *)s->enable.reg_u32))

arch/loongarch/kvm/intc/ipi.c

@@ -99,7 +99,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int
 static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 {
 	int i, idx, ret;
-	uint32_t val = 0, mask = 0;
+	uint64_t val = 0, mask = 0;
 
 	/*
 	 * Bit 27-30 is mask for byte writing.
@@ -108,7 +108,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	if ((data >> 27) & 0xf) {
 		/* Read the old val */
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, 4, &val);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (unlikely(ret)) {
 			kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
@@ -124,7 +124,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	}
 	val |= ((uint32_t)(data >> 32) & ~mask);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, 4, &val);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (unlikely(ret))
 		kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
@@ -298,7 +298,7 @@ static int kvm_ipi_regs_access(struct kvm_device *dev,
 	cpu = (attr->attr >> 16) & 0x3ff;
 	addr = attr->attr & 0xff;
 
-	vcpu = kvm_get_vcpu(dev->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(dev->kvm, cpu);
 	if (unlikely(vcpu == NULL)) {
 		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
 		return -EINVAL;

arch/loongarch/kvm/intc/pch_pic.c

@@ -195,6 +195,11 @@ static int kvm_pch_pic_read(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	/* statistics of pch pic reading */
 	vcpu->stat.pch_pic_read_exits++;
 	ret = loongarch_pch_pic_read(s, addr, len, val);
@@ -302,6 +307,11 @@ static int kvm_pch_pic_write(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	/* statistics of pch pic writing */
 	vcpu->stat.pch_pic_write_exits++;
 	ret = loongarch_pch_pic_write(s, addr, len, val);

arch/loongarch/kvm/vcpu.c

@@ -1283,9 +1283,11 @@ int kvm_own_lbt(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 
 	preempt_disable();
-	set_csr_euen(CSR_EUEN_LBTEN);
-	_restore_lbt(&vcpu->arch.lbt);
-	vcpu->arch.aux_inuse |= KVM_LARCH_LBT;
+	if (!(vcpu->arch.aux_inuse & KVM_LARCH_LBT)) {
+		set_csr_euen(CSR_EUEN_LBTEN);
+		_restore_lbt(&vcpu->arch.lbt);
+		vcpu->arch.aux_inuse |= KVM_LARCH_LBT;
+	}
 	preempt_enable();
 
 	return 0;

arch/x86/boot/startup/sev-shared.c

@@ -785,6 +785,7 @@ static void __head svsm_pval_4k_page(unsigned long paddr, bool validate)
 	pc->entry[0].page_size = RMP_PG_SIZE_4K;
 	pc->entry[0].action    = validate;
 	pc->entry[0].ignore_cf = 0;
+	pc->entry[0].rsvd      = 0;
 	pc->entry[0].pfn       = paddr >> PAGE_SHIFT;
 
 	/* Protocol 0, Call ID 1 */

arch/x86/coco/sev/core.c

@@ -227,6 +227,7 @@ static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
 		pe->page_size = RMP_PG_SIZE_4K;
 		pe->action    = action;
 		pe->ignore_cf = 0;
+		pe->rsvd      = 0;
 		pe->pfn       = pfn;
 
 		pe++;
@@ -257,6 +258,7 @@ static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int d
 		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
 		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
 		pe->ignore_cf = 0;
+		pe->rsvd      = 0;
 		pe->pfn       = e->gfn;
 
 		pe++;

arch/x86/coco/sev/vc-handle.c

@@ -371,29 +371,30 @@ static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
  * executing with Secure TSC enabled, so special handling is required for
  * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
  */
-static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
+static enum es_result __vc_handle_secure_tsc_msrs(struct es_em_ctxt *ctxt, bool write)
 {
+	struct pt_regs *regs = ctxt->regs;
 	u64 tsc;
 
 	/*
-	 * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
-	 * Terminate the SNP guest when the interception is enabled.
+	 * Writing to MSR_IA32_TSC can cause subsequent reads of the TSC to
+	 * return undefined values, and GUEST_TSC_FREQ is read-only. Generate
+	 * a #GP on all writes.
+	 */
+	if (write) {
+		ctxt->fi.vector = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		return ES_EXCEPTION;
+	}
+
+	/*
+	 * GUEST_TSC_FREQ read should not be intercepted when Secure TSC is
+	 * enabled. Terminate the guest if a read is attempted.
 	 */
 	if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
 		return ES_VMM_ERROR;
 
-	/*
-	 * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
-	 *         to return undefined values, so ignore all writes.
-	 *
-	 * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
-	 *        the value returned by rdtsc_ordered().
-	 */
-	if (write) {
-		WARN_ONCE(1, "TSC MSR writes are verboten!\n");
-		return ES_OK;
-	}
-
+	/* Reads of MSR_IA32_TSC should return the current TSC value. */
 	tsc = rdtsc_ordered();
 	regs->ax = lower_32_bits(tsc);
 	regs->dx = upper_32_bits(tsc);
@@ -416,7 +417,7 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 	case MSR_IA32_TSC:
 	case MSR_AMD64_GUEST_TSC_FREQ:
 		if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
-			return __vc_handle_secure_tsc_msrs(regs, write);
+			return __vc_handle_secure_tsc_msrs(ctxt, write);
 		break;
 	default:
 		break;