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

One conflict in the BPF samples Makefile, some fixes in 'net' whilst
we were converting over to Makefile.target rules in 'net-next'.

Signed-off-by: David S. Miller <[email protected]>

Documentation/networking/tls-offload.rst

@@ -436,6 +436,10 @@ by the driver:
    encryption.
  * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream
    but did not arrive in the expected order.
+ * ``tx_tls_skip_no_sync_data`` - number of TX packets which were part of
+   a TLS stream and arrived out-of-order, but skipped the HW offload routine
+   and went to the regular transmit flow as they were retransmissions of the
+   connection handshake.
  * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of
    a TLS stream dropped, because they arrived out of order and associated
    record could not be found.

MAINTAINERS

@@ -3060,6 +3060,7 @@ M:	Daniel Borkmann <[email protected]>
 R:	Martin KaFai Lau <[email protected]>
 R:	Song Liu <[email protected]>
 R:	Yonghong Song <[email protected]>
+R:	Andrii Nakryiko <[email protected]>
 L:	[email protected]
 L:	[email protected]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
@@ -10533,8 +10534,12 @@ F:	mm/memblock.c
 F:	Documentation/core-api/boot-time-mm.rst
 
 MEMORY MANAGEMENT
+M:	Andrew Morton <[email protected]>
 L:	[email protected]
 W:	http://www.linux-mm.org
+T:	quilt https://ozlabs.org/~akpm/mmotm/
+T:	quilt https://ozlabs.org/~akpm/mmots/
+T:	git git://github.com/hnaz/linux-mm.git
 S:	Maintained
 F:	include/linux/mm.h
 F:	include/linux/gfp.h
@@ -18048,6 +18053,7 @@ F:	Documentation/vm/zsmalloc.rst
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <[email protected]>
 M:	Dan Streetman <[email protected]>
+M:	Vitaly Wool <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	mm/zswap.c

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*

arch/arm64/include/asm/pgtable.h

@@ -283,23 +283,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, pte);
 }
 
-#define __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t pte_a, pte_t pte_b)
-{
-	pteval_t lhs, rhs;
-
-	lhs = pte_val(pte_a);
-	rhs = pte_val(pte_b);
-
-	if (pte_present(pte_a))
-		lhs &= ~PTE_RDONLY;
-
-	if (pte_present(pte_b))
-		rhs &= ~PTE_RDONLY;
-
-	return (lhs == rhs);
-}
-
 /*
  * Huge pte definitions.
  */

arch/powerpc/include/asm/book3s/32/kup.h

@@ -91,6 +91,7 @@
 
 static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 {
+	addr &= 0xf0000000;	/* align addr to start of segment */
 	barrier();	/* make sure thread.kuap is updated before playing with SRs */
 	while (addr < end) {
 		mtsrin(sr, addr);

arch/powerpc/include/asm/elf.h

@@ -175,4 +175,7 @@ do {									\
 	ARCH_DLINFO_CACHE_GEOMETRY;					\
 } while (0)
 
+/* Relocate the kernel image to @final_address */
+void relocate(unsigned long final_address);
+
 #endif /* _ASM_POWERPC_ELF_H */

arch/powerpc/kernel/prom_init.c

@@ -3249,7 +3249,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
 	/* Switch to secure mode. */
 	prom_printf("Switching to secure mode.\n");
 
+	/*
+	 * The ultravisor will do an integrity check of the kernel image but we
+	 * relocated it so the check will fail. Restore the original image by
+	 * relocating it back to the kernel virtual base address.
+	 */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(KERNELBASE);
+
 	ret = enter_secure_mode(kbase, fdt);
+
+	/* Relocate the kernel again. */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(kbase);
+
 	if (ret != U_SUCCESS) {
 		prom_printf("Returned %d from switching to secure mode.\n", ret);
 		prom_rtas_os_term("Switch to secure mode failed.\n");

arch/powerpc/kernel/prom_init_check.sh

@@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 logo_linux_clut224 btext_prepare_BAT
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
+__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC.
+relocate"
 
 NM="$1"
 OBJ="$2"

arch/powerpc/net/bpf_jit_comp64.c

@@ -1141,6 +1141,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		goto out_addrs;
 	}
 
+	/*
+	 * If we have seen a tail call, we need a second pass.
+	 * This is because bpf_jit_emit_common_epilogue() is called
+	 * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen.
+	 */
+	if (cgctx.seen & SEEN_TAILCALL) {
+		cgctx.idx = 0;
+		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
+	}
+
 	/*
 	 * Pretend to build prologue, given the features we've seen.  This will
 	 * update ctgtx.idx as it pretends to output instructions, then we can

arch/powerpc/platforms/powernv/eeh-powernv.c

@@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (eeh_has_flag(EEH_FORCE_DISABLED))
+	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");

arch/powerpc/platforms/powernv/smp.c

@@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void)
 	return 0;
 }
 
+static void pnv_flush_interrupts(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (xive_enabled())
+			xive_flush_interrupt();
+		else
+			icp_opal_flush_interrupt();
+	} else {
+		icp_native_flush_interrupt();
+	}
+}
+
 static void pnv_smp_cpu_kill_self(void)
 {
+	unsigned long srr1, unexpected_mask, wmask;
 	unsigned int cpu;
-	unsigned long srr1, wmask;
 	u64 lpcr_val;
 
 	/* Standard hot unplug procedure */
-	/*
-	 * This hard disables local interurpts, ensuring we have no lazy
-	 * irqs pending.
-	 */
-	WARN_ON(irqs_disabled());
-	hard_irq_disable();
-	WARN_ON(lazy_irq_pending());
 
 	idle_task_exit();
 	current->active_mm = NULL; /* for sanity */
@@ -172,6 +177,27 @@ static void pnv_smp_cpu_kill_self(void)
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		wmask = SRR1_WAKEMASK_P8;
 
+	/*
+	 * This turns the irq soft-disabled state we're called with, into a
+	 * hard-disabled state with pending irq_happened interrupts cleared.
+	 *
+	 * PACA_IRQ_DEC   - Decrementer should be ignored.
+	 * PACA_IRQ_HMI   - Can be ignored, processing is done in real mode.
+	 * PACA_IRQ_DBELL, EE, PMI - Unexpected.
+	 */
+	hard_irq_disable();
+	if (generic_check_cpu_restart(cpu))
+		goto out;
+
+	unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS);
+	if (local_paca->irq_happened & unexpected_mask) {
+		if (local_paca->irq_happened & PACA_IRQ_EE)
+			pnv_flush_interrupts();
+		DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n",
+				cpu, local_paca->irq_happened);
+	}
+	local_paca->irq_happened = PACA_IRQ_HARD_DIS;
+
 	/*
 	 * We don't want to take decrementer interrupts while we are
 	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
@@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void)
 
 		srr1 = pnv_cpu_offline(cpu);
 
+		WARN_ON_ONCE(!irqs_disabled());
 		WARN_ON(lazy_irq_pending());
 
 		/*
@@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void)
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
 		    ((srr1 & wmask) == SRR1_WAKEHVI)) {
-			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-				if (xive_enabled())
-					xive_flush_interrupt();
-				else
-					icp_opal_flush_interrupt();
-			} else
-				icp_native_flush_interrupt();
+			pnv_flush_interrupts();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
 	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
-
+out:
 	DBG("CPU%d coming online...\n", cpu);
 }
 

arch/s390/include/asm/unwind.h

@@ -35,6 +35,7 @@ struct unwind_state {
 	struct task_struct *task;
 	struct pt_regs *regs;
 	unsigned long sp, ip;
+	bool reuse_sp;
 	int graph_idx;
 	bool reliable;
 	bool error;

arch/s390/kernel/idle.c

@@ -69,36 +69,51 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 static ssize_t show_idle_time(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
+	unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long now, idle_time, idle_enter, idle_exit;
 	unsigned int seq;
 
 	do {
-		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
 		idle_time = READ_ONCE(idle->idle_time);
 		idle_enter = READ_ONCE(idle->clock_idle_enter);
 		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+	in_idle = 0;
+	now = get_tod_clock();
+	if (idle_enter) {
+		if (idle_exit) {
+			in_idle = idle_exit - idle_enter;
+		} else if (now > idle_enter) {
+			in_idle = now - idle_enter;
+		}
+	}
+	idle_time += in_idle;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
 u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit;
+	unsigned long long now, idle_enter, idle_exit, in_idle;
 	unsigned int seq;
 
 	do {
-		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
 		idle_enter = READ_ONCE(idle->clock_idle_enter);
 		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-
-	return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
+	in_idle = 0;
+	now = get_tod_clock();
+	if (idle_enter) {
+		if (idle_exit) {
+			in_idle = idle_exit - idle_enter;
+		} else if (now > idle_enter) {
+			in_idle = now - idle_enter;
+		}
+	}
+	return cputime_to_nsecs(in_idle);
 }
 
 void arch_cpu_idle_enter(void)

arch/s390/kernel/unwind_bc.c

@@ -46,10 +46,15 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	regs = state->regs;
 	if (unlikely(regs)) {
-		sp = READ_ONCE_NOCHECK(regs->gprs[15]);
-		if (unlikely(outside_of_stack(state, sp))) {
-			if (!update_stack_info(state, sp))
-				goto out_err;
+		if (state->reuse_sp) {
+			sp = state->sp;
+			state->reuse_sp = false;
+		} else {
+			sp = READ_ONCE_NOCHECK(regs->gprs[15]);
+			if (unlikely(outside_of_stack(state, sp))) {
+				if (!update_stack_info(state, sp))
+					goto out_err;
+			}
 		}
 		sf = (struct stack_frame *) sp;
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
@@ -107,9 +112,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 {
 	struct stack_info *info = &state->stack_info;
 	unsigned long *mask = &state->stack_mask;
+	bool reliable, reuse_sp;
 	struct stack_frame *sf;
 	unsigned long ip;
-	bool reliable;
 
 	memset(state, 0, sizeof(*state));
 	state->task = task;
@@ -134,10 +139,12 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	if (regs) {
 		ip = READ_ONCE_NOCHECK(regs->psw.addr);
 		reliable = true;
+		reuse_sp = true;
 	} else {
 		sf = (struct stack_frame *) sp;
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
+		reuse_sp = false;
 	}
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -151,5 +158,6 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	state->sp = sp;
 	state->ip = ip;
 	state->reliable = reliable;
+	state->reuse_sp = reuse_sp;
 }
 EXPORT_SYMBOL_GPL(__unwind_start);

arch/s390/mm/cmm.c

@@ -298,26 +298,26 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write,
 	}
 
 	if (write) {
-		len = *lenp;
-		if (copy_from_user(buf, buffer,
-				   len > sizeof(buf) ? sizeof(buf) : len))
+		len = min(*lenp, sizeof(buf));
+		if (copy_from_user(buf, buffer, len))
 			return -EFAULT;
-		buf[sizeof(buf) - 1] = '\0';
+		buf[len - 1] = '\0';
 		cmm_skip_blanks(buf, &p);
 		nr = simple_strtoul(p, &p, 0);
 		cmm_skip_blanks(p, &p);
 		seconds = simple_strtoul(p, &p, 0);
 		cmm_set_timeout(nr, seconds);
+		*ppos += *lenp;
 	} else {
 		len = sprintf(buf, "%ld %ld\n",
 			      cmm_timeout_pages, cmm_timeout_seconds);
 		if (len > *lenp)
 			len = *lenp;
 		if (copy_to_user(buffer, buf, len))
 			return -EFAULT;
+		*lenp = len;
+		*ppos += len;
 	}
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }