commit: aad8672f9a4d60a64e628aaf62f88040cda97b4e Author: Mike Pagano <mpagano <AT> gentoo <DOT> org> AuthorDate: Wed Jun 30 14:24:17 2021 +0000 Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org> CommitDate: Wed Jun 30 14:24:17 2021 +0000 URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=aad8672f
Linux patch 5.4.129 Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org> 0000_README | 4 + 1128_linux-5.4.129.patch | 2952 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 2956 insertions(+) diff --git a/0000_README b/0000_README index cb07352..bedf8ea 100644 --- a/0000_README +++ b/0000_README @@ -555,6 +555,10 @@ Patch: 1127_linux-5.4.128.patch From: http://www.kernel.org Desc: Linux 5.4.128 +Patch: 1128_linux-5.4.129.patch +From: http://www.kernel.org +Desc: Linux 5.4.129 + Patch: 1500_XATTR_USER_PREFIX.patch From: https://bugs.gentoo.org/show_bug.cgi?id=470644 Desc: Support for namespace user.pax.* on tmpfs. diff --git a/1128_linux-5.4.129.patch b/1128_linux-5.4.129.patch new file mode 100644 index 0000000..ff82b9f --- /dev/null +++ b/1128_linux-5.4.129.patch @@ -0,0 +1,2952 @@ +diff --git a/Makefile b/Makefile +index 5db87d8031f1e..802520ad08cca 100644 +--- a/Makefile ++++ b/Makefile +@@ -1,7 +1,7 @@ + # SPDX-License-Identifier: GPL-2.0 + VERSION = 5 + PATCHLEVEL = 4 +-SUBLEVEL = 128 ++SUBLEVEL = 129 + EXTRAVERSION = + NAME = Kleptomaniac Octopus + +diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c +index 924285d0bccd9..43d6a6085d862 100644 +--- a/arch/arm/kernel/setup.c ++++ b/arch/arm/kernel/setup.c +@@ -544,9 +544,11 @@ void notrace cpu_init(void) + * In Thumb-2, msr with an immediate value is not allowed. + */ + #ifdef CONFIG_THUMB2_KERNEL +-#define PLC "r" ++#define PLC_l "l" ++#define PLC_r "r" + #else +-#define PLC "I" ++#define PLC_l "I" ++#define PLC_r "I" + #endif + + /* +@@ -568,15 +570,15 @@ void notrace cpu_init(void) + "msr cpsr_c, %9" + : + : "r" (stk), +- PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), ++ PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), + "I" (offsetof(struct stack, irq[0])), +- PLC (PSR_F_BIT | PSR_I_BIT | ABT_MODE), ++ PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE), + "I" (offsetof(struct stack, abt[0])), +- PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE), ++ PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE), + "I" (offsetof(struct stack, und[0])), +- PLC (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), ++ PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), + "I" (offsetof(struct stack, fiq[0])), +- PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE) ++ PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE) + : "r14"); + #endif + } +diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile +index cd8f3cdabfd07..d227cf87c48f3 100644 +--- a/arch/arm64/Makefile ++++ b/arch/arm64/Makefile +@@ -10,7 +10,7 @@ + # + # Copyright (C) 1995-2001 by Russell King + +-LDFLAGS_vmlinux :=--no-undefined -X -z norelro ++LDFLAGS_vmlinux :=--no-undefined -X + CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) + GZFLAGS :=-9 + +@@ -82,17 +82,21 @@ CHECKFLAGS += -D__AARCH64EB__ + AS += -EB + # Prefer the baremetal ELF build target, but not all toolchains include + # it so fall back to the standard linux version if needed. +-KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb) ++KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro) + UTS_MACHINE := aarch64_be + else + KBUILD_CPPFLAGS += -mlittle-endian + CHECKFLAGS += -D__AARCH64EL__ + AS += -EL + # Same as above, prefer ELF but fall back to linux target if needed. +-KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux) ++KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro) + UTS_MACHINE := aarch64 + endif + ++ifeq ($(CONFIG_LD_IS_LLD), y) ++KBUILD_LDFLAGS += -z norelro ++endif ++ + CHECKFLAGS += -D__aarch64__ + + ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) +diff --git a/arch/mips/generic/board-boston.its.S b/arch/mips/generic/board-boston.its.S +index a7f51f97b9102..c45ad27594218 100644 +--- a/arch/mips/generic/board-boston.its.S ++++ b/arch/mips/generic/board-boston.its.S +@@ -1,22 +1,22 @@ + / { + images { +- fdt@boston { ++ fdt-boston { + description = "img,boston Device Tree"; + data = /incbin/("boot/dts/img/boston.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; +- hash@0 { ++ hash { + algo = "sha1"; + }; + }; + }; + + configurations { +- conf@boston { ++ conf-boston { + description = "Boston Linux kernel"; +- kernel = "kernel@0"; +- fdt = "fdt@boston"; ++ kernel = "kernel"; ++ fdt = "fdt-boston"; + }; + }; + }; +diff --git a/arch/mips/generic/board-ni169445.its.S b/arch/mips/generic/board-ni169445.its.S +index e4cb4f95a8cc1..0a2e8f7a8526f 100644 +--- a/arch/mips/generic/board-ni169445.its.S ++++ b/arch/mips/generic/board-ni169445.its.S +@@ -1,22 +1,22 @@ + / { + images { +- fdt@ni169445 { ++ fdt-ni169445 { + description = "NI 169445 device tree"; + data = /incbin/("boot/dts/ni/169445.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; +- hash@0 { ++ hash { + algo = "sha1"; + }; + }; + }; + + configurations { +- conf@ni169445 { ++ conf-ni169445 { + description = "NI 169445 Linux Kernel"; +- kernel = "kernel@0"; +- fdt = "fdt@ni169445"; ++ kernel = "kernel"; ++ fdt = "fdt-ni169445"; + }; + }; + }; +diff --git a/arch/mips/generic/board-ocelot.its.S b/arch/mips/generic/board-ocelot.its.S +index 3da23988149a6..8c7e3a1b68d3d 100644 +--- a/arch/mips/generic/board-ocelot.its.S ++++ b/arch/mips/generic/board-ocelot.its.S +@@ -1,40 +1,40 @@ + /* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ + / { + images { +- fdt@ocelot_pcb123 { ++ fdt-ocelot_pcb123 { + description = "MSCC Ocelot PCB123 Device Tree"; + data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; +- hash@0 { ++ hash { + algo = "sha1"; + }; + }; + +- fdt@ocelot_pcb120 { ++ fdt-ocelot_pcb120 { + description = "MSCC Ocelot PCB120 Device Tree"; + data = /incbin/("boot/dts/mscc/ocelot_pcb120.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; +- hash@0 { ++ hash { + algo = "sha1"; + }; + }; + }; + + configurations { +- conf@ocelot_pcb123 { ++ conf-ocelot_pcb123 { + description = "Ocelot Linux kernel"; +- kernel = "kernel@0"; +- fdt = "fdt@ocelot_pcb123"; ++ kernel = "kernel"; ++ fdt = "fdt-ocelot_pcb123"; + }; + +- conf@ocelot_pcb120 { ++ conf-ocelot_pcb120 { + description = "Ocelot Linux kernel"; +- kernel = "kernel@0"; +- fdt = "fdt@ocelot_pcb120"; ++ kernel = "kernel"; ++ fdt = "fdt-ocelot_pcb120"; + }; + }; + }; +diff --git a/arch/mips/generic/board-xilfpga.its.S b/arch/mips/generic/board-xilfpga.its.S +index a2e773d3f14f4..08c1e900eb4ed 100644 +--- a/arch/mips/generic/board-xilfpga.its.S ++++ b/arch/mips/generic/board-xilfpga.its.S +@@ -1,22 +1,22 @@ + / { + images { +- fdt@xilfpga { ++ fdt-xilfpga { + description = "MIPSfpga (xilfpga) Device Tree"; + data = /incbin/("boot/dts/xilfpga/nexys4ddr.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; +- hash@0 { ++ hash { + algo = "sha1"; + }; + }; + }; + + configurations { +- conf@xilfpga { ++ conf-xilfpga { + description = "MIPSfpga Linux kernel"; +- kernel = "kernel@0"; +- fdt = "fdt@xilfpga"; ++ kernel = "kernel"; ++ fdt = "fdt-xilfpga"; + }; + }; + }; +diff --git a/arch/mips/generic/vmlinux.its.S b/arch/mips/generic/vmlinux.its.S +index 1a08438fd8930..3e254676540f4 100644 +--- a/arch/mips/generic/vmlinux.its.S ++++ b/arch/mips/generic/vmlinux.its.S +@@ -6,7 +6,7 @@ + #address-cells = <ADDR_CELLS>; + + images { +- kernel@0 { ++ kernel { + description = KERNEL_NAME; + data = /incbin/(VMLINUX_BINARY); + type = "kernel"; +@@ -15,18 +15,18 @@ + compression = VMLINUX_COMPRESSION; + load = /bits/ ADDR_BITS <VMLINUX_LOAD_ADDRESS>; + entry = /bits/ ADDR_BITS <VMLINUX_ENTRY_ADDRESS>; +- hash@0 { ++ hash { + algo = "sha1"; + }; + }; + }; + + configurations { +- default = "conf@default"; ++ default = "conf-default"; + +- conf@default { ++ conf-default { + description = "Generic Linux kernel"; +- kernel = "kernel@0"; ++ kernel = "kernel"; + }; + }; + }; +diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c +index 0c67a5a94de30..76959a7d88c82 100644 +--- a/arch/x86/pci/fixup.c ++++ b/arch/x86/pci/fixup.c +@@ -779,4 +779,48 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); + DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); + DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); + ++#define RS690_LOWER_TOP_OF_DRAM2 0x30 ++#define RS690_LOWER_TOP_OF_DRAM2_VALID 0x1 ++#define RS690_UPPER_TOP_OF_DRAM2 0x31 ++#define RS690_HTIU_NB_INDEX 0xA8 ++#define RS690_HTIU_NB_INDEX_WR_ENABLE 0x100 ++#define RS690_HTIU_NB_DATA 0xAC ++ ++/* ++ * Some BIOS implementations support RAM above 4GB, but do not configure the ++ * PCI host to respond to bus master accesses for these addresses. These ++ * implementations set the TOP_OF_DRAM_SLOT1 register correctly, so PCI DMA ++ * works as expected for addresses below 4GB. ++ * ++ * Reference: "AMD RS690 ASIC Family Register Reference Guide" (pg. 2-57) ++ * https://www.amd.com/system/files/TechDocs/43372_rs690_rrg_3.00o.pdf ++ */ ++static void rs690_fix_64bit_dma(struct pci_dev *pdev) ++{ ++ u32 val = 0; ++ phys_addr_t top_of_dram = __pa(high_memory - 1) + 1; ++ ++ if (top_of_dram <= (1ULL << 32)) ++ return; ++ ++ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, ++ RS690_LOWER_TOP_OF_DRAM2); ++ pci_read_config_dword(pdev, RS690_HTIU_NB_DATA, &val); ++ ++ if (val) ++ return; ++ ++ pci_info(pdev, "Adjusting top of DRAM to %pa for 64-bit DMA support\n", &top_of_dram); ++ ++ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, ++ RS690_UPPER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE); ++ pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, top_of_dram >> 32); ++ ++ pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, ++ RS690_LOWER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE); ++ pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, ++ top_of_dram | RS690_LOWER_TOP_OF_DRAM2_VALID); ++} ++DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); ++ + #endif +diff --git a/certs/Kconfig b/certs/Kconfig +index c94e93d8bccf0..76e469b56a773 100644 +--- a/certs/Kconfig ++++ b/certs/Kconfig +@@ -83,4 +83,13 @@ config SYSTEM_BLACKLIST_HASH_LIST + wrapper to incorporate the list into the kernel. Each <hash> should + be a string of hex digits. + ++config SYSTEM_REVOCATION_LIST ++ bool "Provide system-wide ring of revocation certificates" ++ depends on SYSTEM_BLACKLIST_KEYRING ++ depends on PKCS7_MESSAGE_PARSER=y ++ help ++ If set, this allows revocation certificates to be stored in the ++ blacklist keyring and implements a hook whereby a PKCS#7 message can ++ be checked to see if it matches such a certificate. ++ + endmenu +diff --git a/certs/Makefile b/certs/Makefile +index f4c25b67aad90..f4b90bad8690a 100644 +--- a/certs/Makefile ++++ b/certs/Makefile +@@ -3,7 +3,7 @@ + # Makefile for the linux kernel signature checking certificates. + # + +-obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o ++obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o + obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o + ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),"") + obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o +diff --git a/certs/blacklist.c b/certs/blacklist.c +index 025a41de28fda..59b2f106b2940 100644 +--- a/certs/blacklist.c ++++ b/certs/blacklist.c +@@ -135,6 +135,58 @@ int is_hash_blacklisted(const u8 *hash, size_t hash_len, const char *type) + } + EXPORT_SYMBOL_GPL(is_hash_blacklisted); + ++int is_binary_blacklisted(const u8 *hash, size_t hash_len) ++{ ++ if (is_hash_blacklisted(hash, hash_len, "bin") == -EKEYREJECTED) ++ return -EPERM; ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(is_binary_blacklisted); ++ ++#ifdef CONFIG_SYSTEM_REVOCATION_LIST ++/** ++ * add_key_to_revocation_list - Add a revocation certificate to the blacklist ++ * @data: The data blob containing the certificate ++ * @size: The size of data blob ++ */ ++int add_key_to_revocation_list(const char *data, size_t size) ++{ ++ key_ref_t key; ++ ++ key = key_create_or_update(make_key_ref(blacklist_keyring, true), ++ "asymmetric", ++ NULL, ++ data, ++ size, ++ ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW), ++ KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN); ++ ++ if (IS_ERR(key)) { ++ pr_err("Problem with revocation key (%ld)\n", PTR_ERR(key)); ++ return PTR_ERR(key); ++ } ++ ++ return 0; ++} ++ ++/** ++ * is_key_on_revocation_list - Determine if the key for a PKCS#7 message is revoked ++ * @pkcs7: The PKCS#7 message to check ++ */ ++int is_key_on_revocation_list(struct pkcs7_message *pkcs7) ++{ ++ int ret; ++ ++ ret = pkcs7_validate_trust(pkcs7, blacklist_keyring); ++ ++ if (ret == 0) ++ return -EKEYREJECTED; ++ ++ return -ENOKEY; ++} ++#endif ++ + /* + * Initialise the blacklist + */ +diff --git a/certs/blacklist.h b/certs/blacklist.h +index 1efd6fa0dc608..51b320cf85749 100644 +--- a/certs/blacklist.h ++++ b/certs/blacklist.h +@@ -1,3 +1,5 @@ + #include <linux/kernel.h> ++#include <linux/errno.h> ++#include <crypto/pkcs7.h> + + extern const char __initconst *const blacklist_hashes[]; +diff --git a/certs/common.c b/certs/common.c +new file mode 100644 +index 0000000000000..16a220887a53e +--- /dev/null ++++ b/certs/common.c +@@ -0,0 +1,57 @@ ++// SPDX-License-Identifier: GPL-2.0-or-later ++ ++#include <linux/kernel.h> ++#include <linux/key.h> ++#include "common.h" ++ ++int load_certificate_list(const u8 cert_list[], ++ const unsigned long list_size, ++ const struct key *keyring) ++{ ++ key_ref_t key; ++ const u8 *p, *end; ++ size_t plen; ++ ++ p = cert_list; ++ end = p + list_size; ++ while (p < end) { ++ /* Each cert begins with an ASN.1 SEQUENCE tag and must be more ++ * than 256 bytes in size. ++ */ ++ if (end - p < 4) ++ goto dodgy_cert; ++ if (p[0] != 0x30 && ++ p[1] != 0x82) ++ goto dodgy_cert; ++ plen = (p[2] << 8) | p[3]; ++ plen += 4; ++ if (plen > end - p) ++ goto dodgy_cert; ++ ++ key = key_create_or_update(make_key_ref(keyring, 1), ++ "asymmetric", ++ NULL, ++ p, ++ plen, ++ ((KEY_POS_ALL & ~KEY_POS_SETATTR) | ++ KEY_USR_VIEW | KEY_USR_READ), ++ KEY_ALLOC_NOT_IN_QUOTA | ++ KEY_ALLOC_BUILT_IN | ++ KEY_ALLOC_BYPASS_RESTRICTION); ++ if (IS_ERR(key)) { ++ pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", ++ PTR_ERR(key)); ++ } else { ++ pr_notice("Loaded X.509 cert '%s'\n", ++ key_ref_to_ptr(key)->description); ++ key_ref_put(key); ++ } ++ p += plen; ++ } ++ ++ return 0; ++ ++dodgy_cert: ++ pr_err("Problem parsing in-kernel X.509 certificate list\n"); ++ return 0; ++} +diff --git a/certs/common.h b/certs/common.h +new file mode 100644 +index 0000000000000..abdb5795936b7 +--- /dev/null ++++ b/certs/common.h +@@ -0,0 +1,9 @@ ++/* SPDX-License-Identifier: GPL-2.0-or-later */ ++ ++#ifndef _CERT_COMMON_H ++#define _CERT_COMMON_H ++ ++int load_certificate_list(const u8 cert_list[], const unsigned long list_size, ++ const struct key *keyring); ++ ++#endif +diff --git a/certs/system_keyring.c b/certs/system_keyring.c +index 798291177186c..a44a8915c94cf 100644 +--- a/certs/system_keyring.c ++++ b/certs/system_keyring.c +@@ -15,6 +15,7 @@ + #include <keys/asymmetric-type.h> + #include <keys/system_keyring.h> + #include <crypto/pkcs7.h> ++#include "common.h" + + static struct key *builtin_trusted_keys; + #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING +@@ -136,54 +137,10 @@ device_initcall(system_trusted_keyring_init); + */ + static __init int load_system_certificate_list(void) + { +- key_ref_t key; +- const u8 *p, *end; +- size_t plen; +- + pr_notice("Loading compiled-in X.509 certificates\n"); + +- p = system_certificate_list; +- end = p + system_certificate_list_size; +- while (p < end) { +- /* Each cert begins with an ASN.1 SEQUENCE tag and must be more +- * than 256 bytes in size. +- */ +- if (end - p < 4) +- goto dodgy_cert; +- if (p[0] != 0x30 && +- p[1] != 0x82) +- goto dodgy_cert; +- plen = (p[2] << 8) | p[3]; +- plen += 4; +- if (plen > end - p) +- goto dodgy_cert; +- +- key = key_create_or_update(make_key_ref(builtin_trusted_keys, 1), +- "asymmetric", +- NULL, +- p, +- plen, +- ((KEY_POS_ALL & ~KEY_POS_SETATTR) | +- KEY_USR_VIEW | KEY_USR_READ), +- KEY_ALLOC_NOT_IN_QUOTA | +- KEY_ALLOC_BUILT_IN | +- KEY_ALLOC_BYPASS_RESTRICTION); +- if (IS_ERR(key)) { +- pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", +- PTR_ERR(key)); +- } else { +- pr_notice("Loaded X.509 cert '%s'\n", +- key_ref_to_ptr(key)->description); +- key_ref_put(key); +- } +- p += plen; +- } +- +- return 0; +- +-dodgy_cert: +- pr_err("Problem parsing in-kernel X.509 certificate list\n"); +- return 0; ++ return load_certificate_list(system_certificate_list, system_certificate_list_size, ++ builtin_trusted_keys); + } + late_initcall(load_system_certificate_list); + +@@ -241,6 +198,12 @@ int verify_pkcs7_message_sig(const void *data, size_t len, + pr_devel("PKCS#7 platform keyring is not available\n"); + goto error; + } ++ ++ ret = is_key_on_revocation_list(pkcs7); ++ if (ret != -ENOKEY) { ++ pr_devel("PKCS#7 platform key is on revocation list\n"); ++ goto error; ++ } + } + ret = pkcs7_validate_trust(pkcs7, trusted_keys); + if (ret < 0) { +diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c +index f40051d6aecbc..9c0ea13ca7883 100644 +--- a/drivers/dma/mediatek/mtk-uart-apdma.c ++++ b/drivers/dma/mediatek/mtk-uart-apdma.c +@@ -131,10 +131,7 @@ static unsigned int mtk_uart_apdma_read(struct mtk_chan *c, unsigned int reg) + + static void mtk_uart_apdma_desc_free(struct virt_dma_desc *vd) + { +- struct dma_chan *chan = vd->tx.chan; +- struct mtk_chan *c = to_mtk_uart_apdma_chan(chan); +- +- kfree(c->desc); ++ kfree(container_of(vd, struct mtk_uart_apdma_desc, vd)); + } + + static void mtk_uart_apdma_start_tx(struct mtk_chan *c) +@@ -207,14 +204,9 @@ static void mtk_uart_apdma_start_rx(struct mtk_chan *c) + + static void mtk_uart_apdma_tx_handler(struct mtk_chan *c) + { +- struct mtk_uart_apdma_desc *d = c->desc; +- + mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B); + mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B); + mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B); +- +- list_del(&d->vd.node); +- vchan_cookie_complete(&d->vd); + } + + static void mtk_uart_apdma_rx_handler(struct mtk_chan *c) +@@ -245,9 +237,17 @@ static void mtk_uart_apdma_rx_handler(struct mtk_chan *c) + + c->rx_status = d->avail_len - cnt; + mtk_uart_apdma_write(c, VFF_RPT, wg); ++} + +- list_del(&d->vd.node); +- vchan_cookie_complete(&d->vd); ++static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c) ++{ ++ struct mtk_uart_apdma_desc *d = c->desc; ++ ++ if (d) { ++ list_del(&d->vd.node); ++ vchan_cookie_complete(&d->vd); ++ c->desc = NULL; ++ } + } + + static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) +@@ -261,6 +261,7 @@ static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) + mtk_uart_apdma_rx_handler(c); + else if (c->dir == DMA_MEM_TO_DEV) + mtk_uart_apdma_tx_handler(c); ++ mtk_uart_apdma_chan_complete_handler(c); + spin_unlock_irqrestore(&c->vc.lock, flags); + + return IRQ_HANDLED; +@@ -348,7 +349,7 @@ static struct dma_async_tx_descriptor *mtk_uart_apdma_prep_slave_sg + return NULL; + + /* Now allocate and setup the descriptor */ +- d = kzalloc(sizeof(*d), GFP_ATOMIC); ++ d = kzalloc(sizeof(*d), GFP_NOWAIT); + if (!d) + return NULL; + +@@ -366,7 +367,7 @@ static void mtk_uart_apdma_issue_pending(struct dma_chan *chan) + unsigned long flags; + + spin_lock_irqsave(&c->vc.lock, flags); +- if (vchan_issue_pending(&c->vc)) { ++ if (vchan_issue_pending(&c->vc) && !c->desc) { + vd = vchan_next_desc(&c->vc); + c->desc = to_mtk_uart_apdma_desc(&vd->tx); + +diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c +index 3993ab65c62cd..89eb9ea258149 100644 +--- a/drivers/dma/sh/rcar-dmac.c ++++ b/drivers/dma/sh/rcar-dmac.c +@@ -1855,7 +1855,7 @@ static int rcar_dmac_probe(struct platform_device *pdev) + + /* Enable runtime PM and initialize the device. */ + pm_runtime_enable(&pdev->dev); +- ret = pm_runtime_get_sync(&pdev->dev); ++ ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) { + dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); + return ret; +diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c +index d47749a35863f..84009c5e0f330 100644 +--- a/drivers/dma/xilinx/zynqmp_dma.c ++++ b/drivers/dma/xilinx/zynqmp_dma.c +@@ -467,7 +467,7 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan) + struct zynqmp_dma_desc_sw *desc; + int i, ret; + +- ret = pm_runtime_get_sync(chan->dev); ++ ret = pm_runtime_resume_and_get(chan->dev); + if (ret < 0) + return ret; + +diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +index 9964ec0035ede..1d8739a4fbcad 100644 +--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c ++++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +@@ -3416,12 +3416,8 @@ static int gfx_v10_0_kiq_init_register(struct amdgpu_ring *ring) + if (ring->use_doorbell) { + WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, + (adev->doorbell_index.kiq * 2) << 2); +- /* If GC has entered CGPG, ringing doorbell > first page doesn't +- * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround +- * this issue. +- */ + WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, +- (adev->doorbell.size - 4)); ++ (adev->doorbell_index.userqueue_end * 2) << 2); + } + + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, +diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +index 354da41f52def..06cdc22b5501d 100644 +--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c ++++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +@@ -3593,12 +3593,8 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring) + if (ring->use_doorbell) { + WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, + (adev->doorbell_index.kiq * 2) << 2); +- /* If GC has entered CGPG, ringing doorbell > first page doesn't +- * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround +- * this issue. +- */ + WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, +- (adev->doorbell.size - 4)); ++ (adev->doorbell_index.userqueue_end * 2) << 2); + } + + WREG32_SOC15_RLC(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, +diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c +index bae6a3eccee0b..f9ee562f72d33 100644 +--- a/drivers/gpu/drm/nouveau/nouveau_prime.c ++++ b/drivers/gpu/drm/nouveau/nouveau_prime.c +@@ -112,7 +112,22 @@ int nouveau_gem_prime_pin(struct drm_gem_object *obj) + if (ret) + return -EINVAL; + +- return 0; ++ ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL); ++ if (ret) ++ goto error; ++ ++ if (nvbo->bo.moving) ++ ret = dma_fence_wait(nvbo->bo.moving, true); ++ ++ ttm_bo_unreserve(&nvbo->bo); ++ if (ret) ++ goto error; ++ ++ return ret; ++ ++error: ++ nouveau_bo_unpin(nvbo); ++ return ret; + } + + void nouveau_gem_prime_unpin(struct drm_gem_object *obj) +diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c +index b906e8fbd5f3a..7bc33a80934c4 100644 +--- a/drivers/gpu/drm/radeon/radeon_prime.c ++++ b/drivers/gpu/drm/radeon/radeon_prime.c +@@ -94,9 +94,19 @@ int radeon_gem_prime_pin(struct drm_gem_object *obj) + + /* pin buffer into GTT */ + ret = radeon_bo_pin(bo, RADEON_GEM_DOMAIN_GTT, NULL); +- if (likely(ret == 0)) +- bo->prime_shared_count++; +- ++ if (unlikely(ret)) ++ goto error; ++ ++ if (bo->tbo.moving) { ++ ret = dma_fence_wait(bo->tbo.moving, false); ++ if (unlikely(ret)) { ++ radeon_bo_unpin(bo); ++ goto error; ++ } ++ } ++ ++ bo->prime_shared_count++; ++error: + radeon_bo_unreserve(bo); + return ret; + } +diff --git a/drivers/i2c/busses/i2c-robotfuzz-osif.c b/drivers/i2c/busses/i2c-robotfuzz-osif.c +index a39f7d0927973..66dfa211e736b 100644 +--- a/drivers/i2c/busses/i2c-robotfuzz-osif.c ++++ b/drivers/i2c/busses/i2c-robotfuzz-osif.c +@@ -83,7 +83,7 @@ static int osif_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, + } + } + +- ret = osif_usb_read(adapter, OSIFI2C_STOP, 0, 0, NULL, 0); ++ ret = osif_usb_write(adapter, OSIFI2C_STOP, 0, 0, NULL, 0); + if (ret) { + dev_err(&adapter->dev, "failure sending STOP\n"); + return -EREMOTEIO; +@@ -153,7 +153,7 @@ static int osif_probe(struct usb_interface *interface, + * Set bus frequency. The frequency is: + * 120,000,000 / ( 16 + 2 * div * 4^prescale). + * Using dev = 52, prescale = 0 give 100KHz */ +- ret = osif_usb_read(&priv->adapter, OSIFI2C_SET_BIT_RATE, 52, 0, ++ ret = osif_usb_write(&priv->adapter, OSIFI2C_SET_BIT_RATE, 52, 0, + NULL, 0); + if (ret) { + dev_err(&interface->dev, "failure sending bit rate"); +diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c +index 545c3f2f8a06c..a3e3b274f0ea3 100644 +--- a/drivers/mmc/host/meson-gx-mmc.c ++++ b/drivers/mmc/host/meson-gx-mmc.c +@@ -166,6 +166,7 @@ struct meson_host { + + unsigned int bounce_buf_size; + void *bounce_buf; ++ void __iomem *bounce_iomem_buf; + dma_addr_t bounce_dma_addr; + struct sd_emmc_desc *descs; + dma_addr_t descs_dma_addr; +@@ -737,6 +738,47 @@ static void meson_mmc_desc_chain_transfer(struct mmc_host *mmc, u32 cmd_cfg) + writel(start, host->regs + SD_EMMC_START); + } + ++/* local sg copy to buffer version with _to/fromio usage for dram_access_quirk */ ++static void meson_mmc_copy_buffer(struct meson_host *host, struct mmc_data *data, ++ size_t buflen, bool to_buffer) ++{ ++ unsigned int sg_flags = SG_MITER_ATOMIC; ++ struct scatterlist *sgl = data->sg; ++ unsigned int nents = data->sg_len; ++ struct sg_mapping_iter miter; ++ unsigned int offset = 0; ++ ++ if (to_buffer) ++ sg_flags |= SG_MITER_FROM_SG; ++ else ++ sg_flags |= SG_MITER_TO_SG; ++ ++ sg_miter_start(&miter, sgl, nents, sg_flags); ++ ++ while ((offset < buflen) && sg_miter_next(&miter)) { ++ unsigned int len; ++ ++ len = min(miter.length, buflen - offset); ++ ++ /* When dram_access_quirk, the bounce buffer is a iomem mapping */ ++ if (host->dram_access_quirk) { ++ if (to_buffer) ++ memcpy_toio(host->bounce_iomem_buf + offset, miter.addr, len); ++ else ++ memcpy_fromio(miter.addr, host->bounce_iomem_buf + offset, len); ++ } else { ++ if (to_buffer) ++ memcpy(host->bounce_buf + offset, miter.addr, len); ++ else ++ memcpy(miter.addr, host->bounce_buf + offset, len); ++ } ++ ++ offset += len; ++ } ++ ++ sg_miter_stop(&miter); ++} ++ + static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd) + { + struct meson_host *host = mmc_priv(mmc); +@@ -780,8 +822,7 @@ static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd) + if (data->flags & MMC_DATA_WRITE) { + cmd_cfg |= CMD_CFG_DATA_WR; + WARN_ON(xfer_bytes > host->bounce_buf_size); +- sg_copy_to_buffer(data->sg, data->sg_len, +- host->bounce_buf, xfer_bytes); ++ meson_mmc_copy_buffer(host, data, xfer_bytes, true); + dma_wmb(); + } + +@@ -950,8 +991,7 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id) + if (meson_mmc_bounce_buf_read(data)) { + xfer_bytes = data->blksz * data->blocks; + WARN_ON(xfer_bytes > host->bounce_buf_size); +- sg_copy_from_buffer(data->sg, data->sg_len, +- host->bounce_buf, xfer_bytes); ++ meson_mmc_copy_buffer(host, data, xfer_bytes, false); + } + + next_cmd = meson_mmc_get_next_command(cmd); +@@ -1179,7 +1219,7 @@ static int meson_mmc_probe(struct platform_device *pdev) + * instead of the DDR memory + */ + host->bounce_buf_size = SD_EMMC_SRAM_DATA_BUF_LEN; +- host->bounce_buf = host->regs + SD_EMMC_SRAM_DATA_BUF_OFF; ++ host->bounce_iomem_buf = host->regs + SD_EMMC_SRAM_DATA_BUF_OFF; + host->bounce_dma_addr = res->start + SD_EMMC_SRAM_DATA_BUF_OFF; + } else { + /* data bounce buffer */ +diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c +index 0f2bee59a82b0..0bc7f6518fb32 100644 +--- a/drivers/net/caif/caif_serial.c ++++ b/drivers/net/caif/caif_serial.c +@@ -351,6 +351,7 @@ static int ldisc_open(struct tty_struct *tty) + rtnl_lock(); + result = register_netdevice(dev); + if (result) { ++ tty_kref_put(tty); + rtnl_unlock(); + free_netdev(dev); + return -ENODEV; +diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +index 5c6a276f69ac4..426b8098c50ee 100644 +--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c ++++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +@@ -1293,9 +1293,11 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn, + p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC; + + p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled; ++ BUILD_BUG_ON(sizeof(dcbx_info->operational.params) != ++ sizeof(p_hwfn->p_dcbx_info->set.config.params)); + memcpy(&p_hwfn->p_dcbx_info->set.config.params, + &dcbx_info->operational.params, +- sizeof(struct qed_dcbx_admin_params)); ++ sizeof(p_hwfn->p_dcbx_info->set.config.params)); + p_hwfn->p_dcbx_info->set.config.valid = true; + + memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set)); +diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c +index 8ff178fc2670c..661202e854121 100644 +--- a/drivers/net/ethernet/realtek/r8169_main.c ++++ b/drivers/net/ethernet/realtek/r8169_main.c +@@ -1801,7 +1801,7 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data) + { + switch(stringset) { + case ETH_SS_STATS: +- memcpy(data, *rtl8169_gstrings, sizeof(rtl8169_gstrings)); ++ memcpy(data, rtl8169_gstrings, sizeof(rtl8169_gstrings)); + break; + } + } +diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c +index a042f4607b0d0..931a44fe7afe8 100644 +--- a/drivers/net/ethernet/renesas/sh_eth.c ++++ b/drivers/net/ethernet/renesas/sh_eth.c +@@ -2322,7 +2322,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) + { + switch (stringset) { + case ETH_SS_STATS: +- memcpy(data, *sh_eth_gstrings_stats, ++ memcpy(data, sh_eth_gstrings_stats, + sizeof(sh_eth_gstrings_stats)); + break; + } +diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c +index 9b55fbdc3a7c6..9a7af7dda70dc 100644 +--- a/drivers/net/ethernet/xilinx/ll_temac_main.c ++++ b/drivers/net/ethernet/xilinx/ll_temac_main.c +@@ -770,12 +770,15 @@ static void temac_start_xmit_done(struct net_device *ndev) + stat = be32_to_cpu(cur_p->app0); + + while (stat & STS_CTRL_APP0_CMPLT) { ++ /* Make sure that the other fields are read after bd is ++ * released by dma ++ */ ++ rmb(); + dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), + be32_to_cpu(cur_p->len), DMA_TO_DEVICE); + skb = (struct sk_buff *)ptr_from_txbd(cur_p); + if (skb) + dev_consume_skb_irq(skb); +- cur_p->app0 = 0; + cur_p->app1 = 0; + cur_p->app2 = 0; + cur_p->app3 = 0; +@@ -784,6 +787,12 @@ static void temac_start_xmit_done(struct net_device *ndev) + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += be32_to_cpu(cur_p->len); + ++ /* app0 must be visible last, as it is used to flag ++ * availability of the bd ++ */ ++ smp_mb(); ++ cur_p->app0 = 0; ++ + lp->tx_bd_ci++; + if (lp->tx_bd_ci >= TX_BD_NUM) + lp->tx_bd_ci = 0; +@@ -810,6 +819,9 @@ static inline int temac_check_tx_bd_space(struct temac_local *lp, int num_frag) + if (cur_p->app0) + return NETDEV_TX_BUSY; + ++ /* Make sure to read next bd app0 after this one */ ++ rmb(); ++ + tail++; + if (tail >= TX_BD_NUM) + tail = 0; +@@ -927,6 +939,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) + wmb(); + lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */ + ++ if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) { ++ netdev_info(ndev, "%s -> netif_stop_queue\n", __func__); ++ netif_stop_queue(ndev); ++ } ++ + return NETDEV_TX_OK; + } + +diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c +index 31a5595133628..87c0cdbf262ae 100644 +--- a/drivers/net/phy/dp83867.c ++++ b/drivers/net/phy/dp83867.c +@@ -468,16 +468,12 @@ static int dp83867_phy_reset(struct phy_device *phydev) + { + int err; + +- err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); ++ err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + if (err < 0) + return err; + + usleep_range(10, 20); + +- /* After reset FORCE_LINK_GOOD bit is set. Although the +- * default value should be unset. Disable FORCE_LINK_GOOD +- * for the phy to work properly. +- */ + return phy_modify(phydev, MII_DP83867_PHYCTRL, + DP83867_PHYCR_FORCE_LINK_GOOD, 0); + } +diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c +index f6d643ecaf39b..24d1246330375 100644 +--- a/drivers/net/usb/r8152.c ++++ b/drivers/net/usb/r8152.c +@@ -5065,7 +5065,7 @@ static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data) + { + switch (stringset) { + case ETH_SS_STATS: +- memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings)); ++ memcpy(data, rtl8152_gstrings, sizeof(rtl8152_gstrings)); + break; + } + } +diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c +index c48c68090d762..1033513d3d9de 100644 +--- a/drivers/net/wireless/mac80211_hwsim.c ++++ b/drivers/net/wireless/mac80211_hwsim.c +@@ -1458,8 +1458,13 @@ static int mac80211_hwsim_start(struct ieee80211_hw *hw) + static void mac80211_hwsim_stop(struct ieee80211_hw *hw) + { + struct mac80211_hwsim_data *data = hw->priv; ++ + data->started = false; + hrtimer_cancel(&data->beacon_timer); ++ ++ while (!skb_queue_empty(&data->pending)) ++ ieee80211_free_txskb(hw, skb_dequeue(&data->pending)); ++ + wiphy_dbg(hw->wiphy, "%s\n", __func__); + } + +diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c +index 34a06e89e176a..3c3bc9f584983 100644 +--- a/drivers/pci/pci.c ++++ b/drivers/pci/pci.c +@@ -1666,11 +1666,21 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) + int err; + int i, bars = 0; + +- if (atomic_inc_return(&dev->enable_cnt) > 1) { +- pci_update_current_state(dev, dev->current_state); +- return 0; /* already enabled */ ++ /* ++ * Power state could be unknown at this point, either due to a fresh ++ * boot or a device removal call. So get the current power state ++ * so that things like MSI message writing will behave as expected ++ * (e.g. if the device really is in D0 at enable time). ++ */ ++ if (dev->pm_cap) { ++ u16 pmcsr; ++ pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); ++ dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); + } + ++ if (atomic_inc_return(&dev->enable_cnt) > 1) ++ return 0; /* already enabled */ ++ + bridge = pci_upstream_bridge(dev); + if (bridge) + pci_enable_bridge(bridge); +diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c +index 2d5e0435af0a4..bac1d040bacab 100644 +--- a/drivers/pinctrl/stm32/pinctrl-stm32.c ++++ b/drivers/pinctrl/stm32/pinctrl-stm32.c +@@ -1153,7 +1153,7 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, + struct resource res; + struct reset_control *rstc; + int npins = STM32_GPIO_PINS_PER_BANK; +- int bank_nr, err; ++ int bank_nr, err, i = 0; + + rstc = of_reset_control_get_exclusive(np, NULL); + if (!IS_ERR(rstc)) +@@ -1182,9 +1182,14 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, + + of_property_read_string(np, "st,bank-name", &bank->gpio_chip.label); + +- if (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args)) { ++ if (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, i, &args)) { + bank_nr = args.args[1] / STM32_GPIO_PINS_PER_BANK; + bank->gpio_chip.base = args.args[1]; ++ ++ npins = args.args[2]; ++ while (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, ++ ++i, &args)) ++ npins += args.args[2]; + } else { + bank_nr = pctl->nbanks; + bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK; +diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c +index efd9e908e2248..36a44a837031d 100644 +--- a/drivers/spi/spi-nxp-fspi.c ++++ b/drivers/spi/spi-nxp-fspi.c +@@ -975,12 +975,6 @@ static int nxp_fspi_probe(struct platform_device *pdev) + goto err_put_ctrl; + } + +- /* Clear potential interrupts */ +- reg = fspi_readl(f, f->iobase + FSPI_INTR); +- if (reg) +- fspi_writel(f, reg, f->iobase + FSPI_INTR); +- +- + /* find the resources - controller memory mapped space */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fspi_mmap"); + f->ahb_addr = devm_ioremap_resource(dev, res); +@@ -1012,6 +1006,11 @@ static int nxp_fspi_probe(struct platform_device *pdev) + goto err_put_ctrl; + } + ++ /* Clear potential interrupts */ ++ reg = fspi_readl(f, f->iobase + FSPI_INTR); ++ if (reg) ++ fspi_writel(f, reg, f->iobase + FSPI_INTR); ++ + /* find the irq */ + ret = platform_get_irq(pdev, 0); + if (ret < 0) +diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c +index e60be7bb55b0b..c6c8a33c81d5e 100644 +--- a/fs/nilfs2/sysfs.c ++++ b/fs/nilfs2/sysfs.c +@@ -1054,6 +1054,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) + nilfs_sysfs_delete_superblock_group(nilfs); + nilfs_sysfs_delete_segctor_group(nilfs); + kobject_del(&nilfs->ns_dev_kobj); ++ kobject_put(&nilfs->ns_dev_kobj); + kfree(nilfs->ns_dev_subgroups); + } + +diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h +index c1a96fdf598bc..875e002a41804 100644 +--- a/include/keys/system_keyring.h ++++ b/include/keys/system_keyring.h +@@ -31,16 +31,37 @@ extern int restrict_link_by_builtin_and_secondary_trusted( + #define restrict_link_by_builtin_and_secondary_trusted restrict_link_by_builtin_trusted + #endif + ++extern struct pkcs7_message *pkcs7; + #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING + extern int mark_hash_blacklisted(const char *hash); + extern int is_hash_blacklisted(const u8 *hash, size_t hash_len, + const char *type); ++extern int is_binary_blacklisted(const u8 *hash, size_t hash_len); + #else + static inline int is_hash_blacklisted(const u8 *hash, size_t hash_len, + const char *type) + { + return 0; + } ++ ++static inline int is_binary_blacklisted(const u8 *hash, size_t hash_len) ++{ ++ return 0; ++} ++#endif ++ ++#ifdef CONFIG_SYSTEM_REVOCATION_LIST ++extern int add_key_to_revocation_list(const char *data, size_t size); ++extern int is_key_on_revocation_list(struct pkcs7_message *pkcs7); ++#else ++static inline int add_key_to_revocation_list(const char *data, size_t size) ++{ ++ return 0; ++} ++static inline int is_key_on_revocation_list(struct pkcs7_message *pkcs7) ++{ ++ return -ENOKEY; ++} + #endif + + #ifdef CONFIG_IMA_BLACKLIST_KEYRING +diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h +index d8b86fd391134..d2dbe462efeef 100644 +--- a/include/linux/huge_mm.h ++++ b/include/linux/huge_mm.h +@@ -259,6 +259,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, + extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); + + extern struct page *huge_zero_page; ++extern unsigned long huge_zero_pfn; + + static inline bool is_huge_zero_page(struct page *page) + { +@@ -267,7 +268,7 @@ static inline bool is_huge_zero_page(struct page *page) + + static inline bool is_huge_zero_pmd(pmd_t pmd) + { +- return is_huge_zero_page(pmd_page(pmd)); ++ return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); + } + + static inline bool is_huge_zero_pud(pud_t pud) +@@ -398,6 +399,11 @@ static inline bool is_huge_zero_page(struct page *page) + return false; + } + ++static inline bool is_huge_zero_pmd(pmd_t pmd) ++{ ++ return false; ++} ++ + static inline bool is_huge_zero_pud(pud_t pud) + { + return false; +diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h +index fc717aeb2b3de..a0513c444446d 100644 +--- a/include/linux/hugetlb.h ++++ b/include/linux/hugetlb.h +@@ -469,17 +469,6 @@ static inline int hstate_index(struct hstate *h) + return h - hstates; + } + +-pgoff_t __basepage_index(struct page *page); +- +-/* Return page->index in PAGE_SIZE units */ +-static inline pgoff_t basepage_index(struct page *page) +-{ +- if (!PageCompound(page)) +- return page->index; +- +- return __basepage_index(page); +-} +- + extern int dissolve_free_huge_page(struct page *page); + extern int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn); +@@ -695,11 +684,6 @@ static inline int hstate_index(struct hstate *h) + return 0; + } + +-static inline pgoff_t basepage_index(struct page *page) +-{ +- return page->index; +-} +- + static inline int dissolve_free_huge_page(struct page *page) + { + return 0; +diff --git a/include/linux/mm.h b/include/linux/mm.h +index 5565d11f95429..a7d626b4cad1c 100644 +--- a/include/linux/mm.h ++++ b/include/linux/mm.h +@@ -1459,6 +1459,7 @@ struct zap_details { + struct address_space *check_mapping; /* Check page->mapping if set */ + pgoff_t first_index; /* Lowest page->index to unmap */ + pgoff_t last_index; /* Highest page->index to unmap */ ++ struct page *single_page; /* Locked page to be unmapped */ + }; + + struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, +@@ -1505,6 +1506,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, + extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, + unsigned long address, unsigned int fault_flags, + bool *unlocked); ++void unmap_mapping_page(struct page *page); + void unmap_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t nr, bool even_cows); + void unmap_mapping_range(struct address_space *mapping, +@@ -1525,6 +1527,7 @@ static inline int fixup_user_fault(struct task_struct *tsk, + BUG(); + return -EFAULT; + } ++static inline void unmap_mapping_page(struct page *page) { } + static inline void unmap_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t nr, bool even_cows) { } + static inline void unmap_mapping_range(struct address_space *mapping, +diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h +index 2ad72d2c8cc52..5d0767cb424aa 100644 +--- a/include/linux/mmdebug.h ++++ b/include/linux/mmdebug.h +@@ -37,6 +37,18 @@ void dump_mm(const struct mm_struct *mm); + BUG(); \ + } \ + } while (0) ++#define VM_WARN_ON_ONCE_PAGE(cond, page) ({ \ ++ static bool __section(".data.once") __warned; \ ++ int __ret_warn_once = !!(cond); \ ++ \ ++ if (unlikely(__ret_warn_once && !__warned)) { \ ++ dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\ ++ __warned = true; \ ++ WARN_ON(1); \ ++ } \ ++ unlikely(__ret_warn_once); \ ++}) ++ + #define VM_WARN_ON(cond) (void)WARN_ON(cond) + #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) + #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format) +@@ -48,6 +60,7 @@ void dump_mm(const struct mm_struct *mm); + #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond) + #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) + #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) ++#define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) + #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) + #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) + #endif +diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h +index 37a4d9e32cd3f..8543b1aaa5299 100644 +--- a/include/linux/pagemap.h ++++ b/include/linux/pagemap.h +@@ -397,7 +397,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping, + } + + /* +- * Get index of the page with in radix-tree ++ * Get index of the page within radix-tree (but not for hugetlb pages). + * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) + */ + static inline pgoff_t page_to_index(struct page *page) +@@ -416,15 +416,16 @@ static inline pgoff_t page_to_index(struct page *page) + return pgoff; + } + ++extern pgoff_t hugetlb_basepage_index(struct page *page); ++ + /* +- * Get the offset in PAGE_SIZE. +- * (TODO: hugepage should have ->index in PAGE_SIZE) ++ * Get the offset in PAGE_SIZE (even for hugetlb pages). ++ * (TODO: hugetlb pages should have ->index in PAGE_SIZE) + */ + static inline pgoff_t page_to_pgoff(struct page *page) + { +- if (unlikely(PageHeadHuge(page))) +- return page->index << compound_order(page); +- ++ if (unlikely(PageHuge(page))) ++ return hugetlb_basepage_index(page); + return page_to_index(page); + } + +diff --git a/include/linux/rmap.h b/include/linux/rmap.h +index d7d6d4eb17949..91ccae9467164 100644 +--- a/include/linux/rmap.h ++++ b/include/linux/rmap.h +@@ -98,7 +98,8 @@ enum ttu_flags { + * do a final flush if necessary */ + TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: + * caller holds it */ +- TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ ++ TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ ++ TTU_SYNC = 0x200, /* avoid racy checks with PVMW_SYNC */ + }; + + #ifdef CONFIG_MMU +diff --git a/include/net/sock.h b/include/net/sock.h +index a0728f24ecc53..d3dd89b6e2cba 100644 +--- a/include/net/sock.h ++++ b/include/net/sock.h +@@ -1860,7 +1860,8 @@ static inline u32 net_tx_rndhash(void) + + static inline void sk_set_txhash(struct sock *sk) + { +- sk->sk_txhash = net_tx_rndhash(); ++ /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ ++ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); + } + + static inline void sk_rethink_txhash(struct sock *sk) +@@ -2125,9 +2126,12 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock, + + static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) + { +- if (sk->sk_txhash) { ++ /* This pairs with WRITE_ONCE() in sk_set_txhash() */ ++ u32 txhash = READ_ONCE(sk->sk_txhash); ++ ++ if (txhash) { + skb->l4_hash = 1; +- skb->hash = sk->sk_txhash; ++ skb->hash = txhash; + } + } + +diff --git a/init/Kconfig b/init/Kconfig +index 4f9fd78e2200b..f23e90d9935f5 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -20,6 +20,9 @@ config GCC_VERSION + config CC_IS_CLANG + def_bool $(success,$(CC) --version | head -n 1 | grep -q clang) + ++config LD_IS_LLD ++ def_bool $(success,$(LD) -v | head -n 1 | grep -q LLD) ++ + config CLANG_VERSION + int + default $(shell,$(srctree)/scripts/clang-version.sh $(CC)) +diff --git a/kernel/futex.c b/kernel/futex.c +index 375e7e98e301f..f82879ae6577c 100644 +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -737,7 +737,7 @@ again: + + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ + key->shared.i_seq = get_inode_sequence_number(inode); +- key->shared.pgoff = basepage_index(tail); ++ key->shared.pgoff = page_to_pgoff(tail); + rcu_read_unlock(); + } + +diff --git a/kernel/kthread.c b/kernel/kthread.c +index 1d4c98a19043f..2eb8d7550324b 100644 +--- a/kernel/kthread.c ++++ b/kernel/kthread.c +@@ -1020,8 +1020,38 @@ void kthread_flush_work(struct kthread_work *work) + EXPORT_SYMBOL_GPL(kthread_flush_work); + + /* +- * This function removes the work from the worker queue. Also it makes sure +- * that it won't get queued later via the delayed work's timer. ++ * Make sure that the timer is neither set nor running and could ++ * not manipulate the work list_head any longer. ++ * ++ * The function is called under worker->lock. The lock is temporary ++ * released but the timer can't be set again in the meantime. ++ */ ++static void kthread_cancel_delayed_work_timer(struct kthread_work *work, ++ unsigned long *flags) ++{ ++ struct kthread_delayed_work *dwork = ++ container_of(work, struct kthread_delayed_work, work); ++ struct kthread_worker *worker = work->worker; ++ ++ /* ++ * del_timer_sync() must be called to make sure that the timer ++ * callback is not running. The lock must be temporary released ++ * to avoid a deadlock with the callback. In the meantime, ++ * any queuing is blocked by setting the canceling counter. ++ */ ++ work->canceling++; ++ raw_spin_unlock_irqrestore(&worker->lock, *flags); ++ del_timer_sync(&dwork->timer); ++ raw_spin_lock_irqsave(&worker->lock, *flags); ++ work->canceling--; ++} ++ ++/* ++ * This function removes the work from the worker queue. ++ * ++ * It is called under worker->lock. The caller must make sure that ++ * the timer used by delayed work is not running, e.g. by calling ++ * kthread_cancel_delayed_work_timer(). + * + * The work might still be in use when this function finishes. See the + * current_work proceed by the worker. +@@ -1029,28 +1059,8 @@ EXPORT_SYMBOL_GPL(kthread_flush_work); + * Return: %true if @work was pending and successfully canceled, + * %false if @work was not pending + */ +-static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, +- unsigned long *flags) ++static bool __kthread_cancel_work(struct kthread_work *work) + { +- /* Try to cancel the timer if exists. */ +- if (is_dwork) { +- struct kthread_delayed_work *dwork = +- container_of(work, struct kthread_delayed_work, work); +- struct kthread_worker *worker = work->worker; +- +- /* +- * del_timer_sync() must be called to make sure that the timer +- * callback is not running. The lock must be temporary released +- * to avoid a deadlock with the callback. In the meantime, +- * any queuing is blocked by setting the canceling counter. +- */ +- work->canceling++; +- raw_spin_unlock_irqrestore(&worker->lock, *flags); +- del_timer_sync(&dwork->timer); +- raw_spin_lock_irqsave(&worker->lock, *flags); +- work->canceling--; +- } +- + /* + * Try to remove the work from a worker list. It might either + * be from worker->work_list or from worker->delayed_work_list. +@@ -1103,11 +1113,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, + /* Work must not be used with >1 worker, see kthread_queue_work() */ + WARN_ON_ONCE(work->worker != worker); + +- /* Do not fight with another command that is canceling this work. */ ++ /* ++ * Temporary cancel the work but do not fight with another command ++ * that is canceling the work as well. ++ * ++ * It is a bit tricky because of possible races with another ++ * mod_delayed_work() and cancel_delayed_work() callers. ++ * ++ * The timer must be canceled first because worker->lock is released ++ * when doing so. But the work can be removed from the queue (list) ++ * only when it can be queued again so that the return value can ++ * be used for reference counting. ++ */ ++ kthread_cancel_delayed_work_timer(work, &flags); + if (work->canceling) + goto out; ++ ret = __kthread_cancel_work(work); + +- ret = __kthread_cancel_work(work, true, &flags); + fast_queue: + __kthread_queue_delayed_work(worker, dwork, delay); + out: +@@ -1129,7 +1151,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); + +- ret = __kthread_cancel_work(work, is_dwork, &flags); ++ if (is_dwork) ++ kthread_cancel_delayed_work_timer(work, &flags); ++ ++ ret = __kthread_cancel_work(work); + + if (worker->current_work != work) + goto out_fast; +diff --git a/kernel/module.c b/kernel/module.c +index 88a6a9e04f8dc..59d487b8d8dad 100644 +--- a/kernel/module.c ++++ b/kernel/module.c +@@ -268,9 +268,18 @@ static void module_assert_mutex_or_preempt(void) + #endif + } + ++#ifdef CONFIG_MODULE_SIG + static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); + module_param(sig_enforce, bool_enable_only, 0644); + ++void set_module_sig_enforced(void) ++{ ++ sig_enforce = true; ++} ++#else ++#define sig_enforce false ++#endif ++ + /* + * Export sig_enforce kernel cmdline parameter to allow other subsystems rely + * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. +@@ -281,11 +290,6 @@ bool is_module_sig_enforced(void) + } + EXPORT_SYMBOL(is_module_sig_enforced); + +-void set_module_sig_enforced(void) +-{ +- sig_enforce = true; +-} +- + /* Block module loading/unloading? */ + int modules_disabled = 0; + core_param(nomodule, modules_disabled, bint, 0); +diff --git a/mm/huge_memory.c b/mm/huge_memory.c +index 7bbf419bb86d6..87a07aa61be0d 100644 +--- a/mm/huge_memory.c ++++ b/mm/huge_memory.c +@@ -61,6 +61,7 @@ static struct shrinker deferred_split_shrinker; + + static atomic_t huge_zero_refcount; + struct page *huge_zero_page __read_mostly; ++unsigned long huge_zero_pfn __read_mostly = ~0UL; + + bool transparent_hugepage_enabled(struct vm_area_struct *vma) + { +@@ -97,6 +98,7 @@ retry: + __free_pages(zero_page, compound_order(zero_page)); + goto retry; + } ++ WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); + + /* We take additional reference here. It will be put back by shrinker */ + atomic_set(&huge_zero_refcount, 2); +@@ -146,6 +148,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, + if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { + struct page *zero_page = xchg(&huge_zero_page, NULL); + BUG_ON(zero_page == NULL); ++ WRITE_ONCE(huge_zero_pfn, ~0UL); + __free_pages(zero_page, compound_order(zero_page)); + return HPAGE_PMD_NR; + } +@@ -2155,7 +2158,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + count_vm_event(THP_SPLIT_PMD); + + if (!vma_is_anonymous(vma)) { +- _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); ++ old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + /* + * We are going to unmap this huge page. So + * just go ahead and zap it +@@ -2164,16 +2167,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + zap_deposited_table(mm, pmd); + if (vma_is_dax(vma)) + return; +- page = pmd_page(_pmd); +- if (!PageDirty(page) && pmd_dirty(_pmd)) +- set_page_dirty(page); +- if (!PageReferenced(page) && pmd_young(_pmd)) +- SetPageReferenced(page); +- page_remove_rmap(page, true); +- put_page(page); ++ if (unlikely(is_pmd_migration_entry(old_pmd))) { ++ swp_entry_t entry; ++ ++ entry = pmd_to_swp_entry(old_pmd); ++ page = migration_entry_to_page(entry); ++ } else { ++ page = pmd_page(old_pmd); ++ if (!PageDirty(page) && pmd_dirty(old_pmd)) ++ set_page_dirty(page); ++ if (!PageReferenced(page) && pmd_young(old_pmd)) ++ SetPageReferenced(page); ++ page_remove_rmap(page, true); ++ put_page(page); ++ } + add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); + return; +- } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { ++ } ++ ++ if (is_huge_zero_pmd(*pmd)) { + /* + * FIXME: Do we want to invalidate secondary mmu by calling + * mmu_notifier_invalidate_range() see comments below inside +@@ -2449,16 +2461,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, + static void unmap_page(struct page *page) + { + enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | +- TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; +- bool unmap_success; ++ TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC; + + VM_BUG_ON_PAGE(!PageHead(page), page); + + if (PageAnon(page)) + ttu_flags |= TTU_SPLIT_FREEZE; + +- unmap_success = try_to_unmap(page, ttu_flags); +- VM_BUG_ON_PAGE(!unmap_success, page); ++ try_to_unmap(page, ttu_flags); ++ ++ VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); + } + + static void remap_page(struct page *page) +@@ -2737,7 +2749,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) + struct deferred_split *ds_queue = get_deferred_split_queue(page); + struct anon_vma *anon_vma = NULL; + struct address_space *mapping = NULL; +- int count, mapcount, extra_pins, ret; ++ int extra_pins, ret; + bool mlocked; + unsigned long flags; + pgoff_t end; +@@ -2799,7 +2811,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) + + mlocked = PageMlocked(page); + unmap_page(head); +- VM_BUG_ON_PAGE(compound_mapcount(head), head); + + /* Make sure the page is not on per-CPU pagevec as it takes pin */ + if (mlocked) +@@ -2822,9 +2833,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) + + /* Prevent deferred_split_scan() touching ->_refcount */ + spin_lock(&ds_queue->split_queue_lock); +- count = page_count(head); +- mapcount = total_mapcount(head); +- if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { ++ if (page_ref_freeze(head, 1 + extra_pins)) { + if (!list_empty(page_deferred_list(head))) { + ds_queue->split_queue_len--; + list_del(page_deferred_list(head)); +@@ -2845,16 +2854,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) + } else + ret = 0; + } else { +- if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { +- pr_alert("total_mapcount: %u, page_count(): %u\n", +- mapcount, count); +- if (PageTail(page)) +- dump_page(head, NULL); +- dump_page(page, "total_mapcount(head) > 0"); +- BUG(); +- } + spin_unlock(&ds_queue->split_queue_lock); +-fail: if (mapping) ++fail: ++ if (mapping) + xa_unlock(&mapping->i_pages); + spin_unlock_irqrestore(&pgdata->lru_lock, flags); + remap_page(head); +diff --git a/mm/hugetlb.c b/mm/hugetlb.c +index fe15e7d8220ab..95a32749af4da 100644 +--- a/mm/hugetlb.c ++++ b/mm/hugetlb.c +@@ -1461,15 +1461,12 @@ int PageHeadHuge(struct page *page_head) + return get_compound_page_dtor(page_head) == free_huge_page; + } + +-pgoff_t __basepage_index(struct page *page) ++pgoff_t hugetlb_basepage_index(struct page *page) + { + struct page *page_head = compound_head(page); + pgoff_t index = page_index(page_head); + unsigned long compound_idx; + +- if (!PageHuge(page_head)) +- return page_index(page); +- + if (compound_order(page_head) >= MAX_ORDER) + compound_idx = page_to_pfn(page) - page_to_pfn(page_head); + else +diff --git a/mm/internal.h b/mm/internal.h +index 7dd7fbb577a9a..cf382549dd702 100644 +--- a/mm/internal.h ++++ b/mm/internal.h +@@ -339,27 +339,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) + extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); + + /* +- * At what user virtual address is page expected in @vma? ++ * At what user virtual address is page expected in vma? ++ * Returns -EFAULT if all of the page is outside the range of vma. ++ * If page is a compound head, the entire compound page is considered. + */ + static inline unsigned long +-__vma_address(struct page *page, struct vm_area_struct *vma) ++vma_address(struct page *page, struct vm_area_struct *vma) + { +- pgoff_t pgoff = page_to_pgoff(page); +- return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); ++ pgoff_t pgoff; ++ unsigned long address; ++ ++ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ ++ pgoff = page_to_pgoff(page); ++ if (pgoff >= vma->vm_pgoff) { ++ address = vma->vm_start + ++ ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); ++ /* Check for address beyond vma (or wrapped through 0?) */ ++ if (address < vma->vm_start || address >= vma->vm_end) ++ address = -EFAULT; ++ } else if (PageHead(page) && ++ pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { ++ /* Test above avoids possibility of wrap to 0 on 32-bit */ ++ address = vma->vm_start; ++ } else { ++ address = -EFAULT; ++ } ++ return address; + } + ++/* ++ * Then at what user virtual address will none of the page be found in vma? ++ * Assumes that vma_address() already returned a good starting address. ++ * If page is a compound head, the entire compound page is considered. ++ */ + static inline unsigned long +-vma_address(struct page *page, struct vm_area_struct *vma) ++vma_address_end(struct page *page, struct vm_area_struct *vma) + { +- unsigned long start, end; +- +- start = __vma_address(page, vma); +- end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); +- +- /* page should be within @vma mapping range */ +- VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); +- +- return max(start, vma->vm_start); ++ pgoff_t pgoff; ++ unsigned long address; ++ ++ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ ++ pgoff = page_to_pgoff(page) + compound_nr(page); ++ address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); ++ /* Check for address beyond vma (or wrapped through 0?) */ ++ if (address < vma->vm_start || address > vma->vm_end) ++ address = vma->vm_end; ++ return address; + } + + static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, +diff --git a/mm/memory.c b/mm/memory.c +index 13a575ce2ec8f..4bb7c6a364c81 100644 +--- a/mm/memory.c ++++ b/mm/memory.c +@@ -1165,7 +1165,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, + else if (zap_huge_pmd(tlb, vma, pmd, addr)) + goto next; + /* fall through */ ++ } else if (details && details->single_page && ++ PageTransCompound(details->single_page) && ++ next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { ++ spinlock_t *ptl = pmd_lock(tlb->mm, pmd); ++ /* ++ * Take and drop THP pmd lock so that we cannot return ++ * prematurely, while zap_huge_pmd() has cleared *pmd, ++ * but not yet decremented compound_mapcount(). ++ */ ++ spin_unlock(ptl); + } ++ + /* + * Here there can be other concurrent MADV_DONTNEED or + * trans huge page faults running, and if the pmd is +@@ -2769,6 +2780,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, + } + } + ++/** ++ * unmap_mapping_page() - Unmap single page from processes. ++ * @page: The locked page to be unmapped. ++ * ++ * Unmap this page from any userspace process which still has it mmaped. ++ * Typically, for efficiency, the range of nearby pages has already been ++ * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once ++ * truncation or invalidation holds the lock on a page, it may find that ++ * the page has been remapped again: and then uses unmap_mapping_page() ++ * to unmap it finally. ++ */ ++void unmap_mapping_page(struct page *page) ++{ ++ struct address_space *mapping = page->mapping; ++ struct zap_details details = { }; ++ ++ VM_BUG_ON(!PageLocked(page)); ++ VM_BUG_ON(PageTail(page)); ++ ++ details.check_mapping = mapping; ++ details.first_index = page->index; ++ details.last_index = page->index + hpage_nr_pages(page) - 1; ++ details.single_page = page; ++ ++ i_mmap_lock_write(mapping); ++ if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) ++ unmap_mapping_range_tree(&mapping->i_mmap, &details); ++ i_mmap_unlock_write(mapping); ++} ++ + /** + * unmap_mapping_pages() - Unmap pages from processes. + * @mapping: The address space containing pages to be unmapped. +diff --git a/mm/migrate.c b/mm/migrate.c +index 00bbe57c1ce22..5092ef2aa8a1f 100644 +--- a/mm/migrate.c ++++ b/mm/migrate.c +@@ -321,6 +321,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + goto out; + + page = migration_entry_to_page(entry); ++ page = compound_head(page); + + /* + * Once page cache replacement of page migration started, page_count +diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c +index eff4b4520c8d5..029f5598251c2 100644 +--- a/mm/page_vma_mapped.c ++++ b/mm/page_vma_mapped.c +@@ -111,6 +111,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) + return pfn_in_hpage(pvmw->page, pfn); + } + ++static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) ++{ ++ pvmw->address = (pvmw->address + size) & ~(size - 1); ++ if (!pvmw->address) ++ pvmw->address = ULONG_MAX; ++} ++ + /** + * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at + * @pvmw->address +@@ -139,6 +146,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) + { + struct mm_struct *mm = pvmw->vma->vm_mm; + struct page *page = pvmw->page; ++ unsigned long end; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; +@@ -148,10 +156,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) + if (pvmw->pmd && !pvmw->pte) + return not_found(pvmw); + +- if (pvmw->pte) +- goto next_pte; ++ if (unlikely(PageHuge(page))) { ++ /* The only possible mapping was handled on last iteration */ ++ if (pvmw->pte) ++ return not_found(pvmw); + +- if (unlikely(PageHuge(pvmw->page))) { + /* when pud is not present, pte will be NULL */ + pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); + if (!pvmw->pte) +@@ -163,78 +172,108 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) + return not_found(pvmw); + return true; + } +-restart: +- pgd = pgd_offset(mm, pvmw->address); +- if (!pgd_present(*pgd)) +- return false; +- p4d = p4d_offset(pgd, pvmw->address); +- if (!p4d_present(*p4d)) +- return false; +- pud = pud_offset(p4d, pvmw->address); +- if (!pud_present(*pud)) +- return false; +- pvmw->pmd = pmd_offset(pud, pvmw->address); ++ + /* +- * Make sure the pmd value isn't cached in a register by the +- * compiler and used as a stale value after we've observed a +- * subsequent update. ++ * Seek to next pte only makes sense for THP. ++ * But more important than that optimization, is to filter out ++ * any PageKsm page: whose page->index misleads vma_address() ++ * and vma_address_end() to disaster. + */ +- pmde = READ_ONCE(*pvmw->pmd); +- if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { +- pvmw->ptl = pmd_lock(mm, pvmw->pmd); +- if (likely(pmd_trans_huge(*pvmw->pmd))) { +- if (pvmw->flags & PVMW_MIGRATION) +- return not_found(pvmw); +- if (pmd_page(*pvmw->pmd) != page) +- return not_found(pvmw); +- return true; +- } else if (!pmd_present(*pvmw->pmd)) { +- if (thp_migration_supported()) { +- if (!(pvmw->flags & PVMW_MIGRATION)) ++ end = PageTransCompound(page) ? ++ vma_address_end(page, pvmw->vma) : ++ pvmw->address + PAGE_SIZE; ++ if (pvmw->pte) ++ goto next_pte; ++restart: ++ do { ++ pgd = pgd_offset(mm, pvmw->address); ++ if (!pgd_present(*pgd)) { ++ step_forward(pvmw, PGDIR_SIZE); ++ continue; ++ } ++ p4d = p4d_offset(pgd, pvmw->address); ++ if (!p4d_present(*p4d)) { ++ step_forward(pvmw, P4D_SIZE); ++ continue; ++ } ++ pud = pud_offset(p4d, pvmw->address); ++ if (!pud_present(*pud)) { ++ step_forward(pvmw, PUD_SIZE); ++ continue; ++ } ++ ++ pvmw->pmd = pmd_offset(pud, pvmw->address); ++ /* ++ * Make sure the pmd value isn't cached in a register by the ++ * compiler and used as a stale value after we've observed a ++ * subsequent update. ++ */ ++ pmde = READ_ONCE(*pvmw->pmd); ++ ++ if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { ++ pvmw->ptl = pmd_lock(mm, pvmw->pmd); ++ pmde = *pvmw->pmd; ++ if (likely(pmd_trans_huge(pmde))) { ++ if (pvmw->flags & PVMW_MIGRATION) + return not_found(pvmw); +- if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { +- swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); ++ if (pmd_page(pmde) != page) ++ return not_found(pvmw); ++ return true; ++ } ++ if (!pmd_present(pmde)) { ++ swp_entry_t entry; + +- if (migration_entry_to_page(entry) != page) +- return not_found(pvmw); +- return true; +- } ++ if (!thp_migration_supported() || ++ !(pvmw->flags & PVMW_MIGRATION)) ++ return not_found(pvmw); ++ entry = pmd_to_swp_entry(pmde); ++ if (!is_migration_entry(entry) || ++ migration_entry_to_page(entry) != page) ++ return not_found(pvmw); ++ return true; + } +- return not_found(pvmw); +- } else { + /* THP pmd was split under us: handle on pte level */ + spin_unlock(pvmw->ptl); + pvmw->ptl = NULL; ++ } else if (!pmd_present(pmde)) { ++ /* ++ * If PVMW_SYNC, take and drop THP pmd lock so that we ++ * cannot return prematurely, while zap_huge_pmd() has ++ * cleared *pmd but not decremented compound_mapcount(). ++ */ ++ if ((pvmw->flags & PVMW_SYNC) && ++ PageTransCompound(page)) { ++ spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); ++ ++ spin_unlock(ptl); ++ } ++ step_forward(pvmw, PMD_SIZE); ++ continue; + } +- } else if (!pmd_present(pmde)) { +- return false; +- } +- if (!map_pte(pvmw)) +- goto next_pte; +- while (1) { ++ if (!map_pte(pvmw)) ++ goto next_pte; ++this_pte: + if (check_pte(pvmw)) + return true; + next_pte: +- /* Seek to next pte only makes sense for THP */ +- if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) +- return not_found(pvmw); + do { + pvmw->address += PAGE_SIZE; +- if (pvmw->address >= pvmw->vma->vm_end || +- pvmw->address >= +- __vma_address(pvmw->page, pvmw->vma) + +- hpage_nr_pages(pvmw->page) * PAGE_SIZE) ++ if (pvmw->address >= end) + return not_found(pvmw); + /* Did we cross page table boundary? */ +- if (pvmw->address % PMD_SIZE == 0) { +- pte_unmap(pvmw->pte); ++ if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { + if (pvmw->ptl) { + spin_unlock(pvmw->ptl); + pvmw->ptl = NULL; + } ++ pte_unmap(pvmw->pte); ++ pvmw->pte = NULL; + goto restart; +- } else { +- pvmw->pte++; ++ } ++ pvmw->pte++; ++ if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) { ++ pvmw->ptl = pte_lockptr(mm, pvmw->pmd); ++ spin_lock(pvmw->ptl); + } + } while (pte_none(*pvmw->pte)); + +@@ -242,7 +281,10 @@ next_pte: + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); + } +- } ++ goto this_pte; ++ } while (pvmw->address < end); ++ ++ return false; + } + + /** +@@ -261,14 +303,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) + .vma = vma, + .flags = PVMW_SYNC, + }; +- unsigned long start, end; +- +- start = __vma_address(page, vma); +- end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); + +- if (unlikely(end < vma->vm_start || start >= vma->vm_end)) ++ pvmw.address = vma_address(page, vma); ++ if (pvmw.address == -EFAULT) + return 0; +- pvmw.address = max(start, vma->vm_start); + if (!page_vma_mapped_walk(&pvmw)) + return 0; + page_vma_mapped_walk_done(&pvmw); +diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c +index 532c29276fcee..49e8a4fbc2051 100644 +--- a/mm/pgtable-generic.c ++++ b/mm/pgtable-generic.c +@@ -126,8 +126,8 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, + { + pmd_t pmd; + VM_BUG_ON(address & ~HPAGE_PMD_MASK); +- VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && +- !pmd_devmap(*pmdp)) || !pmd_present(*pmdp)); ++ VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && ++ !pmd_devmap(*pmdp)); + pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); + flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + return pmd; +diff --git a/mm/rmap.c b/mm/rmap.c +index 0c7b2a9400d4a..45f2106852e84 100644 +--- a/mm/rmap.c ++++ b/mm/rmap.c +@@ -687,7 +687,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) + */ + unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) + { +- unsigned long address; + if (PageAnon(page)) { + struct anon_vma *page__anon_vma = page_anon_vma(page); + /* +@@ -697,15 +696,13 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) + if (!vma->anon_vma || !page__anon_vma || + vma->anon_vma->root != page__anon_vma->root) + return -EFAULT; +- } else if (page->mapping) { +- if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) +- return -EFAULT; +- } else ++ } else if (!vma->vm_file) { + return -EFAULT; +- address = __vma_address(page, vma); +- if (unlikely(address < vma->vm_start || address >= vma->vm_end)) ++ } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { + return -EFAULT; +- return address; ++ } ++ ++ return vma_address(page, vma); + } + + pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) +@@ -899,7 +896,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, + */ + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, + 0, vma, vma->vm_mm, address, +- min(vma->vm_end, address + page_size(page))); ++ vma_address_end(page, vma)); + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { +@@ -1353,6 +1350,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, + struct mmu_notifier_range range; + enum ttu_flags flags = (enum ttu_flags)arg; + ++ /* ++ * When racing against e.g. zap_pte_range() on another cpu, ++ * in between its ptep_get_and_clear_full() and page_remove_rmap(), ++ * try_to_unmap() may return false when it is about to become true, ++ * if page table locking is skipped: use TTU_SYNC to wait for that. ++ */ ++ if (flags & TTU_SYNC) ++ pvmw.flags = PVMW_SYNC; ++ + /* munlock has nothing to gain from examining un-locked vmas */ + if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) + return true; +@@ -1374,9 +1380,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. + */ ++ range.end = PageKsm(page) ? ++ address + PAGE_SIZE : vma_address_end(page, vma); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, +- address, +- min(vma->vm_end, address + page_size(page))); ++ address, range.end); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted +@@ -1690,9 +1697,9 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) + return is_vma_temporary_stack(vma); + } + +-static int page_mapcount_is_zero(struct page *page) ++static int page_not_mapped(struct page *page) + { +- return !total_mapcount(page); ++ return !page_mapped(page); + } + + /** +@@ -1710,7 +1717,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) + struct rmap_walk_control rwc = { + .rmap_one = try_to_unmap_one, + .arg = (void *)flags, +- .done = page_mapcount_is_zero, ++ .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + }; + +@@ -1731,14 +1738,15 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) + else + rmap_walk(page, &rwc); + +- return !page_mapcount(page) ? true : false; ++ /* ++ * When racing against e.g. zap_pte_range() on another cpu, ++ * in between its ptep_get_and_clear_full() and page_remove_rmap(), ++ * try_to_unmap() may return false when it is about to become true, ++ * if page table locking is skipped: use TTU_SYNC to wait for that. ++ */ ++ return !page_mapcount(page); + } + +-static int page_not_mapped(struct page *page) +-{ +- return !page_mapped(page); +-}; +- + /** + * try_to_munlock - try to munlock a page + * @page: the page to be munlocked +@@ -1833,6 +1841,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, + struct vm_area_struct *vma = avc->vma; + unsigned long address = vma_address(page, vma); + ++ VM_BUG_ON_VMA(address == -EFAULT, vma); + cond_resched(); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) +@@ -1887,6 +1896,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, + pgoff_start, pgoff_end) { + unsigned long address = vma_address(page, vma); + ++ VM_BUG_ON_VMA(address == -EFAULT, vma); + cond_resched(); + + if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) +diff --git a/mm/truncate.c b/mm/truncate.c +index dd9ebc1da3566..4d5add7d8ab6d 100644 +--- a/mm/truncate.c ++++ b/mm/truncate.c +@@ -173,13 +173,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, + * its lock, b) when a concurrent invalidate_mapping_pages got there first and + * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. + */ +-static void +-truncate_cleanup_page(struct address_space *mapping, struct page *page) ++static void truncate_cleanup_page(struct page *page) + { +- if (page_mapped(page)) { +- pgoff_t nr = PageTransHuge(page) ? HPAGE_PMD_NR : 1; +- unmap_mapping_pages(mapping, page->index, nr, false); +- } ++ if (page_mapped(page)) ++ unmap_mapping_page(page); + + if (page_has_private(page)) + do_invalidatepage(page, 0, PAGE_SIZE); +@@ -224,7 +221,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) + if (page->mapping != mapping) + return -EIO; + +- truncate_cleanup_page(mapping, page); ++ truncate_cleanup_page(page); + delete_from_page_cache(page); + return 0; + } +@@ -362,7 +359,7 @@ void truncate_inode_pages_range(struct address_space *mapping, + pagevec_add(&locked_pvec, page); + } + for (i = 0; i < pagevec_count(&locked_pvec); i++) +- truncate_cleanup_page(mapping, locked_pvec.pages[i]); ++ truncate_cleanup_page(locked_pvec.pages[i]); + delete_from_page_cache_batch(mapping, &locked_pvec); + for (i = 0; i < pagevec_count(&locked_pvec); i++) + unlock_page(locked_pvec.pages[i]); +@@ -715,6 +712,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, + continue; + } + ++ if (!did_range_unmap && page_mapped(page)) { ++ /* ++ * If page is mapped, before taking its lock, ++ * zap the rest of the file in one hit. ++ */ ++ unmap_mapping_pages(mapping, index, ++ (1 + end - index), false); ++ did_range_unmap = 1; ++ } ++ + lock_page(page); + WARN_ON(page_to_index(page) != index); + if (page->mapping != mapping) { +@@ -722,23 +729,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, + continue; + } + wait_on_page_writeback(page); +- if (page_mapped(page)) { +- if (!did_range_unmap) { +- /* +- * Zap the rest of the file in one hit. +- */ +- unmap_mapping_pages(mapping, index, +- (1 + end - index), false); +- did_range_unmap = 1; +- } else { +- /* +- * Just zap this page +- */ +- unmap_mapping_pages(mapping, index, +- 1, false); +- } +- } ++ ++ if (page_mapped(page)) ++ unmap_mapping_page(page); + BUG_ON(page_mapped(page)); ++ + ret2 = do_launder_page(mapping, page); + if (ret2 == 0) { + if (!invalidate_complete_page2(mapping, page)) +diff --git a/net/core/ethtool.c b/net/core/ethtool.c +index 76506975d59a5..cbd1885f24592 100644 +--- a/net/core/ethtool.c ++++ b/net/core/ethtool.c +@@ -1508,7 +1508,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, + if (eeprom.offset + eeprom.len > total_len) + return -EINVAL; + +- data = kmalloc(PAGE_SIZE, GFP_USER); ++ data = kzalloc(PAGE_SIZE, GFP_USER); + if (!data) + return -ENOMEM; + +@@ -1573,7 +1573,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) + if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) + return -EINVAL; + +- data = kmalloc(PAGE_SIZE, GFP_USER); ++ data = kzalloc(PAGE_SIZE, GFP_USER); + if (!data) + return -ENOMEM; + +@@ -1764,7 +1764,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) + return -EFAULT; + + test.len = test_len; +- data = kmalloc_array(test_len, sizeof(u64), GFP_USER); ++ data = kcalloc(test_len, sizeof(u64), GFP_USER); + if (!data) + return -ENOMEM; + +@@ -2295,7 +2295,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) + ret = ethtool_tunable_valid(&tuna); + if (ret) + return ret; +- data = kmalloc(tuna.len, GFP_USER); ++ data = kzalloc(tuna.len, GFP_USER); + if (!data) + return -ENOMEM; + ret = ops->get_tunable(dev, &tuna, data); +@@ -2481,7 +2481,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) + ret = ethtool_phy_tunable_valid(&tuna); + if (ret) + return ret; +- data = kmalloc(tuna.len, GFP_USER); ++ data = kzalloc(tuna.len, GFP_USER); + if (!data) + return -ENOMEM; + mutex_lock(&phydev->lock); +diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c +index a27d034c85ccb..603a3495afa62 100644 +--- a/net/ipv4/devinet.c ++++ b/net/ipv4/devinet.c +@@ -1989,7 +1989,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) + return -EAFNOSUPPORT; + + if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) +- BUG(); ++ return -EINVAL; + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) +diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c +index df6fbefe44d4b..1c3d5d3702a10 100644 +--- a/net/ipv4/ping.c ++++ b/net/ipv4/ping.c +@@ -963,6 +963,7 @@ bool ping_rcv(struct sk_buff *skb) + struct sock *sk; + struct net *net = dev_net(skb->dev); + struct icmphdr *icmph = icmp_hdr(skb); ++ bool rc = false; + + /* We assume the packet has already been checked by icmp_rcv */ + +@@ -977,14 +978,15 @@ bool ping_rcv(struct sk_buff *skb) + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + + pr_debug("rcv on socket %p\n", sk); +- if (skb2) +- ping_queue_rcv_skb(sk, skb2); ++ if (skb2 && !ping_queue_rcv_skb(sk, skb2)) ++ rc = true; + sock_put(sk); +- return true; + } +- pr_debug("no socket, dropping\n"); + +- return false; ++ if (!rc) ++ pr_debug("no socket, dropping\n"); ++ ++ return rc; + } + EXPORT_SYMBOL_GPL(ping_rcv); + +diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c +index 52feab2baeee5..366c3792b8604 100644 +--- a/net/ipv6/addrconf.c ++++ b/net/ipv6/addrconf.c +@@ -5761,7 +5761,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) + return -EAFNOSUPPORT; + + if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) +- BUG(); ++ return -EINVAL; + + if (tb[IFLA_INET6_TOKEN]) { + err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); +diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h +index a7933279a80b7..e574fbf6745a4 100644 +--- a/net/mac80211/ieee80211_i.h ++++ b/net/mac80211/ieee80211_i.h +@@ -1420,7 +1420,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + +- if (WARN_ON_ONCE(!chanctx_conf)) { ++ if (!chanctx_conf) { + rcu_read_unlock(); + return NULL; + } +diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c +index 3d7a5c5e586a6..670d84e54db73 100644 +--- a/net/mac80211/rx.c ++++ b/net/mac80211/rx.c +@@ -2200,17 +2200,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) + sc = le16_to_cpu(hdr->seq_ctrl); + frag = sc & IEEE80211_SCTL_FRAG; + +- if (is_multicast_ether_addr(hdr->addr1)) { +- I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); +- goto out_no_led; +- } +- + if (rx->sta) + cache = &rx->sta->frags; + + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) + goto out; + ++ if (is_multicast_ether_addr(hdr->addr1)) ++ return RX_DROP_MONITOR; ++ + I802_DEBUG_INC(rx->local->rx_handlers_fragments); + + if (skb_linearize(rx->skb)) +@@ -2336,7 +2334,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) + + out: + ieee80211_led_rx(rx->local); +- out_no_led: + if (rx->sta) + rx->sta->rx_stats.packets++; + return RX_CONTINUE; +diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c +index fbc2d4dfddf0e..0ffbf3d17911a 100644 +--- a/net/packet/af_packet.c ++++ b/net/packet/af_packet.c +@@ -2656,7 +2656,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) + } + if (likely(saddr == NULL)) { + dev = packet_cached_dev_get(po); +- proto = po->num; ++ proto = READ_ONCE(po->num); + } else { + err = -EINVAL; + if (msg->msg_namelen < sizeof(struct sockaddr_ll)) +@@ -2869,7 +2869,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) + + if (likely(saddr == NULL)) { + dev = packet_cached_dev_get(po); +- proto = po->num; ++ proto = READ_ONCE(po->num); + } else { + err = -EINVAL; + if (msg->msg_namelen < sizeof(struct sockaddr_ll)) +@@ -3141,7 +3141,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, + /* prevents packet_notifier() from calling + * register_prot_hook() + */ +- po->num = 0; ++ WRITE_ONCE(po->num, 0); + __unregister_prot_hook(sk, true); + rcu_read_lock(); + dev_curr = po->prot_hook.dev; +@@ -3151,17 +3151,17 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, + } + + BUG_ON(po->running); +- po->num = proto; ++ WRITE_ONCE(po->num, proto); + po->prot_hook.type = proto; + + if (unlikely(unlisted)) { + dev_put(dev); + po->prot_hook.dev = NULL; +- po->ifindex = -1; ++ WRITE_ONCE(po->ifindex, -1); + packet_cached_dev_reset(po); + } else { + po->prot_hook.dev = dev; +- po->ifindex = dev ? dev->ifindex : 0; ++ WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); + packet_cached_dev_assign(po, dev); + } + } +@@ -3475,7 +3475,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, + uaddr->sa_family = AF_PACKET; + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + rcu_read_lock(); +- dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); ++ dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); + if (dev) + strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + rcu_read_unlock(); +@@ -3490,16 +3490,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, + struct sock *sk = sock->sk; + struct packet_sock *po = pkt_sk(sk); + DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); ++ int ifindex; + + if (peer) + return -EOPNOTSUPP; + ++ ifindex = READ_ONCE(po->ifindex); + sll->sll_family = AF_PACKET; +- sll->sll_ifindex = po->ifindex; +- sll->sll_protocol = po->num; ++ sll->sll_ifindex = ifindex; ++ sll->sll_protocol = READ_ONCE(po->num); + sll->sll_pkttype = 0; + rcu_read_lock(); +- dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); ++ dev = dev_get_by_index_rcu(sock_net(sk), ifindex); + if (dev) { + sll->sll_hatype = dev->type; + sll->sll_halen = dev->addr_len; +@@ -4099,7 +4101,7 @@ static int packet_notifier(struct notifier_block *this, + } + if (msg == NETDEV_UNREGISTER) { + packet_cached_dev_reset(po); +- po->ifindex = -1; ++ WRITE_ONCE(po->ifindex, -1); + if (po->prot_hook.dev) + dev_put(po->prot_hook.dev); + po->prot_hook.dev = NULL; +@@ -4405,7 +4407,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, + was_running = po->running; + num = po->num; + if (was_running) { +- po->num = 0; ++ WRITE_ONCE(po->num, 0); + __unregister_prot_hook(sk, false); + } + spin_unlock(&po->bind_lock); +@@ -4440,7 +4442,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, + + spin_lock(&po->bind_lock); + if (was_running) { +- po->num = num; ++ WRITE_ONCE(po->num, num); + register_prot_hook(sk); + } + spin_unlock(&po->bind_lock); +@@ -4613,8 +4615,8 @@ static int packet_seq_show(struct seq_file *seq, void *v) + s, + refcount_read(&s->sk_refcnt), + s->sk_type, +- ntohs(po->num), +- po->ifindex, ++ ntohs(READ_ONCE(po->num)), ++ READ_ONCE(po->ifindex), + po->running, + atomic_read(&s->sk_rmem_alloc), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), +diff --git a/net/wireless/util.c b/net/wireless/util.c +index 4eae6ad328514..f0247eab5bc94 100644 +--- a/net/wireless/util.c ++++ b/net/wireless/util.c +@@ -1006,6 +1006,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, + case NL80211_IFTYPE_MESH_POINT: + /* mesh should be handled? */ + break; ++ case NL80211_IFTYPE_OCB: ++ cfg80211_leave_ocb(rdev, dev); ++ break; + default: + break; + } +diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h +index f9b19524da112..1e9baa5c4fc6e 100644 +--- a/scripts/recordmcount.h ++++ b/scripts/recordmcount.h +@@ -192,15 +192,20 @@ static unsigned int get_symindex(Elf_Sym const *sym, Elf32_Word const *symtab, + Elf32_Word const *symtab_shndx) + { + unsigned long offset; ++ unsigned short shndx = w2(sym->st_shndx); + int index; + +- if (sym->st_shndx != SHN_XINDEX) +- return w2(sym->st_shndx); ++ if (shndx > SHN_UNDEF && shndx < SHN_LORESERVE) ++ return shndx; + +- offset = (unsigned long)sym - (unsigned long)symtab; +- index = offset / sizeof(*sym); ++ if (shndx == SHN_XINDEX) { ++ offset = (unsigned long)sym - (unsigned long)symtab; ++ index = offset / sizeof(*sym); + +- return w(symtab_shndx[index]); ++ return w(symtab_shndx[index]); ++ } ++ ++ return 0; + } + + static unsigned int get_shnum(Elf_Ehdr const *ehdr, Elf_Shdr const *shdr0) +diff --git a/security/integrity/Makefile b/security/integrity/Makefile +index 35e6ca7737346..351c9662994b5 100644 +--- a/security/integrity/Makefile ++++ b/security/integrity/Makefile +@@ -11,7 +11,8 @@ integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o + integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o + integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o + integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \ +- platform_certs/load_uefi.o ++ platform_certs/load_uefi.o \ ++ platform_certs/keyring_handler.o + integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o + + obj-$(CONFIG_IMA) += ima/ +diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c +new file mode 100644 +index 0000000000000..5604bd57c9907 +--- /dev/null ++++ b/security/integrity/platform_certs/keyring_handler.c +@@ -0,0 +1,91 @@ ++// SPDX-License-Identifier: GPL-2.0 ++ ++#include <linux/kernel.h> ++#include <linux/sched.h> ++#include <linux/cred.h> ++#include <linux/err.h> ++#include <linux/efi.h> ++#include <linux/slab.h> ++#include <keys/asymmetric-type.h> ++#include <keys/system_keyring.h> ++#include "../integrity.h" ++ ++static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; ++static efi_guid_t efi_cert_x509_sha256_guid __initdata = ++ EFI_CERT_X509_SHA256_GUID; ++static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID; ++ ++/* ++ * Blacklist a hash. ++ */ ++static __init void uefi_blacklist_hash(const char *source, const void *data, ++ size_t len, const char *type, ++ size_t type_len) ++{ ++ char *hash, *p; ++ ++ hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); ++ if (!hash) ++ return; ++ p = memcpy(hash, type, type_len); ++ p += type_len; ++ bin2hex(p, data, len); ++ p += len * 2; ++ *p = 0; ++ ++ mark_hash_blacklisted(hash); ++ kfree(hash); ++} ++ ++/* ++ * Blacklist an X509 TBS hash. ++ */ ++static __init void uefi_blacklist_x509_tbs(const char *source, ++ const void *data, size_t len) ++{ ++ uefi_blacklist_hash(source, data, len, "tbs:", 4); ++} ++ ++/* ++ * Blacklist the hash of an executable. ++ */ ++static __init void uefi_blacklist_binary(const char *source, ++ const void *data, size_t len) ++{ ++ uefi_blacklist_hash(source, data, len, "bin:", 4); ++} ++ ++/* ++ * Add an X509 cert to the revocation list. ++ */ ++static __init void uefi_revocation_list_x509(const char *source, ++ const void *data, size_t len) ++{ ++ add_key_to_revocation_list(data, len); ++} ++ ++/* ++ * Return the appropriate handler for particular signature list types found in ++ * the UEFI db and MokListRT tables. ++ */ ++__init efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type) ++{ ++ if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) ++ return add_to_platform_keyring; ++ return 0; ++} ++ ++/* ++ * Return the appropriate handler for particular signature list types found in ++ * the UEFI dbx and MokListXRT tables. ++ */ ++__init efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type) ++{ ++ if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) ++ return uefi_blacklist_x509_tbs; ++ if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) ++ return uefi_blacklist_binary; ++ if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) ++ return uefi_revocation_list_x509; ++ return 0; ++} +diff --git a/security/integrity/platform_certs/keyring_handler.h b/security/integrity/platform_certs/keyring_handler.h +new file mode 100644 +index 0000000000000..2462bfa08fe34 +--- /dev/null ++++ b/security/integrity/platform_certs/keyring_handler.h +@@ -0,0 +1,32 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++ ++#ifndef PLATFORM_CERTS_INTERNAL_H ++#define PLATFORM_CERTS_INTERNAL_H ++ ++#include <linux/efi.h> ++ ++void blacklist_hash(const char *source, const void *data, ++ size_t len, const char *type, ++ size_t type_len); ++ ++/* ++ * Blacklist an X509 TBS hash. ++ */ ++void blacklist_x509_tbs(const char *source, const void *data, size_t len); ++ ++/* ++ * Blacklist the hash of an executable. ++ */ ++void blacklist_binary(const char *source, const void *data, size_t len); ++ ++/* ++ * Return the handler for particular signature list types found in the db. ++ */ ++efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type); ++ ++/* ++ * Return the handler for particular signature list types found in the dbx. ++ */ ++efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type); ++ ++#endif +diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c +index 020fc7a11ef0e..aa874d84e413e 100644 +--- a/security/integrity/platform_certs/load_uefi.c ++++ b/security/integrity/platform_certs/load_uefi.c +@@ -9,6 +9,7 @@ + #include <keys/asymmetric-type.h> + #include <keys/system_keyring.h> + #include "../integrity.h" ++#include "keyring_handler.h" + + static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; + static efi_guid_t efi_cert_x509_sha256_guid __initdata = +@@ -69,72 +70,6 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, + return db; + } + +-/* +- * Blacklist a hash. +- */ +-static __init void uefi_blacklist_hash(const char *source, const void *data, +- size_t len, const char *type, +- size_t type_len) +-{ +- char *hash, *p; +- +- hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); +- if (!hash) +- return; +- p = memcpy(hash, type, type_len); +- p += type_len; +- bin2hex(p, data, len); +- p += len * 2; +- *p = 0; +- +- mark_hash_blacklisted(hash); +- kfree(hash); +-} +- +-/* +- * Blacklist an X509 TBS hash. +- */ +-static __init void uefi_blacklist_x509_tbs(const char *source, +- const void *data, size_t len) +-{ +- uefi_blacklist_hash(source, data, len, "tbs:", 4); +-} +- +-/* +- * Blacklist the hash of an executable. +- */ +-static __init void uefi_blacklist_binary(const char *source, +- const void *data, size_t len) +-{ +- uefi_blacklist_hash(source, data, len, "bin:", 4); +-} +- +-/* +- * Return the appropriate handler for particular signature list types found in +- * the UEFI db and MokListRT tables. +- */ +-static __init efi_element_handler_t get_handler_for_db(const efi_guid_t * +- sig_type) +-{ +- if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) +- return add_to_platform_keyring; +- return 0; +-} +- +-/* +- * Return the appropriate handler for particular signature list types found in +- * the UEFI dbx and MokListXRT tables. +- */ +-static __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t * +- sig_type) +-{ +- if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) +- return uefi_blacklist_x509_tbs; +- if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) +- return uefi_blacklist_binary; +- return 0; +-} +- + /* + * Load the certs contained in the UEFI databases into the platform trusted + * keyring and the UEFI blacklisted X.509 cert SHA256 hashes into the blacklist +diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c +index 41cf45416060f..38de88e5ffbb2 100644 +--- a/tools/testing/selftests/kvm/lib/kvm_util.c ++++ b/tools/testing/selftests/kvm/lib/kvm_util.c +@@ -54,7 +54,7 @@ int kvm_check_cap(long cap) + exit(KSFT_SKIP); + + ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); +- TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" ++ TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" + " rc: %i errno: %i", ret, errno); + + close(kvm_fd); +diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c +index f83fa0aeeb451..b2287e7d3ba4a 100644 +--- a/virt/kvm/kvm_main.c ++++ b/virt/kvm/kvm_main.c +@@ -1593,6 +1593,13 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) + return true; + } + ++static int kvm_try_get_pfn(kvm_pfn_t pfn) ++{ ++ if (kvm_is_reserved_pfn(pfn)) ++ return 1; ++ return get_page_unless_zero(pfn_to_page(pfn)); ++} ++ + static int hva_to_pfn_remapped(struct vm_area_struct *vma, + unsigned long addr, bool *async, + bool write_fault, bool *writable, +@@ -1642,13 +1649,21 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, + * Whoever called remap_pfn_range is also going to call e.g. + * unmap_mapping_range before the underlying pages are freed, + * causing a call to our MMU notifier. ++ * ++ * Certain IO or PFNMAP mappings can be backed with valid ++ * struct pages, but be allocated without refcounting e.g., ++ * tail pages of non-compound higher order allocations, which ++ * would then underflow the refcount when the caller does the ++ * required put_page. Don't allow those pages here. + */ +- kvm_get_pfn(pfn); ++ if (!kvm_try_get_pfn(pfn)) ++ r = -EFAULT; + + out: + pte_unmap_unlock(ptep, ptl); + *p_pfn = pfn; +- return 0; ++ ++ return r; + } + + /*
