Re: Linux 4.15.9

[Greg KH <gregkh@linuxfoundation.org>]

diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 3c65feb83010..a81c97a4b4a5 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -54,6 +54,10 @@ KVM_FEATURE_PV_UNHALT              ||     7 || guest checks this feature bit
                                    ||       || before enabling paravirtualized
                                    ||       || spinlock support.
 ------------------------------------------------------------------------------
+KVM_FEATURE_ASYNC_PF_VMEXIT        ||    10 || paravirtualized async PF VM exit
+                                   ||       || can be enabled by setting bit 2
+                                   ||       || when writing to msr 0x4b564d02
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index 1ebecc115dc6..f3f0d57ced8e 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -170,7 +170,8 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02
 	when asynchronous page faults are enabled on the vcpu 0 when
 	disabled. Bit 1 is 1 if asynchronous page faults can be injected
 	when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
-	are delivered to L1 as #PF vmexits.
+	are delivered to L1 as #PF vmexits.  Bit 2 can be set only if
+	KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID.
 
 	First 4 byte of 64 byte memory location will be written to by
 	the hypervisor at the time of asynchronous page fault (APF)
diff --git a/Makefile b/Makefile
index eb18d200a603..0420f9a0c70f 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 15
-SUBLEVEL = 8
+SUBLEVEL = 9
 EXTRAVERSION =
 NAME = Fearless Coyote
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index bb32f7f6dd0f..be155f70f108 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -238,8 +238,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	off = offsetof(struct bpf_array, map.max_entries);
 	emit_a64_mov_i64(tmp, off, ctx);
 	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_MOV(0, r3, r3), ctx);
 	emit(A64_CMP(0, r3, tmp), ctx);
-	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
 
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *     goto out;
@@ -247,7 +248,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
 	emit(A64_CMP(1, tcc, tmp), ctx);
-	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_HI, jmp_offset), ctx);
 	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
 
 	/* prog = array->ptrs[index];
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index d183b4801bdb..35591fb09042 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -242,6 +242,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	 *   goto out;
 	 */
 	PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
+	PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
 	PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
 	PPC_BCC(COND_GE, out);
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 76b058533e47..81a1be326571 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -177,4 +177,41 @@ static inline void indirect_branch_prediction_barrier(void)
 }
 
 #endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ *    callq do_rop
+ *  spec_trap:
+ *    pause
+ *    lfence
+ *    jmp spec_trap
+ *  do_rop:
+ *    mov %rax,(%rsp)
+ *    retq
+ *
+ * Without retpolines configured:
+ *
+ *    jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE	17
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
+	/* spec_trap: */					\
+	EMIT2(0xF3, 0x90);       /* pause */			\
+	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
+	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
+	/* do_rop: */						\
+	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
+	EMIT1(0xC3);             /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE	2
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE0);	 /* jmp *%rax */
+#endif
+
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 09cc06483bed..989db885de97 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -25,6 +25,7 @@
 #define KVM_FEATURE_STEAL_TIME		5
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
+#define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b40ffbf156c1..0a93e83b774a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void)
 #endif
 		pa |= KVM_ASYNC_PF_ENABLED;
 
-		/* Async page fault support for L1 hypervisor is optional */
-		if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
-			(pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0)
-			wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+		if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
+			pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+
+		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 13f5d4217e4f..4f544f2a7b06 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -597,7 +597,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_ASYNC_PF) |
 			     (1 << KVM_FEATURE_PV_EOI) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
-			     (1 << KVM_FEATURE_PV_UNHALT);
+			     (1 << KVM_FEATURE_PV_UNHALT) |
+			     (1 << KVM_FEATURE_ASYNC_PF_VMEXIT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 0554e8aef4d5..940aac70b4da 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -13,6 +13,7 @@
 #include <linux/if_vlan.h>
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
+#include <asm/nospec-branch.h>
 #include <linux/bpf.h>
 
 int bpf_jit_enable __read_mostly;
@@ -287,7 +288,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 43 /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -296,7 +297,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 */
 	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 32
+#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
@@ -310,7 +311,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 *   goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
-#define OFFSET3 10
+#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
 	label3 = cnt;
 
@@ -323,7 +324,7 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 * rdi == ctx (1st arg)
 	 * rax == prog->bpf_func + prologue_size
 	 */
-	EMIT2(0xFF, 0xE0);                        /* jmp rax */
+	RETPOLINE_RAX_BPF_JIT();
 
 	/* out: */
 	BUILD_BUG_ON(cnt - label1 != OFFSET1);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 8027de465d47..f43b51452596 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -6289,14 +6289,14 @@ _base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
 }
 
 /**
- * _wait_for_commands_to_complete - reset controller
+ * mpt3sas_wait_for_commands_to_complete - reset controller
  * @ioc: Pointer to MPT_ADAPTER structure
  *
  * This function waiting(3s) for all pending commands to complete
  * prior to putting controller in reset.
  */
-static void
-_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
+void
+mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
 {
 	u32 ioc_state;
 	unsigned long flags;
@@ -6375,7 +6375,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 			is_fault = 1;
 	}
 	_base_reset_handler(ioc, MPT3_IOC_PRE_RESET);
-	_wait_for_commands_to_complete(ioc);
+	mpt3sas_wait_for_commands_to_complete(ioc);
 	_base_mask_interrupts(ioc);
 	r = _base_make_ioc_ready(ioc, type);
 	if (r)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 60f42ca3954f..69022b10a3d8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1435,6 +1435,9 @@ void mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc,
 
 int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc);
 
+void
+mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc);
+
 
 /* scsih shared API */
 u8 mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b258f210120a..741b0a28c2e3 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2998,7 +2998,8 @@ scsih_abort(struct scsi_cmnd *scmd)
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
-	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
+	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
+	    ioc->remove_host) {
 		sdev_printk(KERN_INFO, scmd->device,
 			"device been deleted! scmd(%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
@@ -3060,7 +3061,8 @@ scsih_dev_reset(struct scsi_cmnd *scmd)
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
-	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
+	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
+	    ioc->remove_host) {
 		sdev_printk(KERN_INFO, scmd->device,
 			"device been deleted! scmd(%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
@@ -3122,7 +3124,8 @@ scsih_target_reset(struct scsi_cmnd *scmd)
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
-	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
+	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
+	    ioc->remove_host) {
 		starget_printk(KERN_INFO, starget, "target been deleted! scmd(%p)\n",
 			scmd);
 		scmd->result = DID_NO_CONNECT << 16;
@@ -3179,7 +3182,7 @@ scsih_host_reset(struct scsi_cmnd *scmd)
 	    ioc->name, scmd);
 	scsi_print_command(scmd);
 
-	if (ioc->is_driver_loading) {
+	if (ioc->is_driver_loading || ioc->remove_host) {
 		pr_info(MPT3SAS_FMT "Blocking the host reset\n",
 		    ioc->name);
 		r = FAILED;
@@ -4611,7 +4614,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
 		_scsih_set_satl_pending(scmd, false);
 		mpt3sas_base_free_smid(ioc, smid);
 		scsi_dma_unmap(scmd);
-		if (ioc->pci_error_recovery)
+		if (ioc->pci_error_recovery || ioc->remove_host)
 			scmd->result = DID_NO_CONNECT << 16;
 		else
 			scmd->result = DID_RESET << 16;
@@ -9901,6 +9904,10 @@ static void scsih_remove(struct pci_dev *pdev)
 	unsigned long flags;
 
 	ioc->remove_host = 1;
+
+	mpt3sas_wait_for_commands_to_complete(ioc);
+	_scsih_flush_running_cmds(ioc);
+
 	_scsih_fw_event_cleanup_queue(ioc);
 
 	spin_lock_irqsave(&ioc->fw_event_lock, flags);
@@ -9977,6 +9984,10 @@ scsih_shutdown(struct pci_dev *pdev)
 	unsigned long flags;
 
 	ioc->remove_host = 1;
+
+	mpt3sas_wait_for_commands_to_complete(ioc);
+	_scsih_flush_running_cmds(ioc);
+
 	_scsih_fw_event_cleanup_queue(ioc);
 
 	spin_lock_irqsave(&ioc->fw_event_lock, flags);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index ab94d304a634..8596aa31c75e 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -26,8 +26,10 @@ static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
 
-	for (i = 0; i < array->map.max_entries; i++)
+	for (i = 0; i < array->map.max_entries; i++) {
 		free_percpu(array->pptrs[i]);
+		cond_resched();
+	}
 }
 
 static int bpf_array_alloc_percpu(struct bpf_array *array)
@@ -43,6 +45,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
 			return -ENOMEM;
 		}
 		array->pptrs[i] = ptr;
+		cond_resched();
 	}
 
 	return 0;
@@ -52,11 +55,11 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
 static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
-	int numa_node = bpf_map_attr_numa_node(attr);
+	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
 	bool unpriv = !capable(CAP_SYS_ADMIN);
+	u64 cost, array_size, mask64;
 	struct bpf_array *array;
-	u64 array_size, mask64;
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -101,8 +104,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		array_size += (u64) max_entries * elem_size;
 
 	/* make sure there is no u32 overflow later in round_up() */
-	if (array_size >= U32_MAX - PAGE_SIZE)
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-ENOMEM);
+	if (percpu) {
+		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
+		if (cost >= U32_MAX - PAGE_SIZE)
+			return ERR_PTR(-ENOMEM);
+	}
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
 	array = bpf_map_area_alloc(array_size, numa_node);
@@ -118,20 +132,13 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array->map.max_entries = attr->max_entries;
 	array->map.map_flags = attr->map_flags;
 	array->map.numa_node = numa_node;
+	array->map.pages = cost;
 	array->elem_size = elem_size;
 
-	if (!percpu)
-		goto out;
-
-	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
-
-	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    bpf_array_alloc_percpu(array)) {
+	if (percpu && bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
-out:
-	array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
 
 	return &array->map;
 }
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 885e45479680..424f89ac4adc 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -560,7 +560,10 @@ static void trie_free(struct bpf_map *map)
 	struct lpm_trie_node __rcu **slot;
 	struct lpm_trie_node *node;
 
-	raw_spin_lock(&trie->lock);
+	/* Wait for outstanding programs to complete
+	 * update/lookup/delete/get_next_key and free the trie.
+	 */
+	synchronize_rcu();
 
 	/* Always start at the root and walk down to a node that has no
 	 * children. Then free that node, nullify its reference in the parent
@@ -571,10 +574,9 @@ static void trie_free(struct bpf_map *map)
 		slot = &trie->root;
 
 		for (;;) {
-			node = rcu_dereference_protected(*slot,
-					lockdep_is_held(&trie->lock));
+			node = rcu_dereference_protected(*slot, 1);
 			if (!node)
-				goto unlock;
+				goto out;
 
 			if (rcu_access_pointer(node->child[0])) {
 				slot = &node->child[0];
@@ -592,8 +594,8 @@ static void trie_free(struct bpf_map *map)
 		}
 	}
 
-unlock:
-	raw_spin_unlock(&trie->lock);
+out:
+	kfree(trie);
 }
 
 static int trie_get_next_key(struct bpf_map *map, void *key, void *next_key)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 13551e623501..7125ddbb24df 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -985,6 +985,13 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 	return reg->type == PTR_TO_CTX;
 }
 
+static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+
+	return type_is_pkt_pointer(reg->type);
+}
+
 static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
 				   const struct bpf_reg_state *reg,
 				   int off, int size, bool strict)
@@ -1045,10 +1052,10 @@ static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
 }
 
 static int check_ptr_alignment(struct bpf_verifier_env *env,
-			       const struct bpf_reg_state *reg,
-			       int off, int size)
+			       const struct bpf_reg_state *reg, int off,
+			       int size, bool strict_alignment_once)
 {
-	bool strict = env->strict_alignment;
+	bool strict = env->strict_alignment || strict_alignment_once;
 	const char *pointer_desc = "";
 
 	switch (reg->type) {
@@ -1108,9 +1115,9 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
  * if t==write && value_regno==-1, some unknown value is stored into memory
  * if t==read && value_regno==-1, don't care what we read from memory
  */
-static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off,
-			    int bpf_size, enum bpf_access_type t,
-			    int value_regno)
+static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
+			    int off, int bpf_size, enum bpf_access_type t,
+			    int value_regno, bool strict_alignment_once)
 {
 	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_reg_state *regs = cur_regs(env);
@@ -1122,7 +1129,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		return size;
 
 	/* alignment checks will add in reg->off themselves */
-	err = check_ptr_alignment(env, reg, off, size);
+	err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
 	if (err)
 		return err;
 
@@ -1265,21 +1272,23 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 		return -EACCES;
 	}
 
-	if (is_ctx_reg(env, insn->dst_reg)) {
-		verbose(env, "BPF_XADD stores into R%d context is not allowed\n",
-			insn->dst_reg);
+	if (is_ctx_reg(env, insn->dst_reg) ||
+	    is_pkt_reg(env, insn->dst_reg)) {
+		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
+			insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
+			"context" : "packet");
 		return -EACCES;
 	}
 
 	/* check whether atomic_add can read the memory */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_READ, -1);
+			       BPF_SIZE(insn->code), BPF_READ, -1, true);
 	if (err)
 		return err;
 
 	/* check whether atomic_add can write into the same memory */
 	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-				BPF_SIZE(insn->code), BPF_WRITE, -1);
+				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
 }
 
 /* Does this register contain a constant zero? */
@@ -1763,7 +1772,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
 	 * is inferred from register state.
 	 */
 	for (i = 0; i < meta.access_size; i++) {
-		err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1);
+		err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
+				       BPF_WRITE, -1, false);
 		if (err)
 			return err;
 	}
@@ -3933,7 +3943,7 @@ static int do_check(struct bpf_verifier_env *env)
 			 */
 			err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_READ,
-					       insn->dst_reg);
+					       insn->dst_reg, false);
 			if (err)
 				return err;
 
@@ -3985,7 +3995,7 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
-					       insn->src_reg);
+					       insn->src_reg, false);
 			if (err)
 				return err;
 
@@ -4020,7 +4030,7 @@ static int do_check(struct bpf_verifier_env *env)
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
-					       -1);
+					       -1, false);
 			if (err)
 				return err;
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 5ed4175c4ff8..0694527acaa0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2254,6 +2254,32 @@ static struct bpf_test tests[] = {
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
+	{
+		"runtime/jit: pass negative index to tail_call",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, -1),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog = { 1 },
+		.result = ACCEPT,
+	},
+	{
+		"runtime/jit: pass > 32bit index to tail_call",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog = { 2 },
+		.result = ACCEPT,
+	},
 	{
 		"stack pointer arithmetic",
 		.insns = {
@@ -8826,6 +8852,64 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
 	},
+	{
+		"xadd/w check unaligned stack",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "misaligned stack access off",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"xadd/w check unaligned map",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_1, 1),
+			BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = REJECT,
+		.errstr = "misaligned value access off",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"xadd/w check unaligned pkt",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 99),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 6),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+			BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0),
+			BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1),
+			BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "BPF_XADD stores into R2 packet",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)