Merge 5.10.35 into android12-5.10

Changes in 5.10.35
	mips: Do not include hi and lo in clobber list for R6
	netfilter: conntrack: Make global sysctls readonly in non-init netns
	net: usb: ax88179_178a: initialize local variables before use
	igb: Enable RSS for Intel I211 Ethernet Controller
	bpf: Fix masking negation logic upon negative dst register
	bpf: Fix leakage of uninitialized bpf stack under speculation
	net: qrtr: Avoid potential use after free in MHI send
	perf data: Fix error return code in perf_data__create_dir()
	capabilities: require CAP_SETFCAP to map uid 0
	perf ftrace: Fix access to pid in array when setting a pid filter
	tools/cgroup/slabinfo.py: updated to work on current kernel
	driver core: add a min_align_mask field to struct device_dma_parameters
	swiotlb: add a IO_TLB_SIZE define
	swiotlb: factor out an io_tlb_offset helper
	swiotlb: factor out a nr_slots helper
	swiotlb: clean up swiotlb_tbl_unmap_single
	swiotlb: refactor swiotlb_tbl_map_single
	swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single
	swiotlb: respect min_align_mask
	nvme-pci: set min_align_mask
	ovl: fix leaked dentry
	ovl: allow upperdir inside lowerdir
	ALSA: usb-audio: Add MIDI quirk for Vox ToneLab EX
	USB: Add LPM quirk for Lenovo ThinkPad USB-C Dock Gen2 Ethernet
	USB: Add reset-resume quirk for WD19's Realtek Hub
	platform/x86: thinkpad_acpi: Correct thermal sensor allocation
	perf/core: Fix unconditional security_locked_down() call
	vfio: Depend on MMU
	Linux 5.10.35

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Iff7d5abe7b821f453bbe4d9dad94dfd35fe0a082

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 34
+SUBLEVEL = 35
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/mips/include/asm/vdso/gettimeofday.h

@@ -20,6 +20,12 @@
 
 #define VDSO_HAS_CLOCK_GETRES		1
 
+#if MIPS_ISA_REV < 6
+#define VDSO_SYSCALL_CLOBBERS "hi", "lo",
+#else
+#define VDSO_SYSCALL_CLOBBERS
+#endif
+
 static __always_inline long gettimeofday_fallback(
 				struct __kernel_old_timeval *_tv,
 				struct timezone *_tz)
@@ -35,7 +41,9 @@ static __always_inline long gettimeofday_fallback(
 	: "=r" (ret), "=r" (error)
 	: "r" (tv), "r" (tz), "r" (nr)
 	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
+	  "$14", "$15", "$24", "$25",
+	  VDSO_SYSCALL_CLOBBERS
+	  "memory");
 
 	return error ? -ret : ret;
 }
@@ -59,7 +67,9 @@ static __always_inline long clock_gettime_fallback(
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
 	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
+	  "$14", "$15", "$24", "$25",
+	  VDSO_SYSCALL_CLOBBERS
+	  "memory");
 
 	return error ? -ret : ret;
 }
@@ -83,7 +93,9 @@ static __always_inline int clock_getres_fallback(
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
 	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
+	  "$14", "$15", "$24", "$25",
+	  VDSO_SYSCALL_CLOBBERS
+	  "memory");
 
 	return error ? -ret : ret;
 }
@@ -105,7 +117,9 @@ static __always_inline long clock_gettime32_fallback(
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
 	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
+	  "$14", "$15", "$24", "$25",
+	  VDSO_SYSCALL_CLOBBERS
+	  "memory");
 
 	return error ? -ret : ret;
 }
@@ -125,7 +139,9 @@ static __always_inline int clock_getres32_fallback(
 	: "=r" (ret), "=r" (error)
 	: "r" (clkid), "r" (ts), "r" (nr)
 	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
+	  "$14", "$15", "$24", "$25",
+	  VDSO_SYSCALL_CLOBBERS
+	  "memory");
 
 	return error ? -ret : ret;
 }

drivers/net/ethernet/intel/igb/igb_main.c

@@ -4482,8 +4482,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
 		else
 			mrqc |= E1000_MRQC_ENABLE_VMDQ;
 	} else {
-		if (hw->mac.type != e1000_i211)
+		mrqc |= E1000_MRQC_ENABLE_RSS_MQ;
-			mrqc |= E1000_MRQC_ENABLE_RSS_MQ;
 	}
 	igb_vmm_control(adapter);
 

drivers/net/usb/ax88179_178a.c

@@ -296,12 +296,12 @@ static int ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 	int ret;
 
 	if (2 == size) {
-		u16 buf;
+		u16 buf = 0;
 		ret = __ax88179_read_cmd(dev, cmd, value, index, size, &buf, 0);
 		le16_to_cpus(&buf);
 		*((u16 *)data) = buf;
 	} else if (4 == size) {
-		u32 buf;
+		u32 buf = 0;
 		ret = __ax88179_read_cmd(dev, cmd, value, index, size, &buf, 0);
 		le32_to_cpus(&buf);
 		*((u32 *)data) = buf;
@@ -1296,6 +1296,8 @@ static void ax88179_get_mac_addr(struct usbnet *dev)
 {
 	u8 mac[ETH_ALEN];
 
+	memset(mac, 0, sizeof(mac));
+
 	/* Maybe the boot loader passed the MAC address via device tree */
 	if (!eth_platform_get_mac_address(&dev->udev->dev, mac)) {
 		netif_dbg(dev, ifup, dev->net,

drivers/nvme/host/pci.c

@@ -2634,6 +2634,7 @@ static void nvme_reset_work(struct work_struct *work)
 	 * Don't limit the IOMMU merged segment size.
 	 */
 	dma_set_max_seg_size(dev->dev, 0xffffffff);
+	dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1);
 
 	mutex_unlock(&dev->shutdown_lock);
 

drivers/platform/x86/thinkpad_acpi.c

@@ -6258,6 +6258,7 @@ enum thermal_access_mode {
 enum { /* TPACPI_THERMAL_TPEC_* */
 	TP_EC_THERMAL_TMP0 = 0x78,	/* ACPI EC regs TMP 0..7 */
 	TP_EC_THERMAL_TMP8 = 0xC0,	/* ACPI EC regs TMP 8..15 */
+	TP_EC_FUNCREV      = 0xEF,      /* ACPI EC Functional revision */
 	TP_EC_THERMAL_TMP_NA = -128,	/* ACPI EC sensor not available */
 
 	TPACPI_THERMAL_SENSOR_NA = -128000, /* Sensor not available */
@@ -6456,7 +6457,7 @@ static const struct attribute_group thermal_temp_input8_group = {
 
 static int __init thermal_init(struct ibm_init_struct *iibm)
 {
-	u8 t, ta1, ta2;
+	u8 t, ta1, ta2, ver = 0;
 	int i;
 	int acpi_tmp7;
 	int res;
@@ -6471,7 +6472,14 @@ static int __init thermal_init(struct ibm_init_struct *iibm)
 		 * 0x78-0x7F, 0xC0-0xC7.  Registers return 0x00 for
 		 * non-implemented, thermal sensors return 0x80 when
 		 * not available
+		 * The above rule is unfortunately flawed. This has been seen with
+		 * 0xC2 (power supply ID) causing thermal control problems.
+		 * The EC version can be determined by offset 0xEF and at least for
+		 * version 3 the Lenovo firmware team confirmed that registers 0xC0-0xC7
+		 * are not thermal registers.
 		 */
+		if (!acpi_ec_read(TP_EC_FUNCREV, &ver))
+			pr_warn("Thinkpad ACPI EC unable to access EC version\n");
 
 		ta1 = ta2 = 0;
 		for (i = 0; i < 8; i++) {
@@ -6481,11 +6489,13 @@ static int __init thermal_init(struct ibm_init_struct *iibm)
 				ta1 = 0;
 				break;
 			}
-			if (acpi_ec_read(TP_EC_THERMAL_TMP8 + i, &t)) {
+			if (ver < 3) {
-				ta2 |= t;
+				if (acpi_ec_read(TP_EC_THERMAL_TMP8 + i, &t)) {
-			} else {
+					ta2 |= t;
-				ta1 = 0;
+				} else {
-				break;
+					ta1 = 0;
+					break;
+				}
 			}
 		}
 		if (ta1 == 0) {
@@ -6498,9 +6508,12 @@ static int __init thermal_init(struct ibm_init_struct *iibm)
 				thermal_read_mode = TPACPI_THERMAL_NONE;
 			}
 		} else {
-			thermal_read_mode =
+			if (ver >= 3)
-			    (ta2 != 0) ?
+				thermal_read_mode = TPACPI_THERMAL_TPEC_8;
-			    TPACPI_THERMAL_TPEC_16 : TPACPI_THERMAL_TPEC_8;
+			else
+				thermal_read_mode =
+					(ta2 != 0) ?
+					TPACPI_THERMAL_TPEC_16 : TPACPI_THERMAL_TPEC_8;
 		}
 	} else if (acpi_tmp7) {
 		if (tpacpi_is_ibm() &&

drivers/usb/core/quirks.c

@@ -406,6 +406,7 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	/* Realtek hub in Dell WD19 (Type-C) */
 	{ USB_DEVICE(0x0bda, 0x0487), .driver_info = USB_QUIRK_NO_LPM },
+	{ USB_DEVICE(0x0bda, 0x5487), .driver_info = USB_QUIRK_RESET_RESUME },
 
 	/* Generic RTL8153 based ethernet adapters */
 	{ USB_DEVICE(0x0bda, 0x8153), .driver_info = USB_QUIRK_NO_LPM },
@@ -438,6 +439,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x17ef, 0xa012), .driver_info =
 			USB_QUIRK_DISCONNECT_SUSPEND },
 
+	/* Lenovo ThinkPad USB-C Dock Gen2 Ethernet (RTL8153 GigE) */
+	{ USB_DEVICE(0x17ef, 0xa387), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* BUILDWIN Photo Frame */
 	{ USB_DEVICE(0x1908, 0x1315), .driver_info =
 			USB_QUIRK_HONOR_BNUMINTERFACES },

drivers/vfio/Kconfig

@@ -22,7 +22,7 @@ config VFIO_VIRQFD
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	select IOMMU_API
-	select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
+	select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/driver-api/vfio.rst for more details.

fs/overlayfs/namei.c

@@ -914,6 +914,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			continue;
 
 		if ((uppermetacopy || d.metacopy) && !ofs->config.metacopy) {
+			dput(this);
 			err = -EPERM;
 			pr_warn_ratelimited("refusing to follow metacopy origin for (%pd2)\n", dentry);
 			goto out_put;

fs/overlayfs/super.c

@@ -1782,7 +1782,8 @@ out_err:
  * - upper/work dir of any overlayfs instance
  */
 static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs,
-			   struct dentry *dentry, const char *name)
+			   struct dentry *dentry, const char *name,
+			   bool is_lower)
 {
 	struct dentry *next = dentry, *parent;
 	int err = 0;
@@ -1794,7 +1795,7 @@ static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs,
 
 	/* Walk back ancestors to root (inclusive) looking for traps */
 	while (!err && parent != next) {
-		if (ovl_lookup_trap_inode(sb, parent)) {
+		if (is_lower && ovl_lookup_trap_inode(sb, parent)) {
 			err = -ELOOP;
 			pr_err("overlapping %s path\n", name);
 		} else if (ovl_is_inuse(parent)) {
@@ -1820,7 +1821,7 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
 
 	if (ovl_upper_mnt(ofs)) {
 		err = ovl_check_layer(sb, ofs, ovl_upper_mnt(ofs)->mnt_root,
-				      "upperdir");
+				      "upperdir", false);
 		if (err)
 			return err;
 
@@ -1831,7 +1832,8 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
 		 * workbasedir.  In that case, we already have their traps in
 		 * inode cache and we will catch that case on lookup.
 		 */
-		err = ovl_check_layer(sb, ofs, ofs->workbasedir, "workdir");
+		err = ovl_check_layer(sb, ofs, ofs->workbasedir, "workdir",
+				      false);
 		if (err)
 			return err;
 	}
@@ -1839,7 +1841,7 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
 	for (i = 1; i < ofs->numlayer; i++) {
 		err = ovl_check_layer(sb, ofs,
 				      ofs->layers[i].mnt->mnt_root,
-				      "lowerdir");
+				      "lowerdir", true);
 		if (err)
 			return err;
 	}

include/linux/bpf_verifier.h

@@ -291,10 +291,11 @@ struct bpf_verifier_state_list {
 };
 
 /* Possible states for alu_state member. */
-#define BPF_ALU_SANITIZE_SRC		1U
+#define BPF_ALU_SANITIZE_SRC		(1U << 0)
-#define BPF_ALU_SANITIZE_DST		2U
+#define BPF_ALU_SANITIZE_DST		(1U << 1)
 #define BPF_ALU_NEG_VALUE		(1U << 2)
 #define BPF_ALU_NON_POINTER		(1U << 3)
+#define BPF_ALU_IMMEDIATE		(1U << 4)
 #define BPF_ALU_SANITIZE		(BPF_ALU_SANITIZE_SRC | \
 					 BPF_ALU_SANITIZE_DST)
 

include/linux/device.h

@@ -291,6 +291,7 @@ struct device_dma_parameters {
 	 * sg limitations.
 	 */
 	unsigned int max_segment_size;
+	unsigned int min_align_mask;
 	unsigned long segment_boundary_mask;
 };
 

include/linux/dma-mapping.h

@@ -517,6 +517,22 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
 	return -EIO;
 }
 
+static inline unsigned int dma_get_min_align_mask(struct device *dev)
+{
+	if (dev->dma_parms)
+		return dev->dma_parms->min_align_mask;
+	return 0;
+}
+
+static inline int dma_set_min_align_mask(struct device *dev,
+		unsigned int min_align_mask)
+{
+	if (WARN_ON_ONCE(!dev->dma_parms))
+		return -EIO;
+	dev->dma_parms->min_align_mask = min_align_mask;
+	return 0;
+}
+
 static inline int dma_get_cache_alignment(void)
 {
 #ifdef ARCH_DMA_MINALIGN

include/linux/swiotlb.h

@@ -29,6 +29,7 @@ enum swiotlb_force {
  * controllable.
  */
 #define IO_TLB_SHIFT 11
+#define IO_TLB_SIZE (1 << IO_TLB_SHIFT)
 
 extern void swiotlb_init(int verbose);
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);

include/linux/user_namespace.h

@@ -65,6 +65,9 @@ struct user_namespace {
 	kgid_t			group;
 	struct ns_common	ns;
 	unsigned long		flags;
+	/* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP
+	 * in its effective capability set at the child ns creation time. */
+	bool			parent_could_setfcap;
 
 #ifdef CONFIG_KEYS
 	/* List of joinable keyrings in this namespace.  Modification access of

include/uapi/linux/capability.h

@@ -333,7 +333,8 @@ struct vfs_ns_cap_data {
 
 #define CAP_AUDIT_CONTROL    30
 
-/* Set or remove capabilities on files */
+/* Set or remove capabilities on files.
+   Map uid=0 into a child user namespace. */
 
 #define CAP_SETFCAP	     31
 

kernel/bpf/verifier.c

@@ -5755,6 +5755,7 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 {
 	struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
 	struct bpf_verifier_state *vstate = env->cur_state;
+	bool off_is_imm = tnum_is_const(off_reg->var_off);
 	bool off_is_neg = off_reg->smin_value < 0;
 	bool ptr_is_dst_reg = ptr_reg == dst_reg;
 	u8 opcode = BPF_OP(insn->code);
@@ -5785,6 +5786,7 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 		alu_limit = abs(tmp_aux->alu_limit - alu_limit);
 	} else {
 		alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+		alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
 		alu_state |= ptr_is_dst_reg ?
 			     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
 	}
@@ -11383,7 +11385,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
 			struct bpf_insn insn_buf[16];
 			struct bpf_insn *patch = &insn_buf[0];
-			bool issrc, isneg;
+			bool issrc, isneg, isimm;
 			u32 off_reg;
 
 			aux = &env->insn_aux_data[i + delta];
@@ -11394,28 +11396,29 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
 			issrc = (aux->alu_state & BPF_ALU_SANITIZE) ==
 				BPF_ALU_SANITIZE_SRC;
+			isimm = aux->alu_state & BPF_ALU_IMMEDIATE;
 
 			off_reg = issrc ? insn->src_reg : insn->dst_reg;
-			if (isneg)
+			if (isimm) {
-				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+				*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
-			*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
-			*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
-			*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
-			*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
-			*patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
-			if (issrc) {
-				*patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX,
-							 off_reg);
-				insn->src_reg = BPF_REG_AX;
 			} else {
-				*patch++ = BPF_ALU64_REG(BPF_AND, off_reg,
+				if (isneg)
-							 BPF_REG_AX);
+					*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+				*patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
+				*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
+				*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
+				*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
+				*patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
+				*patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg);
 			}
+			if (!issrc)
+				*patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg);
+			insn->src_reg = BPF_REG_AX;
 			if (isneg)
 				insn->code = insn->code == code_add ?
 					     code_sub : code_add;
 			*patch++ = *insn;
-			if (issrc && isneg)
+			if (issrc && isneg && !isimm)
 				*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
 			cnt = patch - insn_buf;
 

kernel/dma/swiotlb.c

@@ -50,9 +50,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/swiotlb.h>
 
-#define OFFSET(val,align) ((unsigned long)	\
-	                   ( (val) & ( (align) - 1)))
-
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 
 /*
@@ -176,6 +173,16 @@ void swiotlb_print_info(void)
 	       bytes >> 20);
 }
 
+static inline unsigned long io_tlb_offset(unsigned long val)
+{
+	return val & (IO_TLB_SEGSIZE - 1);
+}
+
+static inline unsigned long nr_slots(u64 val)
+{
+	return DIV_ROUND_UP(val, IO_TLB_SIZE);
+}
+
 /*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to
@@ -225,7 +232,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 		      __func__, alloc_size, PAGE_SIZE);
 
 	for (i = 0; i < io_tlb_nslabs; i++) {
-		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
@@ -359,7 +366,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 		goto cleanup4;
 
 	for (i = 0; i < io_tlb_nslabs; i++) {
-		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
@@ -445,19 +452,119 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+#define slot_addr(start, idx)	((start) + ((idx) << IO_TLB_SHIFT))
+
+/*
+ * Return the offset into a iotlb slot required to keep the device happy.
+ */
+static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+{
+	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+}
+
+/*
+ * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
+ */
+static inline unsigned long get_max_slots(unsigned long boundary_mask)
+{
+	if (boundary_mask == ~0UL)
+		return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+	return nr_slots(boundary_mask + 1);
+}
+
+static unsigned int wrap_index(unsigned int index)
+{
+	if (index >= io_tlb_nslabs)
+		return 0;
+	return index;
+}
+
+/*
+ * Find a suitable number of IO TLB entries size that will fit this request and
+ * allocate a buffer from that IO TLB pool.
+ */
+static int find_slots(struct device *dev, phys_addr_t orig_addr,
+		size_t alloc_size)
+{
+	unsigned long boundary_mask = dma_get_seg_boundary(dev);
+	dma_addr_t tbl_dma_addr =
+		phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask;
+	unsigned long max_slots = get_max_slots(boundary_mask);
+	unsigned int iotlb_align_mask =
+		dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+	unsigned int nslots = nr_slots(alloc_size), stride;
+	unsigned int index, wrap, count = 0, i;
+	unsigned long flags;
+
+	BUG_ON(!nslots);
+
+	/*
+	 * For mappings with an alignment requirement don't bother looping to
+	 * unaligned slots once we found an aligned one.  For allocations of
+	 * PAGE_SIZE or larger only look for page aligned allocations.
+	 */
+	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
+	if (alloc_size >= PAGE_SIZE)
+		stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
+
+	spin_lock_irqsave(&io_tlb_lock, flags);
+	if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
+		goto not_found;
+
+	index = wrap = wrap_index(ALIGN(io_tlb_index, stride));
+	do {
+		if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
+		    (orig_addr & iotlb_align_mask)) {
+			index = wrap_index(index + 1);
+			continue;
+		}
+
+		/*
+		 * If we find a slot that indicates we have 'nslots' number of
+		 * contiguous buffers, we allocate the buffers from that slot
+		 * and mark the entries as '0' indicating unavailable.
+		 */
+		if (!iommu_is_span_boundary(index, nslots,
+					    nr_slots(tbl_dma_addr),
+					    max_slots)) {
+			if (io_tlb_list[index] >= nslots)
+				goto found;
+		}
+		index = wrap_index(index + stride);
+	} while (index != wrap);
+
+not_found:
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return -1;
+
+found:
+	for (i = index; i < index + nslots; i++)
+		io_tlb_list[i] = 0;
+	for (i = index - 1;
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
+	     io_tlb_list[i]; i--)
+		io_tlb_list[i] = ++count;
+
+	/*
+	 * Update the indices to avoid searching in the next round.
+	 */
+	if (index + nslots < io_tlb_nslabs)
+		io_tlb_index = index + nslots;
+	else
+		io_tlb_index = 0;
+	io_tlb_used += nslots;
+
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+	return index;
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		size_t mapping_size, size_t alloc_size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
+	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
-	unsigned long flags;
+	unsigned int index, i;
 	phys_addr_t tlb_addr;
-	unsigned int nslots, stride, index, wrap;
-	int i;
-	unsigned long mask;
-	unsigned long offset_slots;
-	unsigned long max_slots;
-	unsigned long tmp_io_tlb_used;
 
 	if (no_iotlb_memory)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
@@ -466,111 +573,32 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
 		pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
 
 	if (mapping_size > alloc_size) {
-		dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+		dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
 			      mapping_size, alloc_size);
 		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
 
-	mask = dma_get_seg_boundary(hwdev);
+	index = find_slots(dev, orig_addr, alloc_size + offset);
-
+	if (index == -1) {
-	tbl_dma_addr &= mask;
+		if (!(attrs & DMA_ATTR_NO_WARN))
-
+			dev_warn_ratelimited(dev,
-	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-
+				 alloc_size, io_tlb_nslabs, io_tlb_used);
-	/*
+		return (phys_addr_t)DMA_MAPPING_ERROR;
-	 * Carefully handle integer overflow which can occur when mask == ~0UL.
+	}
-	 */
-	max_slots = mask + 1
-		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
-		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
-
-	/*
-	 * For mappings greater than or equal to a page, we limit the stride
-	 * (and hence alignment) to a page size.
-	 */
-	nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (alloc_size >= PAGE_SIZE)
-		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
-	else
-		stride = 1;
-
-	BUG_ON(!nslots);
-
-	/*
-	 * Find suitable number of IO TLB entries size that will fit this
-	 * request and allocate a buffer from that IO TLB pool.
-	 */
-	spin_lock_irqsave(&io_tlb_lock, flags);
-
-	if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
-		goto not_found;
-
-	index = ALIGN(io_tlb_index, stride);
-	if (index >= io_tlb_nslabs)
-		index = 0;
-	wrap = index;
-
-	do {
-		while (iommu_is_span_boundary(index, nslots, offset_slots,
-					      max_slots)) {
-			index += stride;
-			if (index >= io_tlb_nslabs)
-				index = 0;
-			if (index == wrap)
-				goto not_found;
-		}
-
-		/*
-		 * If we find a slot that indicates we have 'nslots' number of
-		 * contiguous buffers, we allocate the buffers from that slot
-		 * and mark the entries as '0' indicating unavailable.
-		 */
-		if (io_tlb_list[index] >= nslots) {
-			int count = 0;
-
-			for (i = index; i < (int) (index + nslots); i++)
-				io_tlb_list[i] = 0;
-			for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
-				io_tlb_list[i] = ++count;
-			tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
-			/*
-			 * Update the indices to avoid searching in the next
-			 * round.
-			 */
-			io_tlb_index = ((index + nslots) < io_tlb_nslabs
-					? (index + nslots) : 0);
-
-			goto found;
-		}
-		index += stride;
-		if (index >= io_tlb_nslabs)
-			index = 0;
-	} while (index != wrap);
-
-not_found:
-	tmp_io_tlb_used = io_tlb_used;
-
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
-	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
-		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-			 alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
-	return (phys_addr_t)DMA_MAPPING_ERROR;
-found:
-	io_tlb_used += nslots;
-	spin_unlock_irqrestore(&io_tlb_lock, flags);
 
 	/*
 	 * Save away the mapping from the original address to the DMA address.
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
-	for (i = 0; i < nslots; i++)
+	for (i = 0; i < nr_slots(alloc_size + offset); i++)
-		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
+		io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
+
+	tlb_addr = slot_addr(io_tlb_start, index) + offset;
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
 		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
-
 	return tlb_addr;
 }
 
@@ -582,8 +610,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 			      enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long flags;
-	int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr);
-	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	int i, count, nslots = nr_slots(alloc_size + offset);
+	int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
 	/*
@@ -601,26 +630,29 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * with slots below and above the pool being returned.
 	 */
 	spin_lock_irqsave(&io_tlb_lock, flags);
-	{
+	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
-		count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
+		count = io_tlb_list[index + nslots];
-			 io_tlb_list[index + nslots] : 0);
+	else
-		/*
+		count = 0;
-		 * Step 1: return the slots to the free list, merging the
-		 * slots with superceeding slots
-		 */
-		for (i = index + nslots - 1; i >= index; i--) {
-			io_tlb_list[i] = ++count;
-			io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
-		}
-		/*
-		 * Step 2: merge the returned slots with the preceding slots,
-		 * if available (non zero)
-		 */
-		for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
-			io_tlb_list[i] = ++count;
 
-		io_tlb_used -= nslots;
+	/*
+	 * Step 1: return the slots to the free list, merging the slots with
+	 * superceeding slots
+	 */
+	for (i = index + nslots - 1; i >= index; i--) {
+		io_tlb_list[i] = ++count;
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
+
+	/*
+	 * Step 2: merge the returned slots with the preceding slots, if
+	 * available (non zero)
+	 */
+	for (i = index - 1;
+	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i];
+	     i--)
+		io_tlb_list[i] = ++count;
+	io_tlb_used -= nslots;
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 }
 
@@ -633,7 +665,6 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 
 	if (orig_addr == INVALID_PHYS_ADDR)
 		return;
-	orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
 
 	switch (target) {
 	case SYNC_FOR_CPU:
@@ -691,7 +722,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 
 size_t swiotlb_max_mapping_size(struct device *dev)
 {
-	return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE;
+	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
 }
 
 bool is_swiotlb_active(void)

kernel/events/core.c

@@ -11706,12 +11706,12 @@ SYSCALL_DEFINE5(perf_event_open,
 			return err;
 	}
 
-	err = security_locked_down(LOCKDOWN_PERF);
+	/* REGS_INTR can leak data, lockdown must prevent this */
-	if (err && (attr.sample_type & PERF_SAMPLE_REGS_INTR))
+	if (attr.sample_type & PERF_SAMPLE_REGS_INTR) {
-		/* REGS_INTR can leak data, lockdown must prevent this */
+		err = security_locked_down(LOCKDOWN_PERF);
-		return err;
+		if (err)
-
+			return err;
-	err = 0;
+	}
 
 	/*
 	 * In cgroup mode, the pid argument is used to pass the fd

kernel/user_namespace.c

@@ -106,6 +106,7 @@ int create_user_ns(struct cred *new)
 	if (!ns)
 		goto fail_dec;
 
+	ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP);
 	ret = ns_alloc_inum(&ns->ns);
 	if (ret)
 		goto fail_free;
@@ -841,6 +842,60 @@ static int sort_idmaps(struct uid_gid_map *map)
 	return 0;
 }
 
+/**
+ * verify_root_map() - check the uid 0 mapping
+ * @file: idmapping file
+ * @map_ns: user namespace of the target process
+ * @new_map: requested idmap
+ *
+ * If a process requests mapping parent uid 0 into the new ns, verify that the
+ * process writing the map had the CAP_SETFCAP capability as the target process
+ * will be able to write fscaps that are valid in ancestor user namespaces.
+ *
+ * Return: true if the mapping is allowed, false if not.
+ */
+static bool verify_root_map(const struct file *file,
+			    struct user_namespace *map_ns,
+			    struct uid_gid_map *new_map)
+{
+	int idx;
+	const struct user_namespace *file_ns = file->f_cred->user_ns;
+	struct uid_gid_extent *extent0 = NULL;
+
+	for (idx = 0; idx < new_map->nr_extents; idx++) {
+		if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+			extent0 = &new_map->extent[idx];
+		else
+			extent0 = &new_map->forward[idx];
+		if (extent0->lower_first == 0)
+			break;
+
+		extent0 = NULL;
+	}
+
+	if (!extent0)
+		return true;
+
+	if (map_ns == file_ns) {
+		/* The process unshared its ns and is writing to its own
+		 * /proc/self/uid_map.  User already has full capabilites in
+		 * the new namespace.  Verify that the parent had CAP_SETFCAP
+		 * when it unshared.
+		 * */
+		if (!file_ns->parent_could_setfcap)
+			return false;
+	} else {
+		/* Process p1 is writing to uid_map of p2, who is in a child
+		 * user namespace to p1's.  Verify that the opener of the map
+		 * file has CAP_SETFCAP against the parent of the new map
+		 * namespace */
+		if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP))
+			return false;
+	}
+
+	return true;
+}
+
 static ssize_t map_write(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos,
 			 int cap_setid,
@@ -848,7 +903,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 			 struct uid_gid_map *parent_map)
 {
 	struct seq_file *seq = file->private_data;
-	struct user_namespace *ns = seq->private;
+	struct user_namespace *map_ns = seq->private;
 	struct uid_gid_map new_map;
 	unsigned idx;
 	struct uid_gid_extent extent;
@@ -895,7 +950,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	/*
 	 * Adjusting namespace settings requires capabilities on the target.
 	 */
-	if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
+	if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN))
 		goto out;
 
 	/* Parse the user data */
@@ -965,7 +1020,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 
 	ret = -EPERM;
 	/* Validate the user is allowed to use user id's mapped to. */
-	if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
+	if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map))
 		goto out;
 
 	ret = -EPERM;
@@ -1086,6 +1141,10 @@ static bool new_idmap_permitted(const struct file *file,
 				struct uid_gid_map *new_map)
 {
 	const struct cred *cred = file->f_cred;
+
+	if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map))
+		return false;
+
 	/* Don't allow mappings that would allow anything that wouldn't
 	 * be allowed without the establishment of unprivileged mappings.
 	 */

net/netfilter/nf_conntrack_standalone.c

@@ -1060,16 +1060,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 	nf_conntrack_standalone_init_dccp_sysctl(net, table);
 	nf_conntrack_standalone_init_gre_sysctl(net, table);
 
-	/* Don't allow unprivileged users to alter certain sysctls */
+	/* Don't allow non-init_net ns to alter global sysctls */
-	if (net->user_ns != &init_user_ns) {
+	if (!net_eq(&init_net, net)) {
 		table[NF_SYSCTL_CT_MAX].mode = 0444;
 		table[NF_SYSCTL_CT_EXPECT_MAX].mode = 0444;
-		table[NF_SYSCTL_CT_HELPER].mode = 0444;
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-		table[NF_SYSCTL_CT_EVENTS].mode = 0444;
-#endif
-		table[NF_SYSCTL_CT_BUCKETS].mode = 0444;
-	} else if (!net_eq(&init_net, net)) {
 		table[NF_SYSCTL_CT_BUCKETS].mode = 0444;
 	}
 

net/qrtr/mhi.c

@@ -50,6 +50,9 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
 	struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep);
 	int rc;
 
+	if (skb->sk)
+		sock_hold(skb->sk);
+
 	rc = skb_linearize(skb);
 	if (rc)
 		goto free_skb;
@@ -59,12 +62,11 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
 	if (rc)
 		goto free_skb;
 
-	if (skb->sk)
-		sock_hold(skb->sk);
-
 	return rc;
 
 free_skb:
+	if (skb->sk)
+		sock_put(skb->sk);
 	kfree_skb(skb);
 
 	return rc;

sound/usb/quirks-table.h

@@ -2376,6 +2376,16 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 	}
 },
 
+{
+	USB_DEVICE_VENDOR_SPEC(0x0944, 0x0204),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "KORG, Inc.",
+		/* .product_name = "ToneLab EX", */
+		.ifnum = 3,
+		.type = QUIRK_MIDI_STANDARD_INTERFACE,
+	}
+},
+
 /* AKAI devices */
 {
 	USB_DEVICE(0x09e8, 0x0062),

tools/cgroup/memcg_slabinfo.py

@@ -128,9 +128,9 @@ def detect_kernel_config():
 
     cfg['nr_nodes'] = prog['nr_online_nodes'].value_()
 
-    if prog.type('struct kmem_cache').members[1][1] == 'flags':
+    if prog.type('struct kmem_cache').members[1].name == 'flags':
         cfg['allocator'] = 'SLUB'
-    elif prog.type('struct kmem_cache').members[1][1] == 'batchcount':
+    elif prog.type('struct kmem_cache').members[1].name == 'batchcount':
         cfg['allocator'] = 'SLAB'
     else:
         err('Can\'t determine the slab allocator')
@@ -193,7 +193,7 @@ def main():
         # look over all slab pages, belonging to non-root memcgs
         # and look for objects belonging to the given memory cgroup
         for page in for_each_slab_page(prog):
-            objcg_vec_raw = page.obj_cgroups.value_()
+            objcg_vec_raw = page.memcg_data.value_()
             if objcg_vec_raw == 0:
                 continue
             cache = page.slab_cache
@@ -202,7 +202,7 @@ def main():
             addr = cache.value_()
             caches[addr] = cache
             # clear the lowest bit to get the true obj_cgroups
-            objcg_vec = Object(prog, page.obj_cgroups.type_,
+            objcg_vec = Object(prog, 'struct obj_cgroup **',
                                value=objcg_vec_raw & ~1)
 
             if addr not in stats:

tools/perf/builtin-ftrace.c

@@ -289,7 +289,7 @@ static int set_tracing_pid(struct perf_ftrace *ftrace)
 
 	for (i = 0; i < perf_thread_map__nr(ftrace->evlist->core.threads); i++) {
 		scnprintf(buf, sizeof(buf), "%d",
-			  ftrace->evlist->core.threads->map[i]);
+			  perf_thread_map__pid(ftrace->evlist->core.threads, i));
 		if (append_tracing_file("set_ftrace_pid", buf) < 0)
 			return -1;
 	}

tools/perf/util/data.c

@@ -35,7 +35,7 @@ void perf_data__close_dir(struct perf_data *data)
 int perf_data__create_dir(struct perf_data *data, int nr)
 {
 	struct perf_data_file *files = NULL;
-	int i, ret = -1;
+	int i, ret;
 
 	if (WARN_ON(!data->is_dir))
 		return -EINVAL;
@@ -51,7 +51,8 @@ int perf_data__create_dir(struct perf_data *data, int nr)
 	for (i = 0; i < nr; i++) {
 		struct perf_data_file *file = &files[i];
 
-		if (asprintf(&file->path, "%s/data.%d", data->path, i) < 0)
+		ret = asprintf(&file->path, "%s/data.%d", data->path, i);
+		if (ret < 0)
 			goto out_err;
 
 		ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);