From 1a812aa15e62a9a85604102ff48229d43bb45498 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Wed, 19 Oct 2022 10:56:00 +0200 Subject: [PATCH 01/79] bpf: Generate BTF_KIND_FLOAT when linking vmlinux stable inclusion from stable-5.10.151 commit bbaea0f1cd33d702d053d5bdaf6d6dec3932894c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit db16c1fe92d7ba7d39061faef897842baee2c887 upstream. [backported for dependency only extra_paholeopt variable setup and usage, we don't want floats generated in 5.10] pahole v1.21 supports the --btf_gen_floats flag, which makes it generate the information about the floating-point types [1]. Adjust link-vmlinux.sh to pass this flag to pahole in case it's supported, which is determined using a simple version check. [1] https://lore.kernel.org/dwarves/YHRiXNX1JUF2Az0A@kernel.org/ Signed-off-by: Ilya Leoshkevich Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210413190043.21918-1-iii@linux.ibm.com Signed-off-by: Jiri Olsa Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- scripts/link-vmlinux.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 07de600ce5c4..779c94c298dd 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -197,6 +197,7 @@ vmlinux_link() gen_btf() { local pahole_ver + local extra_paholeopt= if ! [ -x "$(command -v ${PAHOLE})" ]; then echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available" @@ -212,7 +213,7 @@ gen_btf() vmlinux_link ${1} info "BTF" ${2} - LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} + LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${extra_paholeopt} ${1} # Create ${2} which contains just .BTF section but no symbols. Add # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all -- Gitee From 23836565f066aa8657ceac871f425fb88139b0ba Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Wed, 19 Oct 2022 10:56:01 +0200 Subject: [PATCH 02/79] kbuild: Quote OBJCOPY var to avoid a pahole call break the build stable inclusion from stable-5.10.151 commit 06481cd9f7f692088bce03244f8cf132018f2fc6 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit ff2e6efda0d5c51b33e2bcc0b0b981ac0a0ef214 upstream. [backported for dependency, skipped Makefile.modfinal change, because module BTF is not supported in 5.10] The ccache tool can be used to speed up cross-compilation, by calling the compiler and binutils through ccache. For example, following should work: $ export ARCH=arm64 CROSS_COMPILE="ccache aarch64-linux-gnu-" $ make M=drivers/gpu/drm/rockchip/ but pahole fails to extract the BTF info from DWARF, breaking the build: CC [M] drivers/gpu/drm/rockchip//rockchipdrm.mod.o LD [M] drivers/gpu/drm/rockchip//rockchipdrm.ko BTF [M] drivers/gpu/drm/rockchip//rockchipdrm.ko aarch64-linux-gnu-objcopy: invalid option -- 'J' Usage: aarch64-linux-gnu-objcopy [option(s)] in-file [out-file] Copies a binary file, possibly transforming it in the process ... make[1]: *** [scripts/Makefile.modpost:156: __modpost] Error 2 make: *** [Makefile:1866: modules] Error 2 this fails because OBJCOPY is set to "ccache aarch64-linux-gnu-copy" and later pahole is executed with the following command line: LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@ which gets expanded to: LLVM_OBJCOPY=ccache aarch64-linux-gnu-objcopy pahole -J ... instead of: LLVM_OBJCOPY="ccache aarch64-linux-gnu-objcopy" pahole -J ... Fixes: 5f9ae91f7c0d ("kbuild: Build kernel module BTFs if BTF is enabled and pahole supports it") Signed-off-by: Javier Martinez Canillas Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: Arnaldo Carvalho de Melo Link: https://lore.kernel.org/bpf/20210526215228.3729875-1-javierm@redhat.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- scripts/link-vmlinux.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 779c94c298dd..ed032354f2f3 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -213,7 +213,7 @@ gen_btf() vmlinux_link ${1} info "BTF" ${2} - LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${extra_paholeopt} ${1} + LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${extra_paholeopt} ${1} # Create ${2} which contains just .BTF section but no symbols. Add # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all -- Gitee From 6752e2213eb969453648e7002ec1326ca9e828fa Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 19 Oct 2022 10:56:02 +0200 Subject: [PATCH 03/79] kbuild: skip per-CPU BTF generation for pahole v1.18-v1.21 stable inclusion from stable-5.10.151 commit f5f413cb3e8af235c5d310bea9942424fb242c2c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit a0b8200d06ad6450c179407baa5f0f52f8cfcc97 upstream. [small context changes due to missing floats support in 5.10] Commit "mm/page_alloc: convert per-cpu list protection to local_lock" will introduce a zero-sized per-CPU variable, which causes pahole to generate invalid BTF. Only pahole versions 1.18 through 1.21 are impacted, as before 1.18 pahole doesn't know anything about per-CPU variables, and 1.22 contains the proper fix for the issue. Luckily, pahole 1.18 got --skip_encoding_btf_vars option disabling BTF generation for per-CPU variables in anticipation of some unanticipated problems. So use this escape hatch to disable per-CPU var BTF info on those problematic pahole versions. Users relying on availability of per-CPU var BTFs would need to upgrade to pahole 1.22+, but everyone won't notice any regressions. Link: https://lkml.kernel.org/r/20210530002536.3193829-1-andrii@kernel.org Signed-off-by: Andrii Nakryiko Acked-by: Mel Gorman Cc: Arnaldo Carvalho de Melo Cc: Hao Luo Cc: Michal Suchanek Cc: Jiri Olsa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Jiri Olsa Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- scripts/link-vmlinux.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index ed032354f2f3..a6d920ae2abd 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -212,6 +212,11 @@ gen_btf() vmlinux_link ${1} + if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then + # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars" + fi + info "BTF" ${2} LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${extra_paholeopt} ${1} -- Gitee From 85ff7fa32ed40381285d6d72ae2518b4561ea34c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 19 Oct 2022 10:56:03 +0200 Subject: [PATCH 04/79] kbuild: Unify options for BTF generation for vmlinux and modules stable inclusion from stable-5.10.151 commit c5006abb80e276896ff7237300a6d447708c7924 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 9741e07ece7c247dd65e1aa01e16b683f01c05a8 upstream. [skipped --btf_gen_floats option in pahole-flags.sh, skipped Makefile.modfinal change, because there's no BTF kmod support, squashing in 'exit 0' change from merge commit fc02cb2b37fe] Using new PAHOLE_FLAGS variable to pass extra arguments to pahole for both vmlinux and modules BTF data generation. Adding new scripts/pahole-flags.sh script that detect and prints pahole options. [ fixed issues found by kernel test robot ] Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211029125729.70002-1-jolsa@kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing create mode 100755 scripts/pahole-flags.sh Signed-off-by: wanxiaoqing --- Makefile | 3 +++ scripts/link-vmlinux.sh | 8 +------- scripts/pahole-flags.sh | 17 +++++++++++++++++ 3 files changed, 21 insertions(+), 7 deletions(-) create mode 100755 scripts/pahole-flags.sh diff --git a/Makefile b/Makefile index 87c202803824..6b0f4a5d27ea 100644 --- a/Makefile +++ b/Makefile @@ -466,6 +466,8 @@ LZ4 = lz4c XZ = xz ZSTD = zstd +PAHOLE_FLAGS = $(shell PAHOLE=$(PAHOLE) $(srctree)/scripts/pahole-flags.sh) + CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF) NOSTDINC_FLAGS := @@ -519,6 +521,7 @@ export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL +export PAHOLE_FLAGS # Files to ignore in find ... statements diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index a6d920ae2abd..5222d88a658f 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -197,7 +197,6 @@ vmlinux_link() gen_btf() { local pahole_ver - local extra_paholeopt= if ! [ -x "$(command -v ${PAHOLE})" ]; then echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available" @@ -212,13 +211,8 @@ gen_btf() vmlinux_link ${1} - if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then - # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars - extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars" - fi - info "BTF" ${2} - LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${extra_paholeopt} ${1} + LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1} # Create ${2} which contains just .BTF section but no symbols. Add # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh new file mode 100755 index 000000000000..27445cb72974 --- /dev/null +++ b/scripts/pahole-flags.sh @@ -0,0 +1,17 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +extra_paholeopt= + +if ! [ -x "$(command -v ${PAHOLE})" ]; then + exit 0 +fi + +pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/') + +if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then + # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars" +fi + +echo ${extra_paholeopt} -- Gitee From b17305d3431f99fa23621864f562cd662a0d4b79 Mon Sep 17 00:00:00 2001 From: Martin Rodriguez Reboredo Date: Wed, 19 Oct 2022 10:56:04 +0200 Subject: [PATCH 05/79] kbuild: Add skip_encoding_btf_enum64 option to pahole stable inclusion from stable-5.10.151 commit ecad3312111798d84dac1ce6a853e0ac9de8d505 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- New pahole (version 1.24) generates by default new BTF_KIND_ENUM64 BTF tag, which is not supported by stable kernel. As a result the kernel with CONFIG_DEBUG_INFO_BTF option will fail to compile with following error: BTFIDS vmlinux FAILED: load BTF from vmlinux: Invalid argument New pahole provides --skip_encoding_btf_enum64 option to skip BTF_KIND_ENUM64 generation and produce BTF supported by stable kernel. Adding this option to scripts/pahole-flags.sh. This change does not have equivalent commit in linus tree, because linus tree has support for BTF_KIND_ENUM64 tag, so it does not need to be disabled. Signed-off-by: Martin Rodriguez Reboredo Signed-off-by: Jiri Olsa Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- scripts/pahole-flags.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh index 27445cb72974..8c82173e42e5 100755 --- a/scripts/pahole-flags.sh +++ b/scripts/pahole-flags.sh @@ -14,4 +14,8 @@ if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars" fi +if [ "${pahole_ver}" -ge "124" ]; then + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_enum64" +fi + echo ${extra_paholeopt} -- Gitee From a4de3a217685775dd82d84f1b32fd07d77d1fbd9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 28 Oct 2022 13:02:36 +0200 Subject: [PATCH 06/79] Linux 5.10.151 stable inclusion from stable-5.10.151^0 commit c34d1b22fef329d5cecd003d7be249937ec70a3c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 6b0f4a5d27ea..21ffa61b6af7 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 150 +SUBLEVEL = 151 EXTRAVERSION = NAME = Dare mighty things -- Gitee From 6511108fdf93950abb720b0f79e30ede76e06409 Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Mon, 17 Oct 2022 21:02:27 +0800 Subject: [PATCH 07/79] ocfs2: clear dinode links count in case of error stable inclusion from stable-5.10.152 commit b838dcfda164cb3f8e2125b3e6bad6006843c67c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 28f4821b1b53e0649706912e810c6c232fc506f9 upstream. In ocfs2_mknod(), if error occurs after dinode successfully allocated, ocfs2 i_links_count will not be 0. So even though we clear inode i_nlink before iput in error handling, it still won't wipe inode since we'll refresh inode from dinode during inode lock. So just like clear inode i_nlink, we clear ocfs2 i_links_count as well. Also do the same change for ocfs2_symlink(). Link: https://lkml.kernel.org/r/20221017130227.234480-2-joseph.qi@linux.alibaba.com Signed-off-by: Joseph Qi Reported-by: Yan Wang Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- fs/ocfs2/namei.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c46bf7f581a1..db990df00bea 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -231,6 +231,7 @@ static int ocfs2_mknod(struct inode *dir, handle_t *handle = NULL; struct ocfs2_super *osb; struct ocfs2_dinode *dirfe; + struct ocfs2_dinode *fe = NULL; struct buffer_head *new_fe_bh = NULL; struct inode *inode = NULL; struct ocfs2_alloc_context *inode_ac = NULL; @@ -381,6 +382,7 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } + fe = (struct ocfs2_dinode *) new_fe_bh->b_data; if (S_ISDIR(mode)) { status = ocfs2_fill_new_dir(osb, handle, dir, inode, new_fe_bh, data_ac, meta_ac); @@ -453,8 +455,11 @@ static int ocfs2_mknod(struct inode *dir, leave: if (status < 0 && did_quota_inode) dquot_free_inode(inode); - if (handle) + if (handle) { + if (status < 0 && fe) + ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); + } ocfs2_inode_unlock(dir, 1); if (did_block_signals) @@ -2023,8 +2028,11 @@ static int ocfs2_symlink(struct inode *dir, ocfs2_clusters_to_bytes(osb->sb, 1)); if (status < 0 && did_quota_inode) dquot_free_inode(inode); - if (handle) + if (handle) { + if (status < 0 && fe) + ocfs2_set_links_count(fe, 0); ocfs2_commit_trans(osb, handle); + } ocfs2_inode_unlock(dir, 1); if (did_block_signals) -- Gitee From 27b79e2060208c8a350edd8f45a600cefcd077f4 Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Mon, 17 Oct 2022 21:02:26 +0800 Subject: [PATCH 08/79] ocfs2: fix BUG when iput after ocfs2_mknod fails stable inclusion from stable-5.10.152 commit 0d65f040fdbb812c952fd31a7001baf2becab9eb category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 759a7c6126eef5635506453e9b9d55a6a3ac2084 upstream. Commit b1529a41f777 "ocfs2: should reclaim the inode if '__ocfs2_mknod_locked' returns an error" tried to reclaim the claimed inode if __ocfs2_mknod_locked() fails later. But this introduce a race, the freed bit may be reused immediately by another thread, which will update dinode, e.g. i_generation. Then iput this inode will lead to BUG: inode->i_generation != le32_to_cpu(fe->i_generation) We could make this inode as bad, but we did want to do operations like wipe in some cases. Since the claimed inode bit can only affect that an dinode is missing and will return back after fsck, it seems not a big problem. So just leave it as is by revert the reclaim logic. Link: https://lkml.kernel.org/r/20221017130227.234480-1-joseph.qi@linux.alibaba.com Fixes: b1529a41f777 ("ocfs2: should reclaim the inode if '__ocfs2_mknod_locked' returns an error") Signed-off-by: Joseph Qi Reported-by: Yan Wang Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- fs/ocfs2/namei.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index db990df00bea..856474b0a1ae 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -636,18 +636,9 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, return status; } - status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, + return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh, parent_fe_bh, handle, inode_ac, fe_blkno, suballoc_loc, suballoc_bit); - if (status < 0) { - u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit); - int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode, - inode_ac->ac_bh, suballoc_bit, bg_blkno, 1); - if (tmp) - mlog_errno(tmp); - } - - return status; } static int ocfs2_mkdir(struct inode *dir, -- Gitee From 33b2eb852dc8e07856a9742fc95900a0c954d959 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Wed, 19 Oct 2022 10:57:10 +0800 Subject: [PATCH 09/79] selinux: enable use of both GFP_KERNEL and GFP_ATOMIC in convert_context() stable inclusion from stable-5.10.152 commit 2723875e9d677401d775a03a72abab7e9538c20c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit abe3c631447dcd1ba7af972fe6f054bee6f136fa upstream. The following warning was triggered on a hardware environment: SELinux: Converting 162 SID table entries... BUG: sleeping function called from invalid context at __might_sleep+0x60/0x74 0x0 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 5943, name: tar CPU: 7 PID: 5943 Comm: tar Tainted: P O 5.10.0 #1 Call trace: dump_backtrace+0x0/0x1c8 show_stack+0x18/0x28 dump_stack+0xe8/0x15c ___might_sleep+0x168/0x17c __might_sleep+0x60/0x74 __kmalloc_track_caller+0xa0/0x7dc kstrdup+0x54/0xac convert_context+0x48/0x2e4 sidtab_context_to_sid+0x1c4/0x36c security_context_to_sid_core+0x168/0x238 security_context_to_sid_default+0x14/0x24 inode_doinit_use_xattr+0x164/0x1e4 inode_doinit_with_dentry+0x1c0/0x488 selinux_d_instantiate+0x20/0x34 security_d_instantiate+0x70/0xbc d_splice_alias+0x4c/0x3c0 ext4_lookup+0x1d8/0x200 [ext4] __lookup_slow+0x12c/0x1e4 walk_component+0x100/0x200 path_lookupat+0x88/0x118 filename_lookup+0x98/0x130 user_path_at_empty+0x48/0x60 vfs_statx+0x84/0x140 vfs_fstatat+0x20/0x30 __se_sys_newfstatat+0x30/0x74 __arm64_sys_newfstatat+0x1c/0x2c el0_svc_common.constprop.0+0x100/0x184 do_el0_svc+0x1c/0x2c el0_svc+0x20/0x34 el0_sync_handler+0x80/0x17c el0_sync+0x13c/0x140 SELinux: Context system_u:object_r:pssp_rsyslog_log_t:s0:c0 is not valid (left unmapped). It was found that within a critical section of spin_lock_irqsave in sidtab_context_to_sid(), convert_context() (hooked by sidtab_convert_params.func) might cause the process to sleep via allocating memory with GFP_KERNEL, which is problematic. As Ondrej pointed out [1], convert_context()/sidtab_convert_params.func has another caller sidtab_convert_tree(), which is okay with GFP_KERNEL. Therefore, fix this problem by adding a gfp_t argument for convert_context()/sidtab_convert_params.func and pass GFP_KERNEL/_ATOMIC properly in individual callers. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20221018120111.1474581-1-gongruiqi1@huawei.com/ [1] Reported-by: Tan Ninghao Fixes: ee1a84fdfeed ("selinux: overhaul sidtab to fix bug and improve performance") Signed-off-by: GONG, Ruiqi Reviewed-by: Ondrej Mosnacek [PM: wrap long BUG() output lines, tweak subject line] Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- security/selinux/ss/services.c | 5 +++-- security/selinux/ss/sidtab.c | 4 ++-- security/selinux/ss/sidtab.h | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 31d631fa846e..3db8bd2158d9 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2011,7 +2011,8 @@ static inline int convert_context_handle_invalid_context( * in `newc'. Verify that the context is valid * under the new policy. */ -static int convert_context(struct context *oldc, struct context *newc, void *p) +static int convert_context(struct context *oldc, struct context *newc, void *p, + gfp_t gfp_flags) { struct convert_context_args *args; struct ocontext *oc; @@ -2025,7 +2026,7 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) args = p; if (oldc->str) { - s = kstrdup(oldc->str, GFP_KERNEL); + s = kstrdup(oldc->str, gfp_flags); if (!s) return -ENOMEM; diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index 656d50b09f76..1981c5af13e0 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -325,7 +325,7 @@ int sidtab_context_to_sid(struct sidtab *s, struct context *context, } rc = convert->func(context, &dst_convert->context, - convert->args); + convert->args, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; @@ -404,7 +404,7 @@ static int sidtab_convert_tree(union sidtab_entry_inner *edst, while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = convert->func(&esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, - convert->args); + convert->args, GFP_KERNEL); if (rc) return rc; (*pos)++; diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h index 4eff0e49dcb2..9fce0d553fe2 100644 --- a/security/selinux/ss/sidtab.h +++ b/security/selinux/ss/sidtab.h @@ -65,7 +65,7 @@ struct sidtab_isid_entry { }; struct sidtab_convert_params { - int (*func)(struct context *oldc, struct context *newc, void *args); + int (*func)(struct context *oldc, struct context *newc, void *args, gfp_t gfp_flags); void *args; struct sidtab *target; }; -- Gitee From 4f71ebad92c7aa317732b970e39690603056e37e Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Sat, 15 Oct 2022 15:04:23 +0200 Subject: [PATCH 10/79] cpufreq: qcom: fix writes in read-only memory region stable inclusion from stable-5.10.152 commit 794ded0bc461287a268bed21fea2eebb6e5d232c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 01039fb8e90c9cb684430414bff70cea9eb168c5 upstream. This commit fixes a kernel oops because of a write in some read-only memory: [ 9.068287] Unable to handle kernel write to read-only memory at virtual address ffff800009240ad8 ..snip.. [ 9.138790] Internal error: Oops: 9600004f [#1] PREEMPT SMP ..snip.. [ 9.269161] Call trace: [ 9.276271] __memcpy+0x5c/0x230 [ 9.278531] snprintf+0x58/0x80 [ 9.282002] qcom_cpufreq_msm8939_name_version+0xb4/0x190 [ 9.284869] qcom_cpufreq_probe+0xc8/0x39c ..snip.. The following line defines a pointer that point to a char buffer stored in read-only memory: char *pvs_name = "speedXX-pvsXX-vXX"; This pointer is meant to hold a template "speedXX-pvsXX-vXX" where the XX values get overridden by the qcom_cpufreq_krait_name_version function. Since the template is actually stored in read-only memory, when the function executes the following call we get an oops: snprintf(*pvs_name, sizeof("speedXX-pvsXX-vXX"), "speed%d-pvs%d-v%d", speed, pvs, pvs_ver); To fix this issue, we instead store the template name onto the stack by using the following syntax: char pvs_name_buffer[] = "speedXX-pvsXX-vXX"; Because the `pvs_name` needs to be able to be assigned to NULL, the template buffer is stored in the pvs_name_buffer and not under the pvs_name variable. Cc: v5.7+ # v5.7+ Fixes: a8811ec764f9 ("cpufreq: qcom: Add support for krait based socs") Signed-off-by: Fabien Parent Signed-off-by: Viresh Kumar Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/cpufreq/qcom-cpufreq-nvmem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 7fdd30e92e42..3af5c341d221 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -264,7 +264,8 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) struct nvmem_cell *speedbin_nvmem; struct device_node *np; struct device *cpu_dev; - char *pvs_name = "speedXX-pvsXX-vXX"; + char pvs_name_buffer[] = "speedXX-pvsXX-vXX"; + char *pvs_name = pvs_name_buffer; unsigned cpu; const struct of_device_id *match; int ret; -- Gitee From ef0656b8e360c5253019491c323d41380e7eb635 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Tue, 18 Oct 2022 03:19:20 +0100 Subject: [PATCH 11/79] i2c: qcom-cci: Fix ordering of pm_runtime_xx and i2c_add_adapter stable inclusion from stable-5.10.152 commit 6dcf1f0802cc36df55c94e7ce1edd83666a1d8f4 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 61775d54d674ff8ec3658495e0dbc537227dc5c1 upstream. When we compile-in the CCI along with the imx412 driver and run on the RB5 we see that i2c_add_adapter() causes the probe of the imx412 driver to happen. This probe tries to perform an i2c xfer() and the xfer() in i2c-qcom-cci.c fails on pm_runtime_get() because the i2c-qcom-cci.c::probe() function has not completed to pm_runtime_enable(dev). Fix this sequence by ensuring pm_runtime_xxx() calls happen prior to adding the i2c adapter. Fixes: e517526195de ("i2c: Add Qualcomm CCI I2C driver") Reported-by: Vladimir Zapolskiy Reviewed-by: Vladimir Zapolskiy Tested-by: Vladimir Zapolskiy Cc: Signed-off-by: Bryan O'Donoghue Reviewed-by: Robert Foss Signed-off-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/i2c/busses/i2c-qcom-cci.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c index 09e599069a81..06c87c79bae7 100644 --- a/drivers/i2c/busses/i2c-qcom-cci.c +++ b/drivers/i2c/busses/i2c-qcom-cci.c @@ -638,6 +638,11 @@ static int cci_probe(struct platform_device *pdev) if (ret < 0) goto error; + pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + for (i = 0; i < cci->data->num_masters; i++) { if (!cci->master[i].cci) continue; @@ -649,14 +654,12 @@ static int cci_probe(struct platform_device *pdev) } } - pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); - pm_runtime_use_autosuspend(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - return 0; error_i2c: + pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); + for (--i ; i >= 0; i--) { if (cci->master[i].cci) { i2c_del_adapter(&cci->master[i].adap); -- Gitee From 23922711c8cf14fa8bb54aa08345ddeb875356ba Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 5 Oct 2022 12:00:08 +0200 Subject: [PATCH 12/79] x86/microcode/AMD: Apply the patch early on every logical thread MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stable inclusion from stable-5.10.152 commit 0fb04676c4fd8b55bd0e0564aa49dcf90a7ac444 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit e7ad18d1169c62e6c78c01ff693fd362d9d65278 upstream. Currently, the patch application logic checks whether the revision needs to be applied on each logical CPU (SMT thread). Therefore, on SMT designs where the microcode engine is shared between the two threads, the application happens only on one of them as that is enough to update the shared microcode engine. However, there are microcode patches which do per-thread modification, see Link tag below. Therefore, drop the revision check and try applying on each thread. This is what the BIOS does too so this method is very much tested. Btw, change only the early paths. On the late loading paths, there's no point in doing per-thread modification because if is it some case like in the bugzilla below - removing a CPUID flag - the kernel cannot go and un-use features it has detected are there early. For that, one should use early loading anyway. [ bp: Fixes does not contain the oldest commit which did check for equality but that is good enough. ] Fixes: 8801b3fcb574 ("x86/microcode/AMD: Rework container parsing") Reported-by: Ștefan Talpalaru Signed-off-by: Borislav Petkov Tested-by: Ștefan Talpalaru Cc: Link: https://bugzilla.kernel.org/show_bug.cgi?id=216211 Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/x86/kernel/cpu/microcode/amd.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index c87936441339..234a96f25248 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -441,7 +441,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p return ret; native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev >= mc->hdr.patch_id) + + /* + * Allow application of the same revision to pick up SMT-specific + * changes even if the revision of the other SMT thread is already + * up-to-date. + */ + if (rev > mc->hdr.patch_id) return ret; if (!__apply_microcode_amd(mc)) { @@ -523,8 +529,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* Check whether we have saved a new patch already: */ - if (*new_rev && rev < mc->hdr.patch_id) { + /* + * Check whether a new patch has been saved already. Also, allow application of + * the same revision in order to pick up SMT-thread-specific configuration even + * if the sibling SMT thread already has an up-to-date revision. + */ + if (*new_rev && rev <= mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { *new_rev = mc->hdr.patch_id; return; -- Gitee From 52af3c78f4b78f8e0cde9c17cc794f33a011d8c8 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 14 Oct 2022 17:01:45 +0800 Subject: [PATCH 13/79] hwmon/coretemp: Handle large core ID value stable inclusion from stable-5.10.152 commit d9f0159da05df869071164edf0c6d7302efc5eca category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 7108b80a542b9d65e44b36d64a700a83658c0b73 upstream. The coretemp driver supports up to a hard-coded limit of 128 cores. Today, the driver can not support a core with an ID above that limit. Yet, the encoding of core ID's is arbitrary (BIOS APIC-ID) and so they may be sparse and they may be large. Update the driver to map arbitrary core ID numbers into appropriate array indexes so that 128 cores can be supported, no matter the encoding of core ID's. Signed-off-by: Zhang Rui Signed-off-by: Dave Hansen Acked-by: Len Brown Acked-by: Guenter Roeck Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20221014090147.1836-3-rui.zhang@intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/hwmon/coretemp.c | 56 +++++++++++++++++++++++++++++----------- 1 file changed, 41 insertions(+), 15 deletions(-) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index bb9211215a68..032129292957 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -46,9 +46,6 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); #define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) #define MAX_CORE_DATA (NUM_REAL_CORES + BASE_SYSFS_ATTR_NO) -#define TO_CORE_ID(cpu) (cpu_data(cpu).cpu_core_id) -#define TO_ATTR_NO(cpu) (TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO) - #ifdef CONFIG_SMP #define for_each_sibling(i, cpu) \ for_each_cpu(i, topology_sibling_cpumask(cpu)) @@ -91,6 +88,8 @@ struct temp_data { struct platform_data { struct device *hwmon_dev; u16 pkg_id; + u16 cpu_map[NUM_REAL_CORES]; + struct ida ida; struct cpumask cpumask; struct temp_data *core_data[MAX_CORE_DATA]; struct device_attribute name_attr; @@ -441,7 +440,7 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag) MSR_IA32_THERM_STATUS; tdata->is_pkg_data = pkg_flag; tdata->cpu = cpu; - tdata->cpu_core_id = TO_CORE_ID(cpu); + tdata->cpu_core_id = topology_core_id(cpu); tdata->attr_size = MAX_CORE_ATTRS; mutex_init(&tdata->update_lock); return tdata; @@ -454,7 +453,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, attr_no; + int err, index, attr_no; /* * Find attr number for sysfs: @@ -462,14 +461,26 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, * The attr number is always core id + 2 * The Pkgtemp will always show up as temp1_*, if available */ - attr_no = pkg_flag ? PKG_SYSFS_ATTR_NO : TO_ATTR_NO(cpu); + if (pkg_flag) { + attr_no = PKG_SYSFS_ATTR_NO; + } else { + index = ida_alloc(&pdata->ida, GFP_KERNEL); + if (index < 0) + return index; + pdata->cpu_map[index] = topology_core_id(cpu); + attr_no = index + BASE_SYSFS_ATTR_NO; + } - if (attr_no > MAX_CORE_DATA - 1) - return -ERANGE; + if (attr_no > MAX_CORE_DATA - 1) { + err = -ERANGE; + goto ida_free; + } tdata = init_temp_data(cpu, pkg_flag); - if (!tdata) - return -ENOMEM; + if (!tdata) { + err = -ENOMEM; + goto ida_free; + } /* Test if we can access the status register */ err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx); @@ -505,6 +516,9 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, exit_free: pdata->core_data[attr_no] = NULL; kfree(tdata); +ida_free: + if (!pkg_flag) + ida_free(&pdata->ida, index); return err; } @@ -524,6 +538,9 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx) kfree(pdata->core_data[indx]); pdata->core_data[indx] = NULL; + + if (indx >= BASE_SYSFS_ATTR_NO) + ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO); } static int coretemp_probe(struct platform_device *pdev) @@ -537,6 +554,7 @@ static int coretemp_probe(struct platform_device *pdev) return -ENOMEM; pdata->pkg_id = pdev->id; + ida_init(&pdata->ida); platform_set_drvdata(pdev, pdata); pdata->hwmon_dev = devm_hwmon_device_register_with_groups(dev, DRVNAME, @@ -553,6 +571,7 @@ static int coretemp_remove(struct platform_device *pdev) if (pdata->core_data[i]) coretemp_remove_core(pdata, i); + ida_destroy(&pdata->ida); return 0; } @@ -647,7 +666,7 @@ static int coretemp_cpu_offline(unsigned int cpu) struct platform_device *pdev = coretemp_get_pdev(cpu); struct platform_data *pd; struct temp_data *tdata; - int indx, target; + int i, indx = -1, target; /* * Don't execute this on suspend as the device remove locks @@ -660,12 +679,19 @@ static int coretemp_cpu_offline(unsigned int cpu) if (!pdev) return 0; - /* The core id is too big, just return */ - indx = TO_ATTR_NO(cpu); - if (indx > MAX_CORE_DATA - 1) + pd = platform_get_drvdata(pdev); + + for (i = 0; i < NUM_REAL_CORES; i++) { + if (pd->cpu_map[i] == topology_core_id(cpu)) { + indx = i + BASE_SYSFS_ATTR_NO; + break; + } + } + + /* Too many cores and this core is not populated, just return */ + if (indx < 0) return 0; - pd = platform_get_drvdata(pdev); tdata = pd->core_data[indx]; cpumask_clear_cpu(cpu, &pd->cpumask); -- Gitee From e476ed685bc953a1f48455f9a204f14e7817ef07 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Wed, 12 Oct 2022 15:11:05 +0200 Subject: [PATCH 14/79] ata: ahci-imx: Fix MODULE_ALIAS stable inclusion from stable-5.10.152 commit 6a2aadcb0186c383e9e24450b80269a80ac2bd3f category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 979556f1521a835a059de3b117b9c6c6642c7d58 upstream. 'ahci:' is an invalid prefix, preventing the module from autoloading. Fix this by using the 'platform:' prefix and DRV_NAME. Fixes: 9e54eae23bc9 ("ahci_imx: add ahci sata support on imx platforms") Cc: stable@vger.kernel.org Signed-off-by: Alexander Stein Reviewed-by: Fabio Estevam Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/ata/ahci_imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 388baf528fa8..189f75d53741 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -1230,4 +1230,4 @@ module_platform_driver(imx_ahci_driver); MODULE_DESCRIPTION("Freescale i.MX AHCI SATA platform driver"); MODULE_AUTHOR("Richard Zhu "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ahci:imx"); +MODULE_ALIAS("platform:" DRV_NAME); -- Gitee From 55c29d59de409fc3e457727a8ea6b75c5e1e9781 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Tue, 11 Oct 2022 10:46:17 +0800 Subject: [PATCH 15/79] ata: ahci: Match EM_MAX_SLOTS with SATA_PMP_MAX_PORTS stable inclusion from stable-5.10.152 commit 303d0f761431d848dd8d7ff9fd9b8c101879cabe category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 1e41e693f458eef2d5728207dbd327cd3b16580a upstream. UBSAN complains about array-index-out-of-bounds: [ 1.980703] kernel: UBSAN: array-index-out-of-bounds in /build/linux-9H675w/linux-5.15.0/drivers/ata/libahci.c:968:41 [ 1.980709] kernel: index 15 is out of range for type 'ahci_em_priv [8]' [ 1.980713] kernel: CPU: 0 PID: 209 Comm: scsi_eh_8 Not tainted 5.15.0-25-generic #25-Ubuntu [ 1.980716] kernel: Hardware name: System manufacturer System Product Name/P5Q3, BIOS 1102 06/11/2010 [ 1.980718] kernel: Call Trace: [ 1.980721] kernel: [ 1.980723] kernel: show_stack+0x52/0x58 [ 1.980729] kernel: dump_stack_lvl+0x4a/0x5f [ 1.980734] kernel: dump_stack+0x10/0x12 [ 1.980736] kernel: ubsan_epilogue+0x9/0x45 [ 1.980739] kernel: __ubsan_handle_out_of_bounds.cold+0x44/0x49 [ 1.980742] kernel: ahci_qc_issue+0x166/0x170 [libahci] [ 1.980748] kernel: ata_qc_issue+0x135/0x240 [ 1.980752] kernel: ata_exec_internal_sg+0x2c4/0x580 [ 1.980754] kernel: ? vprintk_default+0x1d/0x20 [ 1.980759] kernel: ata_exec_internal+0x67/0xa0 [ 1.980762] kernel: sata_pmp_read+0x8d/0xc0 [ 1.980765] kernel: sata_pmp_read_gscr+0x3c/0x90 [ 1.980768] kernel: sata_pmp_attach+0x8b/0x310 [ 1.980771] kernel: ata_eh_revalidate_and_attach+0x28c/0x4b0 [ 1.980775] kernel: ata_eh_recover+0x6b6/0xb30 [ 1.980778] kernel: ? ahci_do_hardreset+0x180/0x180 [libahci] [ 1.980783] kernel: ? ahci_stop_engine+0xb0/0xb0 [libahci] [ 1.980787] kernel: ? ahci_do_softreset+0x290/0x290 [libahci] [ 1.980792] kernel: ? trace_event_raw_event_ata_eh_link_autopsy_qc+0xe0/0xe0 [ 1.980795] kernel: sata_pmp_eh_recover.isra.0+0x214/0x560 [ 1.980799] kernel: sata_pmp_error_handler+0x23/0x40 [ 1.980802] kernel: ahci_error_handler+0x43/0x80 [libahci] [ 1.980806] kernel: ata_scsi_port_error_handler+0x2b1/0x600 [ 1.980810] kernel: ata_scsi_error+0x9c/0xd0 [ 1.980813] kernel: scsi_error_handler+0xa1/0x180 [ 1.980817] kernel: ? scsi_unjam_host+0x1c0/0x1c0 [ 1.980820] kernel: kthread+0x12a/0x150 [ 1.980823] kernel: ? set_kthread_struct+0x50/0x50 [ 1.980826] kernel: ret_from_fork+0x22/0x30 [ 1.980831] kernel: This happens because sata_pmp_init_links() initialize link->pmp up to SATA_PMP_MAX_PORTS while em_priv is declared as 8 elements array. I can't find the maximum Enclosure Management ports specified in AHCI spec v1.3.1, but "12.2.1 LED message type" states that "Port Multiplier Information" can utilize 4 bits, which implies it can support up to 16 ports. Hence, use SATA_PMP_MAX_PORTS as EM_MAX_SLOTS to resolve the issue. BugLink: https://bugs.launchpad.net/bugs/1970074 Cc: stable@vger.kernel.org Signed-off-by: Kai-Heng Feng Signed-off-by: Damien Le Moal Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/ata/ahci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index d1f284f0c83d..1ce897356993 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -254,7 +254,7 @@ enum { PCS_7 = 0x94, /* 7+ port PCS (Denverton) */ /* em constants */ - EM_MAX_SLOTS = 8, + EM_MAX_SLOTS = SATA_PMP_MAX_PORTS, EM_MAX_RETRY = 5, /* em_ctl bits */ -- Gitee From fdcba37599100d9b01426c253da5a760531d157f Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Sat, 15 Oct 2022 15:04:22 +0200 Subject: [PATCH 16/79] cpufreq: qcom: fix memory leak in error path stable inclusion from stable-5.10.152 commit e55feb31df3fc78b880d6e9d4b5853f05c974833 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 9f42cf54403a42cb092636804d2628d8ecf71e75 upstream. If for some reason the speedbin length is incorrect, then there is a memory leak in the error path because we never free the speedbin buffer. This commit fixes the error path to always free the speedbin buffer. Cc: v5.7+ # v5.7+ Fixes: a8811ec764f9 ("cpufreq: qcom: Add support for krait based socs") Signed-off-by: Fabien Parent Signed-off-by: Viresh Kumar Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/cpufreq/qcom-cpufreq-nvmem.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 3af5c341d221..9b3d24721d7b 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -215,6 +215,7 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev, int speed = 0, pvs = 0, pvs_ver = 0; u8 *speedbin; size_t len; + int ret = 0; speedbin = nvmem_cell_read(speedbin_nvmem, &len); @@ -232,7 +233,8 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev, break; default: dev_err(cpu_dev, "Unable to read nvmem data. Defaulting to 0!\n"); - return -ENODEV; + ret = -ENODEV; + goto len_error; } snprintf(*pvs_name, sizeof("speedXX-pvsXX-vXX"), "speed%d-pvs%d-v%d", @@ -240,8 +242,9 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev, drv->versions = (1 << speed); +len_error: kfree(speedbin); - return 0; + return ret; } static const struct qcom_cpufreq_match_data match_data_kryo = { -- Gitee From ab9e9b0fdc9c79cf98603048c37cfd93d6b149b2 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 17 Oct 2022 20:45:39 +0200 Subject: [PATCH 17/79] kvm: Add support for arch compat vm ioctls stable inclusion from stable-5.10.152 commit 34db701dc65f266b40f38273761ab4f05703f498 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit ed51862f2f57cbce6fed2d4278cfe70a490899fd upstream. We will introduce the first architecture specific compat vm ioctl in the next patch. Add all necessary boilerplate to allow architectures to override compat vm ioctls when necessary. Signed-off-by: Alexander Graf Message-Id: <20221017184541.2658-2-graf@amazon.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- include/linux/kvm_host.h | 2 ++ virt/kvm/kvm_main.c | 11 +++++++++++ 2 files changed, 13 insertions(+) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 896e563e2c18..9cb0a3d7874f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -911,6 +911,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c4cce817a452..564d5c145fbe 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3966,6 +3966,12 @@ struct compat_kvm_clear_dirty_log { }; }; +long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3974,6 +3980,11 @@ static long kvm_vm_compat_ioctl(struct file *filp, if (kvm->mm != current->mm || kvm->vm_bugged) return -EIO; + + r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); + if (r != -ENOTTY) + return r; + switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { -- Gitee From 4aa27af55b9ddf20d8641ea30fa0159041b6b67f Mon Sep 17 00:00:00 2001 From: Eric Ren Date: Sat, 15 Oct 2022 11:19:28 +0800 Subject: [PATCH 18/79] KVM: arm64: vgic: Fix exit condition in scan_its_table() stable inclusion from stable-5.10.152 commit 6d725672ce853f0d137231698ddddcdef607dff3 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit c000a2607145d28b06c697f968491372ea56c23a upstream. With some PCIe topologies, restoring a guest fails while parsing the ITS device tables. Reproducer hints: 1. Create ARM virt VM with pxb-pcie bus which adds extra host bridges, with qemu command like: ``` -device pxb-pcie,bus_nr=8,id=pci.x,numa_node=0,bus=pcie.0 \ -device pcie-root-port,..,bus=pci.x \ ... -device pxb-pcie,bus_nr=37,id=pci.y,numa_node=1,bus=pcie.0 \ -device pcie-root-port,..,bus=pci.y \ ... ``` 2. Ensure the guest uses 2-level device table 3. Perform VM migration which calls save/restore device tables In that setup, we get a big "offset" between 2 device_ids, which makes unsigned "len" round up a big positive number, causing the scan loop to continue with a bad GPA. For example: 1. L1 table has 2 entries; 2. and we are now scanning at L2 table entry index 2075 (pointed to by L1 first entry) 3. if next device id is 9472, we will get a big offset: 7397; 4. with unsigned 'len', 'len -= offset * esz', len will underflow to a positive number, mistakenly into next iteration with a bad GPA; (It should break out of the current L2 table scanning, and jump into the next L1 table entry) 5. that bad GPA fails the guest read. Fix it by stopping the L2 table scan when the next device id is outside of the current table, allowing the scan to continue from the next L1 table entry. Thanks to Eric Auger for the fix suggestion. Fixes: 920a7a8fa92a ("KVM: arm64: vgic-its: Add infrastructure for tableookup") Suggested-by: Eric Auger Signed-off-by: Eric Ren [maz: commit message tidy-up] Signed-off-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/d9c3a564af9e2c5bf63f48a7dcbf08cd593c5c0b.1665802985.git.renzhengeek@gmail.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/arm64/kvm/vgic/vgic-its.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index b9518f94bd43..23710bf5a86b 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2096,7 +2096,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, memset(entry, 0, esz); - while (len > 0) { + while (true) { int next_offset; size_t byte_offset; @@ -2109,6 +2109,9 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, return next_offset; byte_offset = next_offset * esz; + if (byte_offset >= len) + break; + id += next_offset; gpa += byte_offset; len -= byte_offset; -- Gitee From 3cb107ccf24b46c86b22a83aa63d0e10a90231dc Mon Sep 17 00:00:00 2001 From: Sean Young Date: Fri, 2 Sep 2022 12:32:21 +0200 Subject: [PATCH 19/79] media: mceusb: set timeout to at least timeout provided stable inclusion from stable-5.10.152 commit bce5808fc95dbc8604e55a311881f04c5a9a37d6 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 20b794ddce475ed012deb365000527c17b3e93e6 upstream. By rounding down, the actual timeout can be lower than requested. As a result, long spaces just below the requested timeout can be incorrectly reported as timeout and truncated. Fixes: 877f1a7cee3f ("media: rc: mceusb: allow the timeout to be configurable") Cc: stable@vger.kernel.org Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/media/rc/mceusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index de4cf6eb5258..142319c48405 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -1077,7 +1077,7 @@ static int mceusb_set_timeout(struct rc_dev *dev, unsigned int timeout) struct mceusb_dev *ir = dev->priv; unsigned int units; - units = DIV_ROUND_CLOSEST(timeout, MCE_TIME_UNIT); + units = DIV_ROUND_UP(timeout, MCE_TIME_UNIT); cmdbuf[2] = units >> 8; cmdbuf[3] = units; -- Gitee From 803fc843c19213b0c6216be90d1c8a323c1613ee Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Tue, 26 Jul 2022 04:14:54 +0200 Subject: [PATCH 20/79] media: venus: dec: Handle the case where find_format fails stable inclusion from stable-5.10.152 commit ab6aaa821024978b203b3e4cc431ba61ea495c21 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 06a2da340f762addc5935bf851d95b14d4692db2 upstream. Debugging the decoder on msm8916 I noticed the vdec probe was crashing if the fmt pointer was NULL. A similar fix from Colin Ian King found by Coverity was implemented for the encoder. Implement the same fix on the decoder. Fixes: 7472c1c69138 ("[media] media: venus: vdec: add video decoder files") Cc: stable@vger.kernel.org # v4.13+ Signed-off-by: Bryan O'Donoghue Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/media/platform/qcom/venus/vdec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index ea13170a6a2c..de34a87d1130 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -158,6 +158,8 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f) else return NULL; fmt = find_format(inst, pixmp->pixelformat, f->type); + if (!fmt) + return NULL; } pixmp->width = clamp(pixmp->width, frame_width_min(inst), -- Gitee From 6b85f98aeadd493f43e8cef04ed8509a4eee2ae1 Mon Sep 17 00:00:00 2001 From: Lei Chen Date: Mon, 30 Nov 2020 10:20:52 +0800 Subject: [PATCH 21/79] block: wbt: Remove unnecessary invoking of wbt_update_limits in wbt_init stable inclusion from stable-5.10.152 commit 392536023da18086d57565e716ed50193869b8e7 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 5a20d073ec54a72d9a732fa44bfe14954eb6332f upstream. It's unnecessary to call wbt_update_limits explicitly within wbt_init, because it will be called in the following function wbt_queue_depth_changed. Signed-off-by: Lei Chen Signed-off-by: Jens Axboe Signed-off-by: Yu Kuai Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- block/blk-wbt.c | 1 - 1 file changed, 1 deletion(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 35d81b5deae1..4ec0a018a2ad 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -840,7 +840,6 @@ int wbt_init(struct request_queue *q) rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->wc = 1; rwb->rq_depth.default_depth = RWB_DEF_DEPTH; - wbt_update_limits(rwb); /* * Assign rwb and add the stats callback. -- Gitee From 14eda33ed4ebe4e505ced54c86c3b3dff0207bf7 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 13 Sep 2022 18:57:49 +0800 Subject: [PATCH 22/79] blk-wbt: call rq_qos_add() after wb_normal is initialized MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stable inclusion from stable-5.10.152 commit 910ba49b33450a878128adc7d9c419dd97efd923 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 8c5035dfbb9475b67c82b3fdb7351236525bf52b upstream. Our test found a problem that wbt inflight counter is negative, which will cause io hang(noted that this problem doesn't exist in mainline): t1: device create t2: issue io add_disk blk_register_queue wbt_enable_default wbt_init rq_qos_add // wb_normal is still 0 /* * in mainline, disk can't be opened before * bdev_add(), however, in old kernels, disk * can be opened before blk_register_queue(). */ blkdev_issue_flush // disk size is 0, however, it's not checked submit_bio_wait submit_bio blk_mq_submit_bio rq_qos_throttle wbt_wait bio_to_wbt_flags rwb_enabled // wb_normal is 0, inflight is not increased wbt_queue_depth_changed(&rwb->rqos); wbt_update_limits // wb_normal is initialized rq_qos_track wbt_track rq->wbt_flags |= bio_to_wbt_flags(rwb, bio); // wb_normal is not 0，wbt_flags will be set t3: io completion blk_mq_free_request rq_qos_done wbt_done wbt_is_tracked // return true __wbt_done wbt_rqw_done atomic_dec_return(&rqw->inflight); // inflight is decreased commit 8235b5c1e8c1 ("block: call bdev_add later in device_add_disk") can avoid this problem, however it's better to fix this problem in wbt: 1) Lower kernel can't backport this patch due to lots of refactor. 2) Root cause is that wbt call rq_qos_add() before wb_normal is initialized. Fixes: e34cbd307477 ("blk-wbt: add general throttling mechanism") Cc: Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20220913105749.3086243-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- block/blk-wbt.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 4ec0a018a2ad..bafdb8098893 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -840,6 +840,10 @@ int wbt_init(struct request_queue *q) rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->wc = 1; rwb->rq_depth.default_depth = RWB_DEF_DEPTH; + rwb->min_lat_nsec = wbt_default_latency_nsec(q); + + wbt_queue_depth_changed(&rwb->rqos); + wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); /* * Assign rwb and add the stats callback. @@ -847,10 +851,5 @@ int wbt_init(struct request_queue *q) rq_qos_add(q, &rwb->rqos); blk_stat_add_callback(q, rwb->cb); - rwb->min_lat_nsec = wbt_default_latency_nsec(q); - - wbt_queue_depth_changed(&rwb->rqos); - wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); - return 0; } -- Gitee From e2a12d76f8f551c2f13ae0ab60d2e96ec52788a5 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 14 Jul 2022 17:15:23 +0100 Subject: [PATCH 23/79] arm64: errata: Remove AES hwcap for COMPAT tasks stable inclusion from stable-5.10.152 commit 51b96ecaedc0a12f6827f189a94f59012dde8208 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 44b3834b2eed595af07021b1c64e6f9bc396398b upstream. Cortex-A57 and Cortex-A72 have an erratum where an interrupt that occurs between a pair of AES instructions in aarch32 mode may corrupt the ELR. The task will subsequently produce the wrong AES result. The AES instructions are part of the cryptographic extensions, which are optional. User-space software will detect the support for these instructions from the hwcaps. If the platform doesn't support these instructions a software implementation should be used. Remove the hwcap bits on affected parts to indicate user-space should not use the AES instructions. Acked-by: Ard Biesheuvel Signed-off-by: James Morse Link: https://lore.kernel.org/r/20220714161523.279570-3-james.morse@arm.com Signed-off-by: Will Deacon [florian: removed arch/arm64/tools/cpucaps and fixup cpufeature.c] Signed-off-by: Florian Fainelli Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- Documentation/arm64/silicon-errata.rst | 4 ++++ arch/arm64/Kconfig | 16 ++++++++++++++++ arch/arm64/include/asm/cpucaps.h | 3 ++- arch/arm64/kernel/cpu_errata.c | 16 ++++++++++++++++ arch/arm64/kernel/cpufeature.c | 13 ++++++++++++- 5 files changed, 50 insertions(+), 2 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 22a07c208fee..4f3206495217 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -76,10 +76,14 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #1319537 | ARM64_ERRATUM_1319367 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A57 | #1742098 | ARM64_ERRATUM_1742098 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A72 | #853709 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A72 | #1319367 | ARM64_ERRATUM_1319367 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A72 | #1655431 | ARM64_ERRATUM_1742098 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1188873,1418040| ARM64_ERRATUM_1418040 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ab6cbb944b36..84d2b773e9d2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -487,6 +487,22 @@ config ARM64_ERRATUM_834220 If unsure, say Y. +config ARM64_ERRATUM_1742098 + bool "Cortex-A57/A72: 1742098: ELR recorded incorrectly on interrupt taken between cryptographic instructions in a sequence" + depends on COMPAT + default y + help + This option removes the AES hwcap for aarch32 user-space to + workaround erratum 1742098 on Cortex-A57 and Cortex-A72. + + Affected parts may corrupt the AES state if an interrupt is + taken between a pair of AES instructions. These instructions + are only present if the cryptography extensions are present. + All software should have a fallback implementation for CPUs + that don't implement the cryptography extensions. + + If unsure, say Y. + config ARM64_ERRATUM_845719 bool "Cortex-A53: 845719: a load might read incorrect data" depends on COMPAT diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 53030d3c03a2..d2080a41f6e6 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -68,7 +68,8 @@ #define ARM64_WORKAROUND_1508412 58 #define ARM64_SPECTRE_BHB 59 #define ARM64_WORKAROUND_2457168 60 +#define ARM64_WORKAROUND_1742098 61 -#define ARM64_NCAPS 61 +#define ARM64_NCAPS 62 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index aaacca6fd52f..5d6f19bc628c 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -356,6 +356,14 @@ static const struct midr_range erratum_1463225[] = { }; #endif +#ifdef CONFIG_ARM64_ERRATUM_1742098 +static struct midr_range broken_aarch32_aes[] = { + MIDR_RANGE(MIDR_CORTEX_A57, 0, 1, 0xf, 0xf), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -554,6 +562,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { /* Cortex-A510 r0p0-r1p1 */ CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1) }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1742098 + { + .desc = "ARM erratum 1742098", + .capability = ARM64_WORKAROUND_1742098, + CAP_MIDR_RANGE_LIST(broken_aarch32_aes), + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + }, #endif { } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0f340ae063ef..40003457e27d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -76,6 +76,7 @@ #include #include #include +#include #include #include #include @@ -1730,6 +1731,14 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */ +static void elf_hwcap_fixup(void) +{ +#ifdef CONFIG_ARM64_ERRATUM_1742098 + if (cpus_have_const_cap(ARM64_WORKAROUND_1742098)) + compat_elf_hwcap2 &= ~COMPAT_HWCAP2_AES; +#endif /* ARM64_ERRATUM_1742098 */ +} + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -2735,8 +2744,10 @@ void __init setup_cpu_features(void) setup_system_capabilities(); setup_elf_hwcaps(arm64_elf_hwcaps); - if (system_supports_32bit_el0()) + if (system_supports_32bit_el0()) { setup_elf_hwcaps(compat_elf_hwcaps); + elf_hwcap_fixup(); + } if (system_uses_ttbr0_pan()) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); -- Gitee From cbc5addc2a8753dede00a03a6f146d89d4a12c36 Mon Sep 17 00:00:00 2001 From: Jean-Francois Le Fillatre Date: Wed, 24 Aug 2022 21:14:36 +0200 Subject: [PATCH 24/79] r8152: add PID for the Lenovo OneLink+ Dock stable inclusion from stable-5.10.152 commit cc841a8a704c1de58491b8f158d661c065cfb831 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 1bd3a383075c64d638e65d263c9267b08ee7733c upstream. The Lenovo OneLink+ Dock contains an RTL8153 controller that behaves as a broken CDC device by default. Add the custom Lenovo PID to the r8152 driver to support it properly. Also, systems compatible with this dock provide a BIOS option to enable MAC address passthrough (as per Lenovo document "ThinkPad Docking Solutions 2017"). Add the custom PID to the MAC passthrough list too. Tested on a ThinkPad 13 1st gen with the expected results: passthrough disabled: Invalid header when reading pass-thru MAC addr passthrough enabled: Using pass-thru MAC addr XX:XX:XX:XX:XX:XX Signed-off-by: Jean-Francois Le Fillatre Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/net/usb/cdc_ether.c | 7 +++++++ drivers/net/usb/r8152.c | 1 + 2 files changed, 8 insertions(+) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 43ddbe61dc58..935cd296887f 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -763,6 +763,13 @@ static const struct usb_device_id products[] = { }, #endif +/* Lenovo ThinkPad OneLink+ Dock (based on Realtek RTL8153) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3054, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* ThinkPad USB-C Dock (based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index a526242a3e36..f9a79d67d6d4 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -6870,6 +6870,7 @@ static const struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)}, {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3069)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3082)}, -- Gitee From a6da7a025e279cae112cf9f30865cb4735864405 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 11 Oct 2022 13:16:51 +0100 Subject: [PATCH 25/79] btrfs: fix processing of delayed data refs during backref walking stable inclusion from stable-5.10.152 commit 590929ef6972ee33e20ab439979de6d3208a3e2e category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 4fc7b57228243d09c0d878873bf24fa64a90fa01 ] When processing delayed data references during backref walking and we are using a share context (we are being called through fiemap), whenever we find a delayed data reference for an inode different from the one we are interested in, then we immediately exit and consider the data extent as shared. This is wrong, because: 1) This might be a DROP reference that will cancel out a reference in the extent tree; 2) Even if it's an ADD reference, it may be followed by a DROP reference that cancels it out. In either case we should not exit immediately. Fix this by never exiting when we find a delayed data reference for another inode - instead add the reference and if it does not cancel out other delayed reference, we will exit early when we call extent_is_shared() after processing all delayed references. If we find a drop reference, then signal the code that processes references from the extent tree (add_inline_refs() and add_keyed_refs()) to not exit immediately if it finds there a reference for another inode, since we have delayed drop references that may cancel it out. In this later case we exit once we don't have references in the rb trees that cancel out each other and have two references for different inodes. Example reproducer for case 1): $ cat test-1.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV mount $DEV $MNT xfs_io -f -c "pwrite 0 64K" $MNT/foo cp --reflink=always $MNT/foo $MNT/bar echo echo "fiemap after cloning:" xfs_io -c "fiemap -v" $MNT/foo rm -f $MNT/bar echo echo "fiemap after removing file bar:" xfs_io -c "fiemap -v" $MNT/foo umount $MNT Running it before this patch, the extent is still listed as shared, it has the flag 0x2000 (FIEMAP_EXTENT_SHARED) set: $ ./test-1.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 Example reproducer for case 2): $ cat test-2.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV mount $DEV $MNT xfs_io -f -c "pwrite 0 64K" $MNT/foo cp --reflink=always $MNT/foo $MNT/bar # Flush delayed references to the extent tree and commit current # transaction. sync echo echo "fiemap after cloning:" xfs_io -c "fiemap -v" $MNT/foo rm -f $MNT/bar echo echo "fiemap after removing file bar:" xfs_io -c "fiemap -v" $MNT/foo umount $MNT Running it before this patch, the extent is still listed as shared, it has the flag 0x2000 (FIEMAP_EXTENT_SHARED) set: $ ./test-2.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 After this patch, after deleting bar in both tests, the extent is not reported with the 0x2000 flag anymore, it gets only the flag 0x1 (which is FIEMAP_EXTENT_LAST): $ ./test-1.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x1 $ ./test-2.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x1 These tests will later be converted to a test case for fstests. Fixes: dc046b10c8b7d4 ("Btrfs: make fiemap not blow when you have lots of snapshots") Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/btrfs/backref.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index baff31a147e7..7e8fac12f3f8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -137,6 +137,7 @@ struct share_check { u64 root_objectid; u64 inum; int share_count; + bool have_delayed_delete_refs; }; static inline int extent_is_shared(struct share_check *sc) @@ -881,13 +882,22 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, key.offset = ref->offset; /* - * Found a inum that doesn't match our known inum, we - * know it's shared. + * If we have a share check context and a reference for + * another inode, we can't exit immediately. This is + * because even if this is a BTRFS_ADD_DELAYED_REF + * reference we may find next a BTRFS_DROP_DELAYED_REF + * which cancels out this ADD reference. + * + * If this is a DROP reference and there was no previous + * ADD reference, then we need to signal that when we + * process references from the extent tree (through + * add_inline_refs() and add_keyed_refs()), we should + * not exit early if we find a reference for another + * inode, because one of the delayed DROP references + * may cancel that reference in the extent tree. */ - if (sc && sc->inum && ref->objectid != sc->inum) { - ret = BACKREF_FOUND_SHARED; - goto out; - } + if (sc && count < 0) + sc->have_delayed_delete_refs = true; ret = add_indirect_ref(fs_info, preftrees, ref->root, &key, 0, node->bytenr, count, sc, @@ -917,7 +927,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, } if (!ret) ret = extent_is_shared(sc); -out: + spin_unlock(&head->lock); return ret; } @@ -1020,7 +1030,8 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1030,6 +1041,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, ret = add_indirect_ref(fs_info, preftrees, root, &key, 0, bytenr, count, sc, GFP_NOFS); + break; } default: @@ -1119,7 +1131,8 @@ static int add_keyed_refs(struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1542,6 +1555,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, .root_objectid = root->root_key.objectid, .inum = inum, .share_count = 0, + .have_delayed_delete_refs = false, }; ulist_init(roots); @@ -1576,6 +1590,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, break; bytenr = node->val; shared.share_count = 0; + shared.have_delayed_delete_refs = false; cond_resched(); } -- Gitee From af70d390253a38f64e09eeaea503910b0388bd15 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 11 Oct 2022 13:16:52 +0100 Subject: [PATCH 26/79] btrfs: fix processing of delayed tree block refs during backref walking stable inclusion from stable-5.10.152 commit 57e157749ad9bce8e44db8dd951e3a363061ed42 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 943553ef9b51db303ab2b955c1025261abfdf6fb ] During backref walking, when processing a delayed reference with a type of BTRFS_TREE_BLOCK_REF_KEY, we have two bugs there: 1) We are accessing the delayed references extent_op, and its key, without the protection of the delayed ref head's lock; 2) If there's no extent op for the delayed ref head, we end up with an uninitialized key in the stack, variable 'tmp_op_key', and then pass it to add_indirect_ref(), which adds the reference to the indirect refs rb tree. This is wrong, because indirect references should have a NULL key when we don't have access to the key, and in that case they should be added to the indirect_missing_keys rb tree and not to the indirect rb tree. This means that if have BTRFS_TREE_BLOCK_REF_KEY delayed ref resulting from freeing an extent buffer, therefore with a count of -1, it will not cancel out the corresponding reference we have in the extent tree (with a count of 1), since both references end up in different rb trees. When using fiemap, where we often need to check if extents are shared through shared subtrees resulting from snapshots, it means we can incorrectly report an extent as shared when it's no longer shared. However this is temporary because after the transaction is committed the extent is no longer reported as shared, as running the delayed reference results in deleting the tree block reference from the extent tree. Outside the fiemap context, the result is unpredictable, as the key was not initialized but it's used when navigating the rb trees to insert and search for references (prelim_ref_compare()), and we expect all references in the indirect rb tree to have valid keys. The following reproducer triggers the second bug: $ cat test.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV mount -o compress $DEV $MNT # With a compressed 128M file we get a tree height of 2 (level 1 root). xfs_io -f -c "pwrite -b 1M 0 128M" $MNT/foo btrfs subvolume snapshot $MNT $MNT/snap # Fiemap should output 0x2008 in the flags column. # 0x2000 means shared extent # 0x8 means encoded extent (because it's compressed) echo echo "fiemap after snapshot, range [120M, 120M + 128K):" xfs_io -c "fiemap -v 120M 128K" $MNT/foo echo # Overwrite one extent and fsync to flush delalloc and COW a new path # in the snapshot's tree. # # After this we have a BTRFS_DROP_DELAYED_REF delayed ref of type # BTRFS_TREE_BLOCK_REF_KEY with a count of -1 for every COWed extent # buffer in the path. # # In the extent tree we have inline references of type # BTRFS_TREE_BLOCK_REF_KEY, with a count of 1, for the same extent # buffers, so they should cancel each other, and the extent buffers in # the fs tree should no longer be considered as shared. # echo "Overwriting file range [120M, 120M + 128K)..." xfs_io -c "pwrite -b 128K 120M 128K" $MNT/snap/foo xfs_io -c "fsync" $MNT/snap/foo # Fiemap should output 0x8 in the flags column. The extent in the range # [120M, 120M + 128K) is no longer shared, it's now exclusive to the fs # tree. echo echo "fiemap after overwrite range [120M, 120M + 128K):" xfs_io -c "fiemap -v 120M 128K" $MNT/foo echo umount $MNT Running it before this patch: $ ./test.sh (...) wrote 134217728/134217728 bytes at offset 0 128 MiB, 128 ops; 0.1152 sec (1.085 GiB/sec and 1110.5809 ops/sec) Create a snapshot of '/mnt/sdj' in '/mnt/sdj/snap' fiemap after snapshot, range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x2008 Overwriting file range [120M, 120M + 128K)... wrote 131072/131072 bytes at offset 125829120 128 KiB, 1 ops; 0.0001 sec (683.060 MiB/sec and 5464.4809 ops/sec) fiemap after overwrite range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x2008 The extent in the range [120M, 120M + 128K) is still reported as shared (0x2000 bit set) after overwriting that range and flushing delalloc, which is not correct - an entire path was COWed in the snapshot's tree and the extent is now only referenced by the original fs tree. Running it after this patch: $ ./test.sh (...) wrote 134217728/134217728 bytes at offset 0 128 MiB, 128 ops; 0.1198 sec (1.043 GiB/sec and 1068.2067 ops/sec) Create a snapshot of '/mnt/sdj' in '/mnt/sdj/snap' fiemap after snapshot, range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x2008 Overwriting file range [120M, 120M + 128K)... wrote 131072/131072 bytes at offset 125829120 128 KiB, 1 ops; 0.0001 sec (694.444 MiB/sec and 5555.5556 ops/sec) fiemap after overwrite range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x8 Now the extent is not reported as shared anymore. So fix this by passing a NULL key pointer to add_indirect_ref() when processing a delayed reference for a tree block if there's no extent op for our delayed ref head with a defined key. Also access the extent op only after locking the delayed ref head's lock. The reproducer will be converted later to a test case for fstests. Fixes: 86d5f994425252 ("btrfs: convert prelimary reference tracking to use rbtrees") Fixes: a6dbceafb915e8 ("btrfs: Remove unused op_key var from add_delayed_refs") Signed-off-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/btrfs/backref.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 7e8fac12f3f8..92cb16c0e5ee 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -818,16 +818,11 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct preftrees *preftrees, struct share_check *sc) { struct btrfs_delayed_ref_node *node; - struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct btrfs_key key; - struct btrfs_key tmp_op_key; struct rb_node *n; int count; int ret = 0; - if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); - spin_lock(&head->lock); for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, @@ -853,10 +848,16 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; + struct btrfs_key *key_ptr = NULL; + + if (head->extent_op && head->extent_op->update_key) { + btrfs_disk_key_to_cpu(&key, &head->extent_op->key); + key_ptr = &key; + } ref = btrfs_delayed_node_to_tree_ref(node); ret = add_indirect_ref(fs_info, preftrees, ref->root, - &tmp_op_key, ref->level + 1, + key_ptr, ref->level + 1, node->bytenr, count, sc, GFP_ATOMIC); break; -- Gitee From 7e0a2cbe992d8de3b622da5335cd20704b745ead Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 10 Oct 2022 13:34:23 -0700 Subject: [PATCH 27/79] ACPI: extlog: Handle multiple records stable inclusion from stable-5.10.152 commit fc8c6b8bb294b7c1b2853808648e7a2cec392b61 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit f6ec01da40e4139b41179f046044ee7c4f6370dc ] If there is no user space consumer of extlog_mem trace records, then Linux properly handles multiple error records in an ELOG block extlog_print() print_extlog_rcd() __print_extlog_rcd() cper_estatus_print() apei_estatus_for_each_section() But the other code path hard codes looking for a single record to output a trace record. Fix by using the same apei_estatus_for_each_section() iterator to step over all records. Fixes: 2dfb7d51a61d ("trace, RAS: Add eMCA trace event interface") Signed-off-by: Tony Luck Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/acpi/acpi_extlog.c | 33 ++++++++++++++++++++------------- 1 file changed, 20 insertions(+), 13 deletions(-) diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 72f1fb77abcd..e648158368a7 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -138,8 +139,8 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, int cpu = mce->extcpu; struct acpi_hest_generic_status *estatus, *tmp; struct acpi_hest_generic_data *gdata; - const guid_t *fru_id = &guid_null; - char *fru_text = ""; + const guid_t *fru_id; + char *fru_text; guid_t *sec_type; static u32 err_seq; @@ -160,17 +161,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, /* log event via trace */ err_seq++; - gdata = (struct acpi_hest_generic_data *)(tmp + 1); - if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) - fru_id = (guid_t *)gdata->fru_id; - if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) - fru_text = gdata->fru_text; - sec_type = (guid_t *)gdata->section_type; - if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { - struct cper_sec_mem_err *mem = (void *)(gdata + 1); - if (gdata->error_data_length >= sizeof(*mem)) - trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, - (u8)gdata->error_severity); + apei_estatus_for_each_section(tmp, gdata) { + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) + fru_id = (guid_t *)gdata->fru_id; + else + fru_id = &guid_null; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) + fru_text = gdata->fru_text; + else + fru_text = ""; + sec_type = (guid_t *)gdata->section_type; + if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { + struct cper_sec_mem_err *mem = (void *)(gdata + 1); + + if (gdata->error_data_length >= sizeof(*mem)) + trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, + (u8)gdata->error_severity); + } } out: -- Gitee From 94bc04acdd3d85ab39b6841f6528067212dc512c Mon Sep 17 00:00:00 2001 From: Mark Tomlinson Date: Mon, 10 Oct 2022 15:46:13 +1300 Subject: [PATCH 28/79] tipc: Fix recognition of trial period stable inclusion from stable-5.10.152 commit 1f4ed95ce617fbb4f2e3c3bf54fc3f8c72092fe6 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 28be7ca4fcfd69a2d52aaa331adbf9dbe91f9e6e ] The trial period exists until jiffies is after addr_trial_end. But as jiffies will eventually overflow, just using time_after will eventually give incorrect results. As the node address is set once the trial period ends, this can be used to know that we are not in the trial period. Fixes: e415577f57f4 ("tipc: correct discovery message handling during address trial period") Signed-off-by: Mark Tomlinson Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/tipc/discover.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 14bc20604051..2ae268b67465 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -147,8 +147,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) -- Gitee From 8462e19d0d80a4eafdca9201227a786456fc4dd2 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Wed, 12 Oct 2022 17:25:14 +0200 Subject: [PATCH 29/79] tipc: fix an information leak in tipc_topsrv_kern_subscr stable inclusion from stable-5.10.152 commit e558e148938442dd49628cd7ef61c360832bef31 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 777ecaabd614d47c482a5c9031579e66da13989a ] Use a 8-byte write to initialize sub.usr_handle in tipc_topsrv_kern_subscr(), otherwise four bytes remain uninitialized when issuing setsockopt(..., SOL_TIPC, ...). This resulted in an infoleak reported by KMSAN when the packet was received: ===================================================== BUG: KMSAN: kernel-infoleak in copyout+0xbc/0x100 lib/iov_iter.c:169 instrument_copy_to_user ./include/linux/instrumented.h:121 copyout+0xbc/0x100 lib/iov_iter.c:169 _copy_to_iter+0x5c0/0x20a0 lib/iov_iter.c:527 copy_to_iter ./include/linux/uio.h:176 simple_copy_to_iter+0x64/0xa0 net/core/datagram.c:513 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:419 skb_copy_datagram_iter+0x58/0x200 net/core/datagram.c:527 skb_copy_datagram_msg ./include/linux/skbuff.h:3903 packet_recvmsg+0x521/0x1e70 net/packet/af_packet.c:3469 ____sys_recvmsg+0x2c4/0x810 net/socket.c:? ___sys_recvmsg+0x217/0x840 net/socket.c:2743 __sys_recvmsg net/socket.c:2773 __do_sys_recvmsg net/socket.c:2783 __se_sys_recvmsg net/socket.c:2780 __x64_sys_recvmsg+0x364/0x540 net/socket.c:2780 do_syscall_x64 arch/x86/entry/common.c:50 do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd arch/x86/entry/entry_64.S:120 ... Uninit was stored to memory at: tipc_sub_subscribe+0x42d/0xb50 net/tipc/subscr.c:156 tipc_conn_rcv_sub+0x246/0x620 net/tipc/topsrv.c:375 tipc_topsrv_kern_subscr+0x2e8/0x400 net/tipc/topsrv.c:579 tipc_group_create+0x4e7/0x7d0 net/tipc/group.c:190 tipc_sk_join+0x2a8/0x770 net/tipc/socket.c:3084 tipc_setsockopt+0xae5/0xe40 net/tipc/socket.c:3201 __sys_setsockopt+0x87f/0xdc0 net/socket.c:2252 __do_sys_setsockopt net/socket.c:2263 __se_sys_setsockopt net/socket.c:2260 __x64_sys_setsockopt+0xe0/0x160 net/socket.c:2260 do_syscall_x64 arch/x86/entry/common.c:50 do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd arch/x86/entry/entry_64.S:120 Local variable sub created at: tipc_topsrv_kern_subscr+0x57/0x400 net/tipc/topsrv.c:562 tipc_group_create+0x4e7/0x7d0 net/tipc/group.c:190 Bytes 84-87 of 88 are uninitialized Memory access of size 88 starts at ffff88801ed57cd0 Data copied to user address 0000000020000400 ... ===================================================== Signed-off-by: Alexander Potapenko Fixes: 026321c6d056a5 ("tipc: rename tipc_server to tipc_topsrv") Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/tipc/topsrv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 13f3143609f9..d9e2c0fea3f2 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -568,7 +568,7 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; con = tipc_conn_alloc(tipc_topsrv(net)); if (IS_ERR(con)) -- Gitee From a9ca0c0c4342f29cafa9c4368c217a7e7c68ad94 Mon Sep 17 00:00:00 2001 From: Jan Sokolowski Date: Wed, 12 Oct 2022 13:54:40 -0700 Subject: [PATCH 30/79] i40e: Fix DMA mappings leak stable inclusion from stable-5.10.152 commit ed5baf3d0a33caaca4cd4073ebb0854cc77a616d category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit aae425efdfd1b1d8452260a3cb49344ebf20b1f5 ] During reallocation of RX buffers, new DMA mappings are created for those buffers. steps for reproduction: while : do for ((i=0; i<=8160; i=i+32)) do ethtool -G enp130s0f0 rx $i tx $i sleep 0.5 ethtool -g enp130s0f0 done done This resulted in crash: i40e 0000:01:00.1: Unable to allocate memory for the Rx descriptor ring, size=65536 Driver BUG WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:141 xdp_rxq_info_unreg+0x43/0x50 Call Trace: i40e_free_rx_resources+0x70/0x80 [i40e] i40e_set_ringparam+0x27c/0x800 [i40e] ethnl_set_rings+0x1b2/0x290 genl_family_rcv_msg_doit.isra.15+0x10f/0x150 genl_family_rcv_msg+0xb3/0x160 ? rings_fill_reply+0x1a0/0x1a0 genl_rcv_msg+0x47/0x90 ? genl_family_rcv_msg+0x160/0x160 netlink_rcv_skb+0x4c/0x120 genl_rcv+0x24/0x40 netlink_unicast+0x196/0x230 netlink_sendmsg+0x204/0x3d0 sock_sendmsg+0x4c/0x50 __sys_sendto+0xee/0x160 ? handle_mm_fault+0xbe/0x1e0 ? syscall_trace_enter+0x1d3/0x2c0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x1a0 entry_SYSCALL_64_after_hwframe+0x65/0xca RIP: 0033:0x7f5eac8b035b Missing register, driver bug WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:119 xdp_rxq_info_unreg_mem_model+0x69/0x140 Call Trace: xdp_rxq_info_unreg+0x1e/0x50 i40e_free_rx_resources+0x70/0x80 [i40e] i40e_set_ringparam+0x27c/0x800 [i40e] ethnl_set_rings+0x1b2/0x290 genl_family_rcv_msg_doit.isra.15+0x10f/0x150 genl_family_rcv_msg+0xb3/0x160 ? rings_fill_reply+0x1a0/0x1a0 genl_rcv_msg+0x47/0x90 ? genl_family_rcv_msg+0x160/0x160 netlink_rcv_skb+0x4c/0x120 genl_rcv+0x24/0x40 netlink_unicast+0x196/0x230 netlink_sendmsg+0x204/0x3d0 sock_sendmsg+0x4c/0x50 __sys_sendto+0xee/0x160 ? handle_mm_fault+0xbe/0x1e0 ? syscall_trace_enter+0x1d3/0x2c0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x1a0 entry_SYSCALL_64_after_hwframe+0x65/0xca RIP: 0033:0x7f5eac8b035b This was caused because of new buffers with different RX ring count should substitute older ones, but those buffers were freed in i40e_configure_rx_ring and reallocated again with i40e_alloc_rx_bi, thus kfree on rx_bi caused leak of already mapped DMA. Fix this by reallocating ZC with rx_bi_zc struct when BPF program loads. Additionally reallocate back to rx_bi when BPF program unloads. If BPF program is loaded/unloaded and XSK pools are created, reallocate RX queues accordingly in XSP_SETUP_XSK_POOL handler. Fixes: be1222b585fd ("i40e: Separate kernel allocated rx_bi rings from AF_XDP rings") Signed-off-by: Jan Sokolowski Signed-off-by: Mateusz Palczewski Signed-off-by: Jacob Keller Tested-by: Chandan (A Contingent Worker at Intel) Tested-by: Gurucharan (A Contingent worker at Intel) Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- .../net/ethernet/intel/i40e/i40e_ethtool.c | 3 - drivers/net/ethernet/intel/i40e/i40e_main.c | 16 +++-- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 13 ++-- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 1 - drivers/net/ethernet/intel/i40e/i40e_xsk.c | 67 ++++++++++++++++--- drivers/net/ethernet/intel/i40e/i40e_xsk.h | 2 +- 6 files changed, 74 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 63054061966e..cc5f5c237774 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2081,9 +2081,6 @@ static int i40e_set_ringparam(struct net_device *netdev, */ rx_rings[i].tail = hw->hw_addr + I40E_PRTGEN_STATUS; err = i40e_setup_rx_descriptors(&rx_rings[i]); - if (err) - goto rx_unwind; - err = i40e_alloc_rx_bi(&rx_rings[i]); if (err) goto rx_unwind; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c7f243ddbcf7..ea6a984c6d12 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3409,12 +3409,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->vsi->type == I40E_VSI_MAIN) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - kfree(ring->rx_bi); ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - ret = i40e_alloc_rx_bi_zc(ring); - if (ret) - return ret; ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on @@ -3432,9 +3428,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->queue_index); } else { - ret = i40e_alloc_rx_bi(ring); - if (ret) - return ret; ring->rx_buf_len = vsi->rx_buf_len; if (ring->vsi->type == I40E_VSI_MAIN) { ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -12684,6 +12677,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, i40e_reset_and_rebuild(pf, true, true); } + if (!i40e_enabled_xdp_vsi(vsi) && prog) { + if (i40e_realloc_rx_bi_zc(vsi, true)) + return -ENOMEM; + } else if (i40e_enabled_xdp_vsi(vsi) && !prog) { + if (i40e_realloc_rx_bi_zc(vsi, false)) + return -ENOMEM; + } + for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); @@ -12916,6 +12917,7 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) i40e_queue_pair_disable_irq(vsi, queue_pair); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 5ad28129fab2..43be33d87e39 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1305,14 +1305,6 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) return -ENOMEM; } -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count; - - rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi ? 0 : -ENOMEM; -} - static void i40e_clear_rx_bi(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count); @@ -1443,6 +1435,11 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->xdp_prog = rx_ring->vsi->xdp_prog; + rx_ring->rx_bi = + kcalloc(rx_ring->count, sizeof(*rx_ring->rx_bi), GFP_KERNEL); + if (!rx_ring->rx_bi) + return -ENOMEM; + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 93ac201f68b8..af843e8169f7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -465,7 +465,6 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 75e4a698c3db..7f1226123629 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -9,14 +9,6 @@ #include "i40e_txrx_common.h" #include "i40e_xsk.h" -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count; - - rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi_zc ? 0 : -ENOMEM; -} - void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi_zc, 0, @@ -28,6 +20,58 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) return &rx_ring->rx_bi_zc[idx]; } +/** + * i40e_realloc_rx_xdp_bi - reallocate SW ring for either XSK or normal buffer + * @rx_ring: Current rx ring + * @pool_present: is pool for XSK present + * + * Try allocating memory and return ENOMEM, if failed to allocate. + * If allocation was successful, substitute buffer with allocated one. + * Returns 0 on success, negative on failure + */ +static int i40e_realloc_rx_xdp_bi(struct i40e_ring *rx_ring, bool pool_present) +{ + size_t elem_size = pool_present ? sizeof(*rx_ring->rx_bi_zc) : + sizeof(*rx_ring->rx_bi); + void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); + + if (!sw_ring) + return -ENOMEM; + + if (pool_present) { + kfree(rx_ring->rx_bi); + rx_ring->rx_bi = NULL; + rx_ring->rx_bi_zc = sw_ring; + } else { + kfree(rx_ring->rx_bi_zc); + rx_ring->rx_bi_zc = NULL; + rx_ring->rx_bi = sw_ring; + } + return 0; +} + +/** + * i40e_realloc_rx_bi_zc - reallocate rx SW rings + * @vsi: Current VSI + * @zc: is zero copy set + * + * Reallocate buffer for rx_rings that might be used by XSK. + * XDP requires more memory, than rx_buf provides. + * Returns 0 on success, negative on failure + */ +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc) +{ + struct i40e_ring *rx_ring; + unsigned long q; + + for_each_set_bit(q, vsi->af_xdp_zc_qps, vsi->alloc_queue_pairs) { + rx_ring = vsi->rx_rings[q]; + if (i40e_realloc_rx_xdp_bi(rx_ring, zc)) + return -ENOMEM; + } + return 0; +} + /** * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a * certain ring/qid @@ -68,6 +112,10 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, if (err) return err; + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], true); + if (err) + return err; + err = i40e_queue_pair_enable(vsi, qid); if (err) return err; @@ -112,6 +160,9 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR); if (if_running) { + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], false); + if (err) + return err; err = i40e_queue_pair_enable(vsi, qid); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 7adfd8539247..36f5b6d20601 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -17,7 +17,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring); int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring); +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc); void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring); #endif /* _I40E_XSK_H_ */ -- Gitee From 5e82a130c69ef367c02409ee2c514edf52848c08 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= Date: Sun, 9 Oct 2022 20:27:47 +0200 Subject: [PATCH 31/79] HID: magicmouse: Do not set BTN_MOUSE on double report MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stable inclusion from stable-5.10.152 commit 39d10f0dfb7201cbd722706e0c428e4f7d89281f category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit bb5f0c855dcfc893ae5ed90e4c646bde9e4498bf ] Under certain conditions the Magic Trackpad can group 2 reports in a single packet. The packet is split and the raw event function is invoked recursively for each part. However, after processing each part, the BTN_MOUSE status is updated, sending multiple click events. [1] Return after processing double reports to avoid this issue. Link: https://gitlab.freedesktop.org/libinput/libinput/-/issues/811 # [1] Fixes: a462230e16ac ("HID: magicmouse: enable Magic Trackpad support") Reported-by: Nulo Signed-off-by: José Expósito Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20221009182747.90730-1-jose.exposito89@gmail.com Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/hid/hid-magicmouse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index fc4c07459753..28158d2f2352 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -387,7 +387,7 @@ static int magicmouse_raw_event(struct hid_device *hdev, magicmouse_raw_event(hdev, report, data + 2, data[1]); magicmouse_raw_event(hdev, report, data + 2 + data[1], size - 2 - data[1]); - break; + return 0; default: return 0; } -- Gitee From 8f8d60669b3026988a5958ceda5324c457f96aa3 Mon Sep 17 00:00:00 2001 From: Jonathan Cooper Date: Thu, 13 Oct 2022 10:55:53 +0100 Subject: [PATCH 32/79] sfc: Change VF mac via PF as first preference if available. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stable inclusion from stable-5.10.152 commit c8310a99e7e4ad658aa5160fe817533d0d7069fe category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit a8aed7b35becfd21f22a77c7014029ea837b018f ] Changing a VF's mac address through the VF (rather than via the PF) fails with EPERM because the latter part of efx_ef10_set_mac_address attempts to change the vport mac address list as the VF. Even with this fixed it still fails with EBUSY because the vadaptor is still assigned on the VF - the vadaptor reassignment must be within a section where the VF has torn down its state. A major reason this has broken is because we have two functions that ostensibly do the same thing - have a PF and VF cooperate to change a VF mac address. Rather than do this, if we are changing the mac of a VF that has a link to the PF in the same VM then simply call sriov_set_vf_mac instead, which is a proven working function that does that. If there is no PF available, or that fails non-fatally, then attempt to change the VF's mac address as we would a PF, without updating the PF's data. Test case: Create a VF: echo 1 > /sys/class/net//device/sriov_numvfs Set the mac address of the VF directly: ip link set addr 00:11:22:33:44:55 Set the MAC address of the VF via the PF: ip link set vf 0 mac 00:11:22:33:44:66 Without this patch the last command will fail with ENOENT. Signed-off-by: Jonathan Cooper Reported-by: Íñigo Huguet Fixes: 910c8789a777 ("set the MAC address using MC_CMD_VADAPTOR_SET_MAC") Acked-by: Edward Cree Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/net/ethernet/sfc/ef10.c | 58 ++++++++++++++------------------- 1 file changed, 24 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 5b7413305be6..eb1be7302082 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3255,6 +3255,30 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) bool was_enabled = efx->port_enabled; int rc; +#ifdef CONFIG_SFC_SRIOV + /* If this function is a VF and we have access to the parent PF, + * then use the PF control path to attempt to change the VF MAC address. + */ + if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { + struct efx_nic *efx_pf = pci_get_drvdata(efx->pci_dev->physfn); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + u8 mac[ETH_ALEN]; + + /* net_dev->dev_addr can be zeroed by efx_net_stop in + * efx_ef10_sriov_set_vf_mac, so pass in a copy. + */ + ether_addr_copy(mac, efx->net_dev->dev_addr); + + rc = efx_ef10_sriov_set_vf_mac(efx_pf, nic_data->vf_index, mac); + if (!rc) + return 0; + + netif_dbg(efx, drv, efx->net_dev, + "Updating VF mac via PF failed (%d), setting directly\n", + rc); + } +#endif + efx_device_detach_sync(efx); efx_net_stop(efx->net_dev); @@ -3277,40 +3301,6 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) efx_net_open(efx->net_dev); efx_device_attach_if_not_resetting(efx); -#ifdef CONFIG_SFC_SRIOV - if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { - struct efx_ef10_nic_data *nic_data = efx->nic_data; - struct pci_dev *pci_dev_pf = efx->pci_dev->physfn; - - if (rc == -EPERM) { - struct efx_nic *efx_pf; - - /* Switch to PF and change MAC address on vport */ - efx_pf = pci_get_drvdata(pci_dev_pf); - - rc = efx_ef10_sriov_set_vf_mac(efx_pf, - nic_data->vf_index, - efx->net_dev->dev_addr); - } else if (!rc) { - struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf); - struct efx_ef10_nic_data *nic_data = efx_pf->nic_data; - unsigned int i; - - /* MAC address successfully changed by VF (with MAC - * spoofing) so update the parent PF if possible. - */ - for (i = 0; i < efx_pf->vf_count; ++i) { - struct ef10_vf *vf = nic_data->vf + i; - - if (vf->efx == efx) { - ether_addr_copy(vf->mac, - efx->net_dev->dev_addr); - return 0; - } - } - } - } else -#endif if (rc == -EPERM) { netif_err(efx, drv, efx->net_dev, "Cannot change MAC address; use sfboot to enable" -- Gitee From 48f787d8ef53de4aabd218493da844af9865a350 Mon Sep 17 00:00:00 2001 From: Xiaobo Liu Date: Fri, 14 Oct 2022 10:05:40 +0800 Subject: [PATCH 33/79] net/atm: fix proc_mpc_write incorrect return value stable inclusion from stable-5.10.152 commit 118f412bedc5843032d65f41eb4e635a830c2fa8 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit d8bde3bf7f82dac5fc68a62c2816793a12cafa2a ] Then the input contains '\0' or '\n', proc_mpc_write has read them, so the return value needs +1. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Xiaobo Liu Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/atm/mpoa_proc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 829db9eba0cb..aaf64b953915 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -219,11 +219,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, if (!page) return -ENOMEM; - for (p = page, len = 0; len < nbytes; p++, len++) { + for (p = page, len = 0; len < nbytes; p++) { if (get_user(*p, buff++)) { free_page((unsigned long)page); return -EFAULT; } + len += 1; if (*p == '\0' || *p == '\n') break; } -- Gitee From 1837d6f4f485113737104004a3257db51356071a Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Fri, 14 Oct 2022 12:17:35 +0530 Subject: [PATCH 34/79] net: phy: dp83867: Extend RX strap quirk for SGMII mode stable inclusion from stable-5.10.152 commit 05cc22c0085e18627df110facd731359b83be7ef category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 0c9efbd5c50c64ead434960a404c9c9a097b0403 ] When RX strap in HW is not set to MODE 3 or 4, bit 7 and 8 in CF4 register should be set. The former is already handled in dp83867_config_init; add the latter in SGMII specific initialization. Fixes: 2a10154abcb7 ("net: phy: dp83867: Add TI dp83867 phy") Signed-off-by: Harini Katakam Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/net/phy/dp83867.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index f86acad0aad4..c8031e297faf 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -757,6 +757,14 @@ static int dp83867_config_init(struct phy_device *phydev) else val &= ~DP83867_SGMII_TYPE; phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_SGMIICTL, val); + + /* This is a SW workaround for link instability if RX_CTRL is + * not strapped to mode 3 or 4 in HW. This is required for SGMII + * in addition to clearing bit 7, handled above. + */ + if (dp83867->rxctrl_strap_quirk) + phy_set_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + BIT(8)); } val = phy_read(phydev, DP83867_CFG3); -- Gitee From 8efb43558a558735f0aef5384d82c1e58c74c3ee Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Mon, 17 Oct 2022 22:45:22 +0800 Subject: [PATCH 35/79] cifs: Fix xid leak in cifs_copy_file_range() stable inclusion from stable-5.10.152 commit bf49d4fe4ab7b8d812927a2c7b514864d5fc1bb2 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 9a97df404a402fe1174d2d1119f87ff2a0ca2fe9 ] If the file is used by swap, before return -EOPNOTSUPP, should free the xid, otherwise, the xid will be leaked. Fixes: 4e8aea30f775 ("smb3: enable swap on SMB3 mounts") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Zhang Xiaoxu Signed-off-by: Steve French Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/cifs/cifsfs.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index bc957e6ca48b..f442ef8b65da 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1221,8 +1221,11 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, ssize_t rc; struct cifsFileInfo *cfile = dst_file->private_data; - if (cfile->swapfile) - return -EOPNOTSUPP; + if (cfile->swapfile) { + rc = -EOPNOTSUPP; + free_xid(xid); + return rc; + } rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, len, flags); -- Gitee From 63d55e733c5b3c975ce04bdb10efc6b00626893e Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Mon, 17 Oct 2022 22:45:23 +0800 Subject: [PATCH 36/79] cifs: Fix xid leak in cifs_flock() stable inclusion from stable-5.10.152 commit 2d08311aa3056a84bfdc09bc47777de6a9b16c30 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 575e079c782b9862ec2626403922d041a42e6ed6 ] If not flock, before return -ENOLCK, should free the xid, otherwise, the xid will be leaked. Fixes: d0677992d2af ("cifs: add support for flock") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Zhang Xiaoxu Signed-off-by: Steve French Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/cifs/file.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index a648146e49cf..144064dc0d38 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1735,11 +1735,13 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) struct cifsFileInfo *cfile; __u32 type; - rc = -EACCES; xid = get_xid(); - if (!(fl->fl_flags & FL_FLOCK)) - return -ENOLCK; + if (!(fl->fl_flags & FL_FLOCK)) { + rc = -ENOLCK; + free_xid(xid); + return rc; + } cfile = (struct cifsFileInfo *)file->private_data; tcon = tlink_tcon(cfile->tlink); @@ -1758,8 +1760,9 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) * if no lock or unlock then nothing to do since we do not * know what it is */ + rc = -EOPNOTSUPP; free_xid(xid); - return -EOPNOTSUPP; + return rc; } rc = cifs_setlk(file, fl, type, wait_flag, posix_lck, lock, unlock, -- Gitee From b7b4f6a1b1085e5eefb4f729329ec6387b43f9c3 Mon Sep 17 00:00:00 2001 From: Zhang Xiaoxu Date: Mon, 17 Oct 2022 22:45:24 +0800 Subject: [PATCH 37/79] cifs: Fix xid leak in cifs_ses_add_channel() stable inclusion from stable-5.10.152 commit 7286f875510486fdc2fc426b7c826262e2283a65 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit e909d054bdea75ef1ec48c18c5936affdaecbb2c ] Before return, should free the xid, otherwise, the xid will be leaked. Fixes: d70e9fa55884 ("cifs: try opening channels after mounting") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Zhang Xiaoxu Signed-off-by: Steve French Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/cifs/sess.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index d58c5ffeca0d..cf6fd138d8d5 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -306,6 +306,7 @@ cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) cifs_put_tcp_session(chan->server, 0); unload_nls(vol.local_nls); + free_xid(xid); return rc; } -- Gitee From aa30cb8a9f12e5f66a02558679692b86eb217b21 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Oct 2022 16:59:28 +0000 Subject: [PATCH 38/79] net: hsr: avoid possible NULL deref in skb_clone() stable inclusion from stable-5.10.152 commit ff7ba766758313129794f150bbc4d351b5e17a53 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit d8b57135fd9ffe9a5b445350a686442a531c5339 ] syzbot got a crash [1] in skb_clone(), caused by a bug in hsr_get_untagged_frame(). When/if create_stripped_skb_hsr() returns NULL, we must not attempt to call skb_clone(). While we are at it, replace a WARN_ONCE() by netdev_warn_once(). [1] general protection fault, probably for non-canonical address 0xdffffc000000000f: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000078-0x000000000000007f] CPU: 1 PID: 754 Comm: syz-executor.0 Not tainted 6.0.0-syzkaller-02734-g0326074ff465 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 RIP: 0010:skb_clone+0x108/0x3c0 net/core/skbuff.c:1641 Code: 93 02 00 00 49 83 7c 24 28 00 0f 85 e9 00 00 00 e8 5d 4a 29 fa 4c 8d 75 7e 48 b8 00 00 00 00 00 fc ff df 4c 89 f2 48 c1 ea 03 <0f> b6 04 02 4c 89 f2 83 e2 07 38 d0 7f 08 84 c0 0f 85 9e 01 00 00 RSP: 0018:ffffc90003ccf4e0 EFLAGS: 00010207 RAX: dffffc0000000000 RBX: ffffc90003ccf5f8 RCX: ffffc9000c24b000 RDX: 000000000000000f RSI: ffffffff8751cb13 RDI: 0000000000000000 RBP: 0000000000000000 R08: 00000000000000f0 R09: 0000000000000140 R10: fffffbfff181d972 R11: 0000000000000000 R12: ffff888161fc3640 R13: 0000000000000a20 R14: 000000000000007e R15: ffffffff8dc5f620 FS: 00007feb621e4700(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007feb621e3ff8 CR3: 00000001643a9000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: hsr_get_untagged_frame+0x4e/0x610 net/hsr/hsr_forward.c:164 hsr_forward_do net/hsr/hsr_forward.c:461 [inline] hsr_forward_skb+0xcca/0x1d50 net/hsr/hsr_forward.c:623 hsr_handle_frame+0x588/0x7c0 net/hsr/hsr_slave.c:69 __netif_receive_skb_core+0x9fe/0x38f0 net/core/dev.c:5379 __netif_receive_skb_one_core+0xae/0x180 net/core/dev.c:5483 __netif_receive_skb+0x1f/0x1c0 net/core/dev.c:5599 netif_receive_skb_internal net/core/dev.c:5685 [inline] netif_receive_skb+0x12f/0x8d0 net/core/dev.c:5744 tun_rx_batched+0x4ab/0x7a0 drivers/net/tun.c:1544 tun_get_user+0x2686/0x3a00 drivers/net/tun.c:1995 tun_chr_write_iter+0xdb/0x200 drivers/net/tun.c:2025 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9e9/0xdd0 fs/read_write.c:584 ksys_write+0x127/0x250 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: f266a683a480 ("net/hsr: Better frame dispatch") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20221017165928.2150130-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/hsr/hsr_forward.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index baf4765be6d7..908324b46328 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -108,15 +108,15 @@ struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port) { if (!frame->skb_std) { - if (frame->skb_hsr) { + if (frame->skb_hsr) frame->skb_std = create_stripped_skb_hsr(frame->skb_hsr, frame); - } else { - /* Unexpected */ - WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", - __FILE__, __LINE__, port->dev->name); + else + netdev_warn_once(port->dev, + "Unexpected frame received in hsr_get_untagged_frame()\n"); + + if (!frame->skb_std) return NULL; - } } return skb_clone(frame->skb_std, GFP_ATOMIC); -- Gitee From 33f01578bd647951c4ab73329def0308ce65b014 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 17 Oct 2022 16:31:23 -0700 Subject: [PATCH 39/79] ionic: catch NULL pointer issue on reconfig stable inclusion from stable-5.10.152 commit 191d71c6357ef6e64b07e37b1e28c44480526d5a category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit aa1d7e1267c12e07d979aa34c613716a89029db2 ] It's possible that the driver will dereference a qcq that doesn't exist when calling ionic_reconfigure_queues(), which causes a page fault BUG. If a reduction in the number of queues is followed by a different reconfig such as changing the ring size, the driver can hit a NULL pointer when trying to clean up non-existent queues. Fix this by checking to make sure both the qcqs array and qcq entry exists bofore trying to use and free the entry. Fixes: 101b40a0171f ("ionic: change queue count with no reset") Signed-off-by: Brett Creeley Signed-off-by: Shannon Nelson Link: https://lore.kernel.org/r/20221017233123.15869-1-snelson@pensando.io Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index e42520f909fe..cb12d0171517 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2383,11 +2383,15 @@ int ionic_reconfigure_queues(struct ionic_lif *lif, * than the full array, but leave the qcq shells in place */ for (i = lif->nxqs; i < lif->ionic->ntxqs_per_lif; i++) { - lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->txqcqs[i]); + if (lif->txqcqs && lif->txqcqs[i]) { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->txqcqs[i]); + } - lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->rxqcqs[i]); + if (lif->rxqcqs && lif->rxqcqs[i]) { + lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->rxqcqs[i]); + } } return err; -- Gitee From 3f3eaed70492616d87741a2f16b13bbd22926498 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 19 Jan 2021 07:43:18 +0100 Subject: [PATCH 40/79] nvme-hwmon: rework to avoid devm allocation stable inclusion from stable-5.10.152 commit bc17f727b005921fc3b8651daefa053200c57cf0 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit ed7770f6628691c13c9423bce7eee7cff2399c12 ] The original design to use device-managed resource allocation doesn't really work as the NVMe controller has a vastly different lifetime than the hwmon sysfs attributes, causing warning about duplicate sysfs entries upon reconnection. This patch reworks the hwmon allocation to avoid device-managed resource allocation, and uses the NVMe controller as parent for the sysfs attributes. Cc: Guenter Roeck Signed-off-by: Hannes Reinecke Tested-by: Enzo Matsumiya Tested-by: Daniel Wagner Signed-off-by: Christoph Hellwig Stable-dep-of: c94b7f9bab22 ("nvme-hwmon: kmalloc the NVME SMART log buffer") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/nvme/host/core.c | 1 + drivers/nvme/host/hwmon.c | 31 +++++++++++++++++++++---------- drivers/nvme/host/nvme.h | 8 ++++++++ 3 files changed, 30 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a19ac13ae546..d5c1bd62e264 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4465,6 +4465,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { + nvme_hwmon_exit(ctrl); nvme_fault_inject_fini(&ctrl->fault_inject); dev_pm_qos_hide_latency_tolerance(ctrl->device); cdev_device_del(&ctrl->cdev, ctrl->device); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 552dbc04567b..8f9e96986780 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -223,12 +223,12 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = { int nvme_hwmon_init(struct nvme_ctrl *ctrl) { - struct device *dev = ctrl->dev; + struct device *dev = ctrl->device; struct nvme_hwmon_data *data; struct device *hwmon; int err; - data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return 0; @@ -237,19 +237,30 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) err = nvme_hwmon_get_smart_log(data); if (err) { - dev_warn(ctrl->device, - "Failed to read smart log (error %d)\n", err); - devm_kfree(dev, data); + dev_warn(dev, "Failed to read smart log (error %d)\n", err); + kfree(data); return err; } - hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, - &nvme_hwmon_chip_info, - NULL); + hwmon = hwmon_device_register_with_info(dev, "nvme", + data, &nvme_hwmon_chip_info, + NULL); if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); - devm_kfree(dev, data); + kfree(data); } - + ctrl->hwmon_device = hwmon; return 0; } + +void nvme_hwmon_exit(struct nvme_ctrl *ctrl) +{ + if (ctrl->hwmon_device) { + struct nvme_hwmon_data *data = + dev_get_drvdata(ctrl->hwmon_device); + + hwmon_device_unregister(ctrl->hwmon_device); + ctrl->hwmon_device = NULL; + kfree(data); + } +} diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ec3a8d582a0f..d3d5b3545802 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -257,6 +257,9 @@ struct nvme_ctrl { struct rw_semaphore namespaces_rwsem; struct device ctrl_device; struct device *device; /* char device */ +#ifdef CONFIG_NVME_HWMON + struct device *hwmon_device; +#endif struct cdev cdev; struct work_struct reset_work; struct work_struct delete_work; @@ -891,11 +894,16 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) #ifdef CONFIG_NVME_HWMON int nvme_hwmon_init(struct nvme_ctrl *ctrl); +void nvme_hwmon_exit(struct nvme_ctrl *ctrl); #else static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl) { return 0; } + +static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl) +{ +} #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, -- Gitee From b8628b37663fe719d1ca61a9e454842053023d64 Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Fri, 12 Feb 2021 10:30:15 +0100 Subject: [PATCH 41/79] nvme-hwmon: Return error code when registration fails stable inclusion from stable-5.10.152 commit 67106ac27243313beb58097449555f92ea5947ec category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 78570f8873c8cd44c12714c7fa7db2601ec5617d ] The hwmon pointer wont be NULL if the registration fails. Though the exit code path will assign it to ctrl->hwmon_device. Later nvme_hwmon_exit() will try to free the invalid pointer. Avoid this by returning the error code from hwmon_device_register_with_info(). Fixes: ed7770f66286 ("nvme/hwmon: rework to avoid devm allocation") Signed-off-by: Daniel Wagner Signed-off-by: Christoph Hellwig Stable-dep-of: c94b7f9bab22 ("nvme-hwmon: kmalloc the NVME SMART log buffer") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/nvme/host/hwmon.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 8f9e96986780..0a586d712920 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -248,6 +248,7 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); kfree(data); + return PTR_ERR(hwmon); } ctrl->hwmon_device = hwmon; return 0; -- Gitee From 71c2f78ad1e48d76be4bf70507da99f5afb3f35e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 18 Oct 2022 16:55:55 +0200 Subject: [PATCH 42/79] nvme-hwmon: consistently ignore errors from nvme_hwmon_init stable inclusion from stable-5.10.152 commit 770b7e3a2c1f32e82c5c9143d0a3670e9ea95a5f category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 6b8cf94005187952f794c0c4ed3920a1e8accfa3 ] An NVMe controller works perfectly fine even when the hwmon initialization fails. Stop returning errors that do not come from a controller reset from nvme_hwmon_init to handle this case consistently. Signed-off-by: Christoph Hellwig Reviewed-by: Guenter Roeck Reviewed-by: Serge Semin Stable-dep-of: c94b7f9bab22 ("nvme-hwmon: kmalloc the NVME SMART log buffer") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/nvme/host/core.c | 6 +++++- drivers/nvme/host/hwmon.c | 13 ++++++++----- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d5c1bd62e264..fe2dfe0de1fd 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3212,8 +3212,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) return ret; if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) { + /* + * Do not return errors unless we are in a controller reset, + * the controller works perfectly fine without hwmon. + */ ret = nvme_hwmon_init(ctrl); - if (ret < 0) + if (ret == -EINTR) return ret; } diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 0a586d712920..23918bb7bdca 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -230,7 +230,7 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) - return 0; + return -ENOMEM; data->ctrl = ctrl; mutex_init(&data->read_lock); @@ -238,8 +238,7 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) err = nvme_hwmon_get_smart_log(data); if (err) { dev_warn(dev, "Failed to read smart log (error %d)\n", err); - kfree(data); - return err; + goto err_free_data; } hwmon = hwmon_device_register_with_info(dev, "nvme", @@ -247,11 +246,15 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) NULL); if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); - kfree(data); - return PTR_ERR(hwmon); + err = PTR_ERR(hwmon); + goto err_free_data; } ctrl->hwmon_device = hwmon; return 0; + +err_free_data: + kfree(data); + return err; } void nvme_hwmon_exit(struct nvme_ctrl *ctrl) -- Gitee From 1cb24d3212c3a8a521d4f38a0ddf0a468093e0c6 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Tue, 18 Oct 2022 17:33:52 +0200 Subject: [PATCH 43/79] nvme-hwmon: kmalloc the NVME SMART log buffer stable inclusion from stable-5.10.152 commit 2008ad08a2aee0aa8d6201c509bf6546f0df1183 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit c94b7f9bab22ac504f9153767676e659988575ad ] Recent commit 52fde2c07da6 ("nvme: set dma alignment to dword") has caused a regression on our platform. It turned out that the nvme_get_log() method invocation caused the nvme_hwmon_data structure instance corruption. In particular the nvme_hwmon_data.ctrl pointer was overwritten either with zeros or with garbage. After some research we discovered that the problem happened even before the actual NVME DMA execution, but during the buffer mapping. Since our platform is DMA-noncoherent, the mapping implied the cache-line invalidations or write-backs depending on the DMA-direction parameter. In case of the NVME SMART log getting the DMA was performed from-device-to-memory, thus the cache-invalidation was activated during the buffer mapping. Since the log-buffer isn't cache-line aligned, the cache-invalidation caused the neighbour data to be discarded. The neighbouring data turned to be the data surrounding the buffer in the framework of the nvme_hwmon_data structure. In order to fix that we need to make sure that the whole log-buffer is defined within the cache-line-aligned memory region so the cache-invalidation procedure wouldn't involve the adjacent data. One of the option to guarantee that is to kmalloc the DMA-buffer [1]. Seeing the rest of the NVME core driver prefer that method it has been chosen to fix this problem too. Note after a deeper researches we found out that the denoted commit wasn't a root cause of the problem. It just revealed the invalidity by activating the DMA-based NVME SMART log getting performed in the framework of the NVME hwmon driver. The problem was here since the initial commit of the driver. [1] Documentation/core-api/dma-api-howto.rst Fixes: 400b6a7b13a3 ("nvme: Add hardware monitoring support") Signed-off-by: Serge Semin Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/nvme/host/hwmon.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 23918bb7bdca..9e6e56c20ec9 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -12,7 +12,7 @@ struct nvme_hwmon_data { struct nvme_ctrl *ctrl; - struct nvme_smart_log log; + struct nvme_smart_log *log; struct mutex read_lock; }; @@ -60,14 +60,14 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) { return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, - NVME_CSI_NVM, &data->log, sizeof(data->log), 0); + NVME_CSI_NVM, data->log, sizeof(*data->log), 0); } static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { struct nvme_hwmon_data *data = dev_get_drvdata(dev); - struct nvme_smart_log *log = &data->log; + struct nvme_smart_log *log = data->log; int temp; int err; @@ -163,7 +163,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log.temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1])) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; @@ -176,7 +176,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data, break; case hwmon_temp_input: case hwmon_temp_label: - if (!channel || data->log.temp_sensor[channel - 1]) + if (!channel || data->log->temp_sensor[channel - 1]) return 0444; break; default: @@ -232,13 +232,19 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; + data->log = kzalloc(sizeof(*data->log), GFP_KERNEL); + if (!data->log) { + err = -ENOMEM; + goto err_free_data; + } + data->ctrl = ctrl; mutex_init(&data->read_lock); err = nvme_hwmon_get_smart_log(data); if (err) { dev_warn(dev, "Failed to read smart log (error %d)\n", err); - goto err_free_data; + goto err_free_log; } hwmon = hwmon_device_register_with_info(dev, "nvme", @@ -247,11 +253,13 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); err = PTR_ERR(hwmon); - goto err_free_data; + goto err_free_log; } ctrl->hwmon_device = hwmon; return 0; +err_free_log: + kfree(data->log); err_free_data: kfree(data); return err; @@ -265,6 +273,7 @@ void nvme_hwmon_exit(struct nvme_ctrl *ctrl) hwmon_device_unregister(ctrl->hwmon_device); ctrl->hwmon_device = NULL; + kfree(data->log); kfree(data); } } -- Gitee From f23a5f402766467789f169d5ee05162018971475 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 18 Oct 2022 14:31:59 +0800 Subject: [PATCH 44/79] net: sched: cake: fix null pointer access issue when cake_init() fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stable inclusion from stable-5.10.152 commit ae48bee2830bf216800e1447baca39541e27a12e category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 51f9a8921ceacd7bf0d3f47fa867a64988ba1dcb ] When the default qdisc is cake, if the qdisc of dev_queue fails to be inited during mqprio_init(), cake_reset() is invoked to clear resources. In this case, the tins is NULL, and it will cause gpf issue. The process is as follows: qdisc_create_dflt() cake_init() q->tins = kvcalloc(...) --->failed, q->tins is NULL ... qdisc_put() ... cake_reset() ... cake_dequeue_one() b = &q->tins[...] --->q->tins is NULL The following is the Call Trace information: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:cake_dequeue_one+0xc9/0x3c0 Call Trace: cake_reset+0xb1/0x140 qdisc_reset+0xed/0x6f0 qdisc_destroy+0x82/0x4c0 qdisc_put+0x9e/0xb0 qdisc_create_dflt+0x2c3/0x4a0 mqprio_init+0xa71/0x1760 qdisc_create+0x3eb/0x1000 tc_modify_qdisc+0x408/0x1720 rtnetlink_rcv_msg+0x38e/0xac0 netlink_rcv_skb+0x12d/0x3a0 netlink_unicast+0x4a2/0x740 netlink_sendmsg+0x826/0xcc0 sock_sendmsg+0xc5/0x100 ____sys_sendmsg+0x583/0x690 ___sys_sendmsg+0xe8/0x160 __sys_sendmsg+0xbf/0x160 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f89e5122d04 Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Zhengchao Shao Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/sched/sch_cake.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c580139fcede..5dc7a3c310c9 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2224,8 +2224,12 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) static void cake_reset(struct Qdisc *sch) { + struct cake_sched_data *q = qdisc_priv(sch); u32 c; + if (!q->tins) + return; + for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } -- Gitee From 3f65bf45b1edcb12986aa973a3ef620339d869a9 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Wed, 24 Aug 2022 08:52:31 +0800 Subject: [PATCH 45/79] net: sched: delete duplicate cleanup of backlog and qlen stable inclusion from stable-5.10.152 commit 305aa36b628e2c7974fb23674a56b28b7224c2c2 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit c19d893fbf3f2f8fa864ae39652c7fee939edde2 ] qdisc_reset() is clearing qdisc->q.qlen and qdisc->qstats.backlog _after_ calling qdisc->ops->reset. There is no need to clear them again in the specific reset function. Signed-off-by: Zhengchao Shao Link: https://lore.kernel.org/r/20220824005231.345727-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni Stable-dep-of: 2a3fc78210b9 ("net: sched: sfb: fix null pointer access issue when sfb_init() fails") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- include/net/sch_generic.h | 1 - net/sched/sch_atm.c | 1 - net/sched/sch_cbq.c | 1 - net/sched/sch_choke.c | 2 -- net/sched/sch_drr.c | 2 -- net/sched/sch_dsmark.c | 2 -- net/sched/sch_etf.c | 3 --- net/sched/sch_ets.c | 2 -- net/sched/sch_fq_codel.c | 2 -- net/sched/sch_fq_pie.c | 3 --- net/sched/sch_hfsc.c | 2 -- net/sched/sch_htb.c | 2 -- net/sched/sch_multiq.c | 1 - net/sched/sch_prio.c | 2 -- net/sched/sch_qfq.c | 2 -- net/sched/sch_red.c | 2 -- net/sched/sch_sfb.c | 2 -- net/sched/sch_skbprio.c | 3 --- net/sched/sch_taprio.c | 2 -- net/sched/sch_tbf.c | 2 -- net/sched/sch_teql.c | 1 - 21 files changed, 40 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index bed2387af456..e7e8c318925d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1178,7 +1178,6 @@ static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) static inline void qdisc_reset_queue(struct Qdisc *sch) { __qdisc_reset_queue(&sch->q); - sch->qstats.backlog = 0; } static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 5e0d55ac9c5d..95967ce1f370 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -578,7 +578,6 @@ static void atm_tc_reset(struct Qdisc *sch) pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); list_for_each_entry(flow, &p->flows, list) qdisc_reset(flow->q); - sch->q.qlen = 0; } static void atm_tc_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 01853de86bc0..3da5eb313c24 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1053,7 +1053,6 @@ cbq_reset(struct Qdisc *sch) cl->cpriority = cl->priority; } } - sch->q.qlen = 0; } diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 2adbd945bf15..25d2daaa8122 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -315,8 +315,6 @@ static void choke_reset(struct Qdisc *sch) rtnl_qdisc_drop(skb, sch); } - sch->q.qlen = 0; - sch->qstats.backlog = 0; if (q->tab) memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index dde564670ad8..08424aac6da8 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -443,8 +443,6 @@ static void drr_reset_qdisc(struct Qdisc *sch) qdisc_reset(cl->qdisc); } } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void drr_destroy_qdisc(struct Qdisc *sch) diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 76ed1a05ded2..a75bc7f80cd7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -408,8 +408,6 @@ static void dsmark_reset(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); if (p->q) qdisc_reset(p->q); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void dsmark_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index c48f91075b5c..d96103b0e2bf 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -445,9 +445,6 @@ static void etf_reset(struct Qdisc *sch) timesortedlist_clear(sch); __qdisc_reset_queue(&sch->q); - sch->qstats.backlog = 0; - sch->q.qlen = 0; - q->last = 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 9c224872ef03..05817c55692f 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -722,8 +722,6 @@ static void ets_qdisc_reset(struct Qdisc *sch) } for (band = 0; band < q->nbands; band++) qdisc_reset(q->classes[band].qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void ets_qdisc_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 99e8db262198..01d6eea5b0ce 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -347,8 +347,6 @@ static void fq_codel_reset(struct Qdisc *sch) codel_vars_init(&flow->cvars); } memset(q->backlogs, 0, q->flows_cnt * sizeof(u32)); - sch->q.qlen = 0; - sch->qstats.backlog = 0; q->memory_usage = 0; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index c70802785518..cf04f70e96bf 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -521,9 +521,6 @@ static void fq_pie_reset(struct Qdisc *sch) INIT_LIST_HEAD(&flow->flowchain); pie_vars_init(&flow->vars); } - - sch->q.qlen = 0; - sch->qstats.backlog = 0; } static void fq_pie_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index d1902fca9844..cdc43a06aa9b 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1484,8 +1484,6 @@ hfsc_reset_qdisc(struct Qdisc *sch) } q->eligible = RB_ROOT; qdisc_watchdog_cancel(&q->watchdog); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cd70dbcbd72f..c3ba018fd083 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -966,8 +966,6 @@ static void htb_reset(struct Qdisc *sch) } qdisc_watchdog_cancel(&q->watchdog); __qdisc_reset_queue(&q->direct_queue); - sch->q.qlen = 0; - sch->qstats.backlog = 0; memset(q->hlevel, 0, sizeof(q->hlevel)); memset(q->row_mask, 0, sizeof(q->row_mask)); } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 5c27b4270b90..1c6dbcfa89b8 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -152,7 +152,6 @@ multiq_reset(struct Qdisc *sch) for (band = 0; band < q->bands; band++) qdisc_reset(q->queues[band]); - sch->q.qlen = 0; q->curband = 0; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 3eabb871a1d5..1c805fe05b82 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -135,8 +135,6 @@ prio_reset(struct Qdisc *sch) for (prio = 0; prio < q->bands; prio++) qdisc_reset(q->queues[prio]); - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static int prio_offload(struct Qdisc *sch, struct tc_prio_qopt *qopt) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index af8c63a9ec18..1d1d81aeb389 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1458,8 +1458,6 @@ static void qfq_reset_qdisc(struct Qdisc *sch) qdisc_reset(cl->qdisc); } } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void qfq_destroy_qdisc(struct Qdisc *sch) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 40adf1f07a82..f1e013e3f04a 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -176,8 +176,6 @@ static void red_reset(struct Qdisc *sch) struct red_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index b2724057629f..0e1cb517b0d9 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -456,8 +456,6 @@ static void sfb_reset(struct Qdisc *sch) struct sfb_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 7a5e4c454715..df72fb83d9c7 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -213,9 +213,6 @@ static void skbprio_reset(struct Qdisc *sch) struct skbprio_sched_data *q = qdisc_priv(sch); int prio; - sch->qstats.backlog = 0; - sch->q.qlen = 0; - for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_purge(&q->qdiscs[prio]); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index ab8835a72cee..7f33b31c7b8b 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1626,8 +1626,6 @@ static void taprio_reset(struct Qdisc *sch) if (q->qdiscs[i]) qdisc_reset(q->qdiscs[i]); } - sch->qstats.backlog = 0; - sch->q.qlen = 0; } static void taprio_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6eb17004a9e4..7461e5c67d50 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -316,8 +316,6 @@ static void tbf_reset(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_reset(q->qdisc); - sch->qstats.backlog = 0; - sch->q.qlen = 0; q->t_c = ktime_get_ns(); q->tokens = q->buffer; q->ptokens = q->mtu; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 6af6b95bdb67..79aaab51cbf5 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -124,7 +124,6 @@ teql_reset(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); skb_queue_purge(&dat->q); - sch->q.qlen = 0; } static void -- Gitee From b406e20fbb2b8e477c3dd1af9c08e5550b8394c0 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 18 Oct 2022 14:32:01 +0800 Subject: [PATCH 46/79] net: sched: sfb: fix null pointer access issue when sfb_init() fails stable inclusion from stable-5.10.152 commit ded86c4191a3c17f8200d17a7d8a6f63b74554ae category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 2a3fc78210b9f0e85372a2435368962009f480fc ] When the default qdisc is sfb, if the qdisc of dev_queue fails to be inited during mqprio_init(), sfb_reset() is invoked to clear resources. In this case, the q->qdisc is NULL, and it will cause gpf issue. The process is as follows: qdisc_create_dflt() sfb_init() tcf_block_get() --->failed, q->qdisc is NULL ... qdisc_put() ... sfb_reset() qdisc_reset(q->qdisc) --->q->qdisc is NULL ops = qdisc->ops The following is the Call Trace information: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] RIP: 0010:qdisc_reset+0x2b/0x6f0 Call Trace: sfb_reset+0x37/0xd0 qdisc_reset+0xed/0x6f0 qdisc_destroy+0x82/0x4c0 qdisc_put+0x9e/0xb0 qdisc_create_dflt+0x2c3/0x4a0 mqprio_init+0xa71/0x1760 qdisc_create+0x3eb/0x1000 tc_modify_qdisc+0x408/0x1720 rtnetlink_rcv_msg+0x38e/0xac0 netlink_rcv_skb+0x12d/0x3a0 netlink_unicast+0x4a2/0x740 netlink_sendmsg+0x826/0xcc0 sock_sendmsg+0xc5/0x100 ____sys_sendmsg+0x583/0x690 ___sys_sendmsg+0xe8/0x160 __sys_sendmsg+0xbf/0x160 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f2164122d04 Fixes: e13e02a3c68d ("net_sched: SFB flow scheduler") Signed-off-by: Zhengchao Shao Signed-off-by: David S. Miller Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- net/sched/sch_sfb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0e1cb517b0d9..9ded56228ea1 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -455,7 +455,8 @@ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - qdisc_reset(q->qdisc); + if (likely(q->qdisc)) + qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); -- Gitee From 8b80ae1645d4b0e590f6a19b0f83d9853a27ad27 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Tue, 18 Oct 2022 10:28:41 +0100 Subject: [PATCH 47/79] sfc: include vport_id in filter spec hash and equal() stable inclusion from stable-5.10.152 commit 3032e316e0a9a04b9cc3ca73ff22c4d546aee243 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit c2bf23e4a5af37a4d77901d9ff14c50a269f143d ] Filters on different vports are qualified by different implicit MACs and/or VLANs, so shouldn't be considered equal even if their other match fields are identical. Fixes: 7c460d9be610 ("sfc: Extend and abstract efx_filter_spec to cover Huntington/EF10") Co-developed-by: Edward Cree Signed-off-by: Edward Cree Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Martin Habets Link: https://lore.kernel.org/r/20221018092841.32206-1-pieter.jansen-van-vuuren@amd.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/net/ethernet/sfc/filter.h | 3 ++- drivers/net/ethernet/sfc/rx_common.c | 10 +++++----- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index 40b2af8bfb81..2ac3c8f1b04b 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -157,7 +157,8 @@ struct efx_filter_spec { u32 flags:6; u32 dmaq_id:12; u32 rss_context; - __be16 outer_vid __aligned(4); /* allow jhash2() of match values */ + u32 vport_id; + __be16 outer_vid; __be16 inner_vid; u8 loc_mac[ETH_ALEN]; u8 rem_mac[ETH_ALEN]; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 2c09afac5beb..36b46ddb6710 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -676,17 +676,17 @@ bool efx_filter_spec_equal(const struct efx_filter_spec *left, (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX))) return false; - return memcmp(&left->outer_vid, &right->outer_vid, + return memcmp(&left->vport_id, &right->vport_id, sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) == 0; + offsetof(struct efx_filter_spec, vport_id)) == 0; } u32 efx_filter_spec_hash(const struct efx_filter_spec *spec) { - BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3); - return jhash2((const u32 *)&spec->outer_vid, + BUILD_BUG_ON(offsetof(struct efx_filter_spec, vport_id) & 3); + return jhash2((const u32 *)&spec->vport_id, (sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) / 4, + offsetof(struct efx_filter_spec, vport_id)) / 4, 0); } -- Gitee From 28ddcfb6f9684526b87ab5b278eacf8c467da338 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 18 Oct 2022 20:24:51 +0800 Subject: [PATCH 48/79] net: hns: fix possible memory leak in hnae_ae_register() stable inclusion from stable-5.10.152 commit 2974f3b330ef25f5d34a4948d04290c2cd7802cf category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit ff2f5ec5d009844ec28f171123f9e58750cef4bf ] Inject fault while probing module, if device_register() fails, but the refcount of kobject is not decreased to 0, the name allocated in dev_set_name() is leaked. Fix this by calling put_device(), so that name can be freed in callback function kobject_cleanup(). unreferenced object 0xffff00c01aba2100 (size 128): comm "systemd-udevd", pid 1259, jiffies 4294903284 (age 294.152s) hex dump (first 32 bytes): 68 6e 61 65 30 00 00 00 18 21 ba 1a c0 00 ff ff hnae0....!...... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000034783f26>] slab_post_alloc_hook+0xa0/0x3e0 [<00000000748188f2>] __kmem_cache_alloc_node+0x164/0x2b0 [<00000000ab0743e8>] __kmalloc_node_track_caller+0x6c/0x390 [<000000006c0ffb13>] kvasprintf+0x8c/0x118 [<00000000fa27bfe1>] kvasprintf_const+0x60/0xc8 [<0000000083e10ed7>] kobject_set_name_vargs+0x3c/0xc0 [<000000000b87affc>] dev_set_name+0x7c/0xa0 [<000000003fd8fe26>] hnae_ae_register+0xcc/0x190 [hnae] [<00000000fe97edc9>] hns_dsaf_ae_init+0x9c/0x108 [hns_dsaf] [<00000000c36ff1eb>] hns_dsaf_probe+0x548/0x748 [hns_dsaf] Fixes: 6fe6611ff275 ("net: add Hisilicon Network Subsystem hnae framework support") Signed-off-by: Yang Yingliang Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20221018122451.1749171-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/net/ethernet/hisilicon/hns/hnae.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 00fafc0f8512..430eccea8e5e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -419,8 +419,10 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) hdev->cls_dev.release = hnae_release; (void)dev_set_name(&hdev->cls_dev, "hnae%d", hdev->id); ret = device_register(&hdev->cls_dev); - if (ret) + if (ret) { + put_device(&hdev->cls_dev); return ret; + } __module_get(THIS_MODULE); -- Gitee From f273a930ba64100860e36e709069d45b048f97ea Mon Sep 17 00:00:00 2001 From: Felix Riemann Date: Tue, 18 Oct 2022 12:47:54 +0200 Subject: [PATCH 49/79] net: phy: dp83822: disable MDI crossover status change interrupt stable inclusion from stable-5.10.152 commit 35c92435be76acdd544c834ae734b88d08e91e0e category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 7f378c03aa4952507521174fb0da7b24a9ad0be6 ] If the cable is disconnected the PHY seems to toggle between MDI and MDI-X modes. With the MDI crossover status interrupt active this causes roughly 10 interrupts per second. As the crossover status isn't checked by the driver, the interrupt can be disabled to reduce the interrupt load. Fixes: 87461f7a58ab ("net: phy: DP83822 initial driver submission") Signed-off-by: Felix Riemann Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20221018104755.30025-1-svc.sw.rte.linux@sma.de Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/net/phy/dp83822.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 3a8849716459..db651649e0b8 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -268,8 +268,7 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_EEE_ERROR_CHANGE_INT_EN); if (!dp83822->fx_enabled) - misr_status |= DP83822_MDI_XOVER_INT_EN | - DP83822_ANEG_ERR_INT_EN | + misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; err = phy_write(phydev, MII_DP83822_MISR2, misr_status); -- Gitee From ff4adc7c85a9c5dee8d4812390699d77ca4257d6 Mon Sep 17 00:00:00 2001 From: Charlotte Tan Date: Wed, 19 Oct 2022 08:44:46 +0800 Subject: [PATCH 50/79] iommu/vt-d: Allow NVS regions in arch_rmrr_sanity_check() stable inclusion from stable-5.10.152 commit ef11e8ec00b976a30131751cca1792ac6e87e95c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 5566e68d829f5d87670d5984c1c2ccb4c518405f ] arch_rmrr_sanity_check() warns if the RMRR is not covered by an ACPI Reserved region, but it seems like it should accept an NVS region as well. The ACPI spec https://uefi.org/specs/ACPI/6.5/15_System_Address_Map_Interfaces.html uses similar wording for "Reserved" and "NVS" region types; for NVS regions it says "This range of addresses is in use or reserved by the system and must not be used by the operating system." There is an old comment on this mailing list that also suggests NVS regions should pass the arch_rmrr_sanity_check() test: The warnings come from arch_rmrr_sanity_check() since it checks whether the region is E820_TYPE_RESERVED. However, if the purpose of the check is to detect RMRR has regions that may be used by OS as free memory, isn't E820_TYPE_NVS safe, too? This patch overlaps with another proposed patch that would add the region type to the log since sometimes the bug reporter sees this log on the console but doesn't know to include the kernel log: https://lore.kernel.org/lkml/20220611204859.234975-3-atomlin@redhat.com/ Here's an example of the "Firmware Bug" apparent false positive (wrapped for line length): DMAR: [Firmware Bug]: No firmware reserved region can cover this RMRR [0x000000006f760000-0x000000006f762fff], contact BIOS vendor for fixes DMAR: [Firmware Bug]: Your BIOS is broken; bad RMRR [0x000000006f760000-0x000000006f762fff] This is the snippet from the e820 table: BIOS-e820: [mem 0x0000000068bff000-0x000000006ebfefff] reserved BIOS-e820: [mem 0x000000006ebff000-0x000000006f9fefff] ACPI NVS BIOS-e820: [mem 0x000000006f9ff000-0x000000006fffefff] ACPI data Fixes: f036c7fa0ab6 ("iommu/vt-d: Check VT-d RMRR region in BIOS is reported as reserved") Cc: Will Mortensen Link: https://lore.kernel.org/linux-iommu/64a5843d-850d-e58c-4fc2-0a0eeeb656dc@nec.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=216443 Signed-off-by: Charlotte Tan Reviewed-by: Aaron Tomlin Link: https://lore.kernel.org/r/20220929044449.32515-1-charlotte@extrahop.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- arch/x86/include/asm/iommu.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index bf1ed2ddc74b..7a983119bc40 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -17,8 +17,10 @@ arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) { u64 start = rmrr->base_address; u64 end = rmrr->end_address + 1; + int entry_type; - if (e820__mapped_all(start, end, E820_TYPE_RESERVED)) + entry_type = e820__get_entry_type(start, end); + if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS) return 0; pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n", -- Gitee From 6681548bddcce62f2cb4e39e013b97b99223b370 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Wed, 19 Oct 2022 08:44:47 +0800 Subject: [PATCH 51/79] iommu/vt-d: Clean up si_domain in the init_dmars() error path stable inclusion from stable-5.10.152 commit d74196bb278b8f8af88e16bd595997dfa3d6fdb0 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 620bf9f981365c18cc2766c53d92bf8131c63f32 ] A splat from kmem_cache_destroy() was seen with a kernel prior to commit ee2653bbe89d ("iommu/vt-d: Remove domain and devinfo mempool") when there was a failure in init_dmars(), because the iommu_domain cache still had objects. While the mempool code is now gone, there still is a leak of the si_domain memory if init_dmars() fails. So clean up si_domain in the init_dmars() error path. Cc: Lu Baolu Cc: Joerg Roedel Cc: Will Deacon Cc: Robin Murphy Fixes: 86080ccc223a ("iommu/vt-d: Allocate si_domain in init_dmars()") Signed-off-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20221010144842.308890-1-jsnitsel@redhat.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/iommu/intel/iommu.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index c48cf737b521..f23329b7f97c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2846,6 +2846,7 @@ static int __init si_domain_init(int hw) if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); + si_domain = NULL; return -EFAULT; } @@ -3505,6 +3506,10 @@ static int __init init_dmars(void) disable_dmar_iommu(iommu); free_dmar_iommu(iommu); } + if (si_domain) { + domain_exit(si_domain); + si_domain = NULL; + } kfree(g_iommus); -- Gitee From d45753b6288e44410f0a1523977b9785b9291450 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 30 Jun 2022 23:07:22 +0300 Subject: [PATCH 52/79] drm/virtio: Use appropriate atomic state in virtio_gpu_plane_cleanup_fb() stable inclusion from stable-5.10.152 commit 1414e9bf3c307759347e6c91ed1143065ee86402 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 4656b3a26a9e9fe5f04bfd2ab55b066266ba7f4d ] Make virtio_gpu_plane_cleanup_fb() to clean the state which DRM core wants to clean up and not the current plane's state. Normally the older atomic state is cleaned up, but the newer state could also be cleaned up in case of aborted commits. Cc: stable@vger.kernel.org Signed-off-by: Dmitry Osipenko Link: http://patchwork.freedesktop.org/patch/msgid/20220630200726.1884320-6-dmitry.osipenko@collabora.com Signed-off-by: Gerd Hoffmann Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/gpu/drm/virtio/virtgpu_plane.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 6a311cd93440..e6de62734269 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -213,14 +213,14 @@ static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane, } static void virtio_gpu_cursor_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) + struct drm_plane_state *state) { struct virtio_gpu_framebuffer *vgfb; - if (!plane->state->fb) + if (!state->fb) return; - vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgfb = to_virtio_gpu_framebuffer(state->fb); if (vgfb->fence) { dma_fence_put(&vgfb->fence->f); vgfb->fence = NULL; -- Gitee From aa002f3270af61005dd882b10b398940dbadd450 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 23 Nov 2020 16:30:51 -0300 Subject: [PATCH 53/79] dmaengine: mxs-dma: Remove the unused .id_table stable inclusion from stable-5.10.152 commit 1da5d249704666fe8d3b1cb531d73fb6c621d84f category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit cc2afb0d4c7cbba6743ed6d9564f0883cab6bae1 ] The mxs-dma driver is only used by DT platforms and the .id_table is unused. Get rid of it to simplify the code. Signed-off-by: Fabio Estevam Link: https://lore.kernel.org/r/20201123193051.17285-1-festevam@gmail.com Signed-off-by: Vinod Koul Stable-dep-of: 26696d465716 ("dmaengine: mxs: use platform_driver_register") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/dma/mxs-dma.c | 37 +++++-------------------------------- 1 file changed, 5 insertions(+), 32 deletions(-) diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c index 65f816b40c32..994fc4d2aca4 100644 --- a/drivers/dma/mxs-dma.c +++ b/drivers/dma/mxs-dma.c @@ -167,29 +167,11 @@ static struct mxs_dma_type mxs_dma_types[] = { } }; -static const struct platform_device_id mxs_dma_ids[] = { - { - .name = "imx23-dma-apbh", - .driver_data = (kernel_ulong_t) &mxs_dma_types[0], - }, { - .name = "imx23-dma-apbx", - .driver_data = (kernel_ulong_t) &mxs_dma_types[1], - }, { - .name = "imx28-dma-apbh", - .driver_data = (kernel_ulong_t) &mxs_dma_types[2], - }, { - .name = "imx28-dma-apbx", - .driver_data = (kernel_ulong_t) &mxs_dma_types[3], - }, { - /* end of list */ - } -}; - static const struct of_device_id mxs_dma_dt_ids[] = { - { .compatible = "fsl,imx23-dma-apbh", .data = &mxs_dma_ids[0], }, - { .compatible = "fsl,imx23-dma-apbx", .data = &mxs_dma_ids[1], }, - { .compatible = "fsl,imx28-dma-apbh", .data = &mxs_dma_ids[2], }, - { .compatible = "fsl,imx28-dma-apbx", .data = &mxs_dma_ids[3], }, + { .compatible = "fsl,imx23-dma-apbh", .data = &mxs_dma_types[0], }, + { .compatible = "fsl,imx23-dma-apbx", .data = &mxs_dma_types[1], }, + { .compatible = "fsl,imx28-dma-apbh", .data = &mxs_dma_types[2], }, + { .compatible = "fsl,imx28-dma-apbx", .data = &mxs_dma_types[3], }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, mxs_dma_dt_ids); @@ -762,8 +744,6 @@ static struct dma_chan *mxs_dma_xlate(struct of_phandle_args *dma_spec, static int __init mxs_dma_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct platform_device_id *id_entry; - const struct of_device_id *of_id; const struct mxs_dma_type *dma_type; struct mxs_dma_engine *mxs_dma; struct resource *iores; @@ -779,13 +759,7 @@ static int __init mxs_dma_probe(struct platform_device *pdev) return ret; } - of_id = of_match_device(mxs_dma_dt_ids, &pdev->dev); - if (of_id) - id_entry = of_id->data; - else - id_entry = platform_get_device_id(pdev); - - dma_type = (struct mxs_dma_type *)id_entry->driver_data; + dma_type = (struct mxs_dma_type *)of_device_get_match_data(&pdev->dev); mxs_dma->type = dma_type->type; mxs_dma->dev_id = dma_type->id; @@ -865,7 +839,6 @@ static struct platform_driver mxs_dma_driver = { .name = "mxs-dma", .of_match_table = mxs_dma_dt_ids, }, - .id_table = mxs_dma_ids, }; static int __init mxs_dma_module_init(void) -- Gitee From 722baab4b482fc2a9d5d12b0fc24ea8e5463d418 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Wed, 21 Sep 2022 19:05:56 +0200 Subject: [PATCH 54/79] dmaengine: mxs: use platform_driver_register stable inclusion from stable-5.10.152 commit 4e3a15ca24b33961da73d54ebfd4a3fd8bcc7bd7 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 26696d4657167112a1079f86cba1739765c1360e ] Driver registration fails on SOC imx8mn as its supplier, the clock control module, is probed later than subsys initcall level. This driver uses platform_driver_probe which is not compatible with deferred probing and won't be probed again later if probe function fails due to clock not being available at that time. This patch replaces the use of platform_driver_probe with platform_driver_register which will allow probing the driver later again when the clock control module will be available. The __init annotation has been dropped because it is not compatible with deferred probing. The code is not executed once and its memory cannot be freed. Fixes: a580b8c5429a ("dmaengine: mxs-dma: add dma support for i.MX23/28") Co-developed-by: Michael Trimarchi Signed-off-by: Michael Trimarchi Signed-off-by: Dario Binacchi Acked-by: Sascha Hauer Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220921170556.1055962-1-dario.binacchi@amarulasolutions.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/dma/mxs-dma.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c index 994fc4d2aca4..dc147cc2436e 100644 --- a/drivers/dma/mxs-dma.c +++ b/drivers/dma/mxs-dma.c @@ -670,7 +670,7 @@ static enum dma_status mxs_dma_tx_status(struct dma_chan *chan, return mxs_chan->status; } -static int __init mxs_dma_init(struct mxs_dma_engine *mxs_dma) +static int mxs_dma_init(struct mxs_dma_engine *mxs_dma) { int ret; @@ -741,7 +741,7 @@ static struct dma_chan *mxs_dma_xlate(struct of_phandle_args *dma_spec, ofdma->of_node); } -static int __init mxs_dma_probe(struct platform_device *pdev) +static int mxs_dma_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; const struct mxs_dma_type *dma_type; @@ -839,10 +839,7 @@ static struct platform_driver mxs_dma_driver = { .name = "mxs-dma", .of_match_table = mxs_dma_dt_ids, }, + .probe = mxs_dma_probe, }; -static int __init mxs_dma_module_init(void) -{ - return platform_driver_probe(&mxs_dma_driver, mxs_dma_probe); -} -subsys_initcall(mxs_dma_module_init); +builtin_platform_driver(mxs_dma_driver); -- Gitee From a3c0c09b577fb18ad69351c0205bc17a5b5cb27e Mon Sep 17 00:00:00 2001 From: sunliming Date: Thu, 2 Jun 2022 22:06:13 +0800 Subject: [PATCH 55/79] tracing: Simplify conditional compilation code in tracing_set_tracer() stable inclusion from stable-5.10.152 commit bd6af07e7993e304679ac21781d2d39ecdf97de0 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit f4b0d318097e45cbac5e14976f8bb56aa2cef504 ] Two conditional compilation directives "#ifdef CONFIG_TRACER_MAX_TRACE" are used consecutively, and no other code in between. Simplify conditional the compilation code and only use one "#ifdef CONFIG_TRACER_MAX_TRACE". Link: https://lkml.kernel.org/r/20220602140613.545069-1-sunliming@kylinos.cn Signed-off-by: sunliming Signed-off-by: Steven Rostedt (Google) Stable-dep-of: a541a9559bb0 ("tracing: Do not free snapshot if tracer is on cmdline") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- kernel/trace/trace.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a5245362ce7a..870033f9c198 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6025,9 +6025,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) synchronize_rcu(); free_snapshot(tr); } -#endif -#ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr && !had_max_tr) { ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) -- Gitee From caa8052fde5f74f9d7ca228ed9d0f8f7cf76eafb Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 5 Oct 2022 11:37:57 -0400 Subject: [PATCH 56/79] tracing: Do not free snapshot if tracer is on cmdline stable inclusion from stable-5.10.152 commit ea82edad0aee6e080ec6dcdd200c3eade374d5bb category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit a541a9559bb0a8ecc434de01d3e4826c32e8bb53 ] The ftrace_boot_snapshot and alloc_snapshot cmdline options allocate the snapshot buffer at boot up for use later. The ftrace_boot_snapshot in particular requires the snapshot to be allocated because it will take a snapshot at the end of boot up allowing to see the traces that happened during boot so that it's not lost when user space takes over. When a tracer is registered (started) there's a path that checks if it requires the snapshot buffer or not, and if it does not and it was allocated it will do a synchronization and free the snapshot buffer. This is only required if the previous tracer was using it for "max latency" snapshots, as it needs to make sure all max snapshots are complete before freeing. But this is only needed if the previous tracer was using the snapshot buffer for latency (like irqoff tracer and friends). But it does not make sense to free it, if the previous tracer was not using it, and the snapshot was allocated by the cmdline parameters. This basically takes away the point of allocating it in the first place! Note, the allocated snapshot worked fine for just trace events, but fails when a tracer is enabled on the cmdline. Further investigation, this goes back even further and it does not require a tracer on the cmdline to fail. Simply enable snapshots and then enable a tracer, and it will remove the snapshot. Link: https://lkml.kernel.org/r/20221005113757.041df7fe@gandalf.local.home Cc: Masami Hiramatsu Cc: Andrew Morton Cc: stable@vger.kernel.org Fixes: 45ad21ca5530 ("tracing: Have trace_array keep track if snapshot buffer is allocated") Reported-by: Ross Zwisler Tested-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- kernel/trace/trace.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 870033f9c198..b7cb9147f0c5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6008,12 +6008,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); +#ifdef CONFIG_TRACER_MAX_TRACE + had_max_tr = tr->current_trace->use_max_tr; + /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; -#ifdef CONFIG_TRACER_MAX_TRACE - had_max_tr = tr->allocated_snapshot; - if (had_max_tr && !t->use_max_tr) { /* * We need to make sure that the update_max_tr sees that @@ -6026,11 +6026,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf) free_snapshot(tr); } - if (t->use_max_tr && !had_max_tr) { + if (t->use_max_tr && !tr->allocated_snapshot) { ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) goto out; } +#else + tr->current_trace = &nop_trace; #endif if (t->init) { -- Gitee From 48eb19dc35a680f809b252a7a449d4fedfa58d8a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 30 Jul 2021 09:18:04 +0200 Subject: [PATCH 57/79] xen: assume XENFEAT_gnttab_map_avail_bits being set for pv guests stable inclusion from stable-5.10.152 commit 5232411f37d79654db574ff7357c5acc4620f173 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 30dcc56bba911db561c35d4131baf983a41023f8 ] XENFEAT_gnttab_map_avail_bits is always set in Xen 4.0 and newer. Remove coding assuming it might be zero. Signed-off-by: Juergen Gross Acked-by: Peter Zijlstra (Intel) Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20210730071804.4302-4-jgross@suse.com Signed-off-by: Juergen Gross Stable-dep-of: 5c13a4a0291b ("xen/gntdev: Accommodate VMA splitting") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/xen/gntdev.c | 36 ++---------------------------------- 1 file changed, 2 insertions(+), 34 deletions(-) diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 54fee4087bf1..5dd9d1ac755e 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -289,20 +289,13 @@ static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) { struct gntdev_grant_map *map = data; unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT; - int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte; + int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte | + (1 << _GNTMAP_guest_avail0); u64 pte_maddr; BUG_ON(pgnr >= map->count); pte_maddr = arbitrary_virt_to_machine(pte).maddr; - /* - * Set the PTE as special to force get_user_pages_fast() fall - * back to the slow path. If this is not supported as part of - * the grant map, it will be done afterwards. - */ - if (xen_feature(XENFEAT_gnttab_map_avail_bits)) - flags |= (1 << _GNTMAP_guest_avail0); - gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags, map->grants[pgnr].ref, map->grants[pgnr].domid); @@ -311,14 +304,6 @@ static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) return 0; } -#ifdef CONFIG_X86 -static int set_grant_ptes_as_special(pte_t *pte, unsigned long addr, void *data) -{ - set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte)); - return 0; -} -#endif - int gntdev_map_grant_pages(struct gntdev_grant_map *map) { size_t alloced = 0; @@ -1102,23 +1087,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) err = vm_map_pages_zero(vma, map->pages, map->count); if (err) goto out_put_map; - } else { -#ifdef CONFIG_X86 - /* - * If the PTEs were not made special by the grant map - * hypercall, do so here. - * - * This is racy since the mapping is already visible - * to userspace but userspace should be well-behaved - * enough to not touch it until the mmap() call - * returns. - */ - if (!xen_feature(XENFEAT_gnttab_map_avail_bits)) { - apply_to_page_range(vma->vm_mm, vma->vm_start, - vma->vm_end - vma->vm_start, - set_grant_ptes_as_special, NULL); - } -#endif } return 0; -- Gitee From d817c26fdf9ca2af8639b12f69a8896a63190d5a Mon Sep 17 00:00:00 2001 From: "M. Vefa Bicakci" Date: Sun, 2 Oct 2022 18:20:06 -0400 Subject: [PATCH 58/79] xen/gntdev: Accommodate VMA splitting stable inclusion from stable-5.10.152 commit 3c6a888e352283a14f37b9b433cd598a1a3a7dd0 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 5c13a4a0291b30191eff9ead8d010e1ca43a4d0c ] Prior to this commit, the gntdev driver code did not handle the following scenario correctly with paravirtualized (PV) Xen domains: * User process sets up a gntdev mapping composed of two grant mappings (i.e., two pages shared by another Xen domain). * User process munmap()s one of the pages. * User process munmap()s the remaining page. * User process exits. In the scenario above, the user process would cause the kernel to log the following messages in dmesg for the first munmap(), and the second munmap() call would result in similar log messages: BUG: Bad page map in process doublemap.test pte:... pmd:... page:0000000057c97bff refcount:1 mapcount:-1 \ mapping:0000000000000000 index:0x0 pfn:... ... page dumped because: bad pte ... file:gntdev fault:0x0 mmap:gntdev_mmap [xen_gntdev] readpage:0x0 ... Call Trace: dump_stack_lvl+0x46/0x5e print_bad_pte.cold+0x66/0xb6 unmap_page_range+0x7e5/0xdc0 unmap_vmas+0x78/0xf0 unmap_region+0xa8/0x110 __do_munmap+0x1ea/0x4e0 __vm_munmap+0x75/0x120 __x64_sys_munmap+0x28/0x40 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x61/0xcb ... For each munmap() call, the Xen hypervisor (if built with CONFIG_DEBUG) would print out the following and trigger a general protection fault in the affected Xen PV domain: (XEN) d0v... Attempt to implicitly unmap d0's grant PTE ... (XEN) d0v... Attempt to implicitly unmap d0's grant PTE ... As of this writing, gntdev_grant_map structure's vma field (referred to as map->vma below) is mainly used for checking the start and end addresses of mappings. However, with split VMAs, these may change, and there could be more than one VMA associated with a gntdev mapping. Hence, remove the use of map->vma and rely on map->pages_vm_start for the original start address and on (map->count << PAGE_SHIFT) for the original mapping size. Let the invalidate() and find_special_page() hooks use these. Also, given that there can be multiple VMAs associated with a gntdev mapping, move the "mmu_interval_notifier_remove(&map->notifier)" call to the end of gntdev_put_map, so that the MMU notifier is only removed after the closing of the last remaining VMA. Finally, use an atomic to prevent inadvertent gntdev mapping re-use, instead of using the map->live_grants atomic counter and/or the map->vma pointer (the latter of which is now removed). This prevents the userspace from mmap()'ing (with MAP_FIXED) a gntdev mapping over the same address range as a previously set up gntdev mapping. This scenario can be summarized with the following call-trace, which was valid prior to this commit: mmap gntdev_mmap mmap (repeat mmap with MAP_FIXED over the same address range) gntdev_invalidate unmap_grant_pages (sets 'being_removed' entries to true) gnttab_unmap_refs_async unmap_single_vma gntdev_mmap (maps the shared pages again) munmap gntdev_invalidate unmap_grant_pages (no-op because 'being_removed' entries are true) unmap_single_vma (For PV domains, Xen reports that a granted page is being unmapped and triggers a general protection fault in the affected domain, if Xen was built with CONFIG_DEBUG) The fix for this last scenario could be worth its own commit, but we opted for a single commit, because removing the gntdev_grant_map structure's vma field requires guarding the entry to gntdev_mmap(), and the live_grants atomic counter is not sufficient on its own to prevent the mmap() over a pre-existing mapping. Link: https://github.com/QubesOS/qubes-issues/issues/7631 Fixes: ab31523c2fca ("xen/gntdev: allow usermode to map granted pages") Cc: stable@vger.kernel.org Signed-off-by: M. Vefa Bicakci Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20221002222006.2077-3-m.v.b@runbox.com Signed-off-by: Juergen Gross Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/xen/gntdev-common.h | 3 +- drivers/xen/gntdev.c | 58 ++++++++++++++++--------------------- 2 files changed, 27 insertions(+), 34 deletions(-) diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 40ef379c28ab..9c286b2a1900 100644 --- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -44,9 +44,10 @@ struct gntdev_unmap_notify { }; struct gntdev_grant_map { + atomic_t in_use; struct mmu_interval_notifier notifier; + bool notifier_init; struct list_head next; - struct vm_area_struct *vma; int index; int count; int flags; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 5dd9d1ac755e..ff195b571763 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -276,6 +276,9 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) */ } + if (use_ptemod && map->notifier_init) + mmu_interval_notifier_remove(&map->notifier); + if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(map->notify.event); evtchn_put(map->notify.event); @@ -288,7 +291,7 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) { struct gntdev_grant_map *map = data; - unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT; + unsigned int pgnr = (addr - map->pages_vm_start) >> PAGE_SHIFT; int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte | (1 << _GNTMAP_guest_avail0); u64 pte_maddr; @@ -478,11 +481,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma) struct gntdev_priv *priv = file->private_data; pr_debug("gntdev_vma_close %p\n", vma); - if (use_ptemod) { - WARN_ON(map->vma != vma); - mmu_interval_notifier_remove(&map->notifier); - map->vma = NULL; - } + vma->vm_private_data = NULL; gntdev_put_map(priv, map); } @@ -510,29 +509,30 @@ static bool gntdev_invalidate(struct mmu_interval_notifier *mn, struct gntdev_grant_map *map = container_of(mn, struct gntdev_grant_map, notifier); unsigned long mstart, mend; + unsigned long map_start, map_end; if (!mmu_notifier_range_blockable(range)) return false; + map_start = map->pages_vm_start; + map_end = map->pages_vm_start + (map->count << PAGE_SHIFT); + /* * If the VMA is split or otherwise changed the notifier is not * updated, but we don't want to process VA's outside the modified * VMA. FIXME: It would be much more understandable to just prevent * modifying the VMA in the first place. */ - if (map->vma->vm_start >= range->end || - map->vma->vm_end <= range->start) + if (map_start >= range->end || map_end <= range->start) return true; - mstart = max(range->start, map->vma->vm_start); - mend = min(range->end, map->vma->vm_end); + mstart = max(range->start, map_start); + mend = min(range->end, map_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", - map->index, map->count, - map->vma->vm_start, map->vma->vm_end, - range->start, range->end, mstart, mend); - unmap_grant_pages(map, - (mstart - map->vma->vm_start) >> PAGE_SHIFT, - (mend - mstart) >> PAGE_SHIFT); + map->index, map->count, map_start, map_end, + range->start, range->end, mstart, mend); + unmap_grant_pages(map, (mstart - map_start) >> PAGE_SHIFT, + (mend - mstart) >> PAGE_SHIFT); return true; } @@ -1012,18 +1012,15 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) return -EINVAL; pr_debug("map %d+%d at %lx (pgoff %lx)\n", - index, count, vma->vm_start, vma->vm_pgoff); + index, count, vma->vm_start, vma->vm_pgoff); mutex_lock(&priv->lock); map = gntdev_find_map_index(priv, index, count); if (!map) goto unlock_out; - if (use_ptemod && map->vma) - goto unlock_out; - if (atomic_read(&map->live_grants)) { - err = -EAGAIN; + if (!atomic_add_unless(&map->in_use, 1, 1)) goto unlock_out; - } + refcount_inc(&map->users); vma->vm_ops = &gntdev_vmops; @@ -1044,15 +1041,16 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) map->flags |= GNTMAP_readonly; } + map->pages_vm_start = vma->vm_start; + if (use_ptemod) { - map->vma = vma; err = mmu_interval_notifier_insert_locked( &map->notifier, vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, &gntdev_mmu_ops); - if (err) { - map->vma = NULL; + if (err) goto out_unlock_put; - } + + map->notifier_init = true; } mutex_unlock(&priv->lock); @@ -1069,7 +1067,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) */ mmu_interval_read_begin(&map->notifier); - map->pages_vm_start = vma->vm_start; err = apply_to_page_range(vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, find_grant_ptes, map); @@ -1098,13 +1095,8 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) out_unlock_put: mutex_unlock(&priv->lock); out_put_map: - if (use_ptemod) { + if (use_ptemod) unmap_grant_pages(map, 0, map->count); - if (map->vma) { - mmu_interval_notifier_remove(&map->notifier); - map->vma = NULL; - } - } gntdev_put_map(priv, map); return err; } -- Gitee From 32d563ed95e03379763129ad2dfb3b9d8d1c27f1 Mon Sep 17 00:00:00 2001 From: Prathamesh Shete Date: Thu, 6 Oct 2022 18:36:22 +0530 Subject: [PATCH 59/79] mmc: sdhci-tegra: Use actual clock rate for SW tuning correction stable inclusion from stable-5.10.152 commit 7fba4a389d070daf17e18c657c8e31f03cc2486b category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit b78870e7f41534cc719c295d1f8809aca93aeeab ] Ensure tegra_host member "curr_clk_rate" holds the actual clock rate instead of requested clock rate for proper use during tuning correction algorithm. Actual clk rate may not be the same as the requested clk frequency depending on the parent clock source set. Tuning correction algorithm depends on certain parameters which are sensitive to current clk rate. If the host clk is selected instead of the actual clock rate, tuning correction algorithm may end up applying invalid correction, which could result in errors Fixes: ea8fc5953e8b ("mmc: tegra: update hw tuning process") Signed-off-by: Aniruddha TVS Rao Signed-off-by: Prathamesh Shete Acked-by: Adrian Hunter Acked-by: Thierry Reding Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221006130622.22900-4-pshete@nvidia.com Signed-off-by: Ulf Hansson Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- drivers/mmc/host/sdhci-tegra.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index d50b691f6c44..67211fc42d24 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -760,7 +760,7 @@ static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock) */ host_clk = tegra_host->ddr_signaling ? clock * 2 : clock; clk_set_rate(pltfm_host->clk, host_clk); - tegra_host->curr_clk_rate = host_clk; + tegra_host->curr_clk_rate = clk_get_rate(pltfm_host->clk); if (tegra_host->ddr_signaling) host->max_clk = host_clk; else -- Gitee From d43b340ada1f21fa73a370db408e04de815d3367 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 25 Nov 2020 19:44:15 +0800 Subject: [PATCH 60/79] riscv: Add machine name to kernel boot log and stack dump output stable inclusion from stable-5.10.152 commit 0e4c06ae7c546764eb4769ede647ef71a2fd363d category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 46ad48e8a28da7cc37a16c7e7fc632ecf906e4bf ] Add the machine name to kernel boot-up log, and install the machine name to stack dump for DT boot mode. Signed-off-by: Kefeng Wang Reviewed-by: Atish Patra Signed-off-by: Palmer Dabbelt Stable-dep-of: 10f6913c548b ("riscv: always honor the CONFIG_CMDLINE_FORCE when parsing dtb") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- arch/riscv/kernel/setup.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 117f3212a8e4..5d17d3ce36fd 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -54,8 +54,15 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va)) + if (early_init_dt_scan(dtb_early_va)) { + const char *name = of_flat_dt_get_machine_name(); + + if (name) { + pr_info("Machine model: %s\n", name); + dump_stack_set_arch_desc("%s (DT)", name); + } return; + } pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE -- Gitee From f390784423032dc4d2ee5ac9843581224d2f03ac Mon Sep 17 00:00:00 2001 From: Wenting Zhang Date: Fri, 8 Jul 2022 16:38:22 -0400 Subject: [PATCH 61/79] riscv: always honor the CONFIG_CMDLINE_FORCE when parsing dtb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stable inclusion from stable-5.10.152 commit 86e995f964f6ebc1ff48b0e1649f03b2c8931088 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit 10f6913c548b32ecb73801a16b120e761c6957ea ] When CONFIG_CMDLINE_FORCE is enabled, cmdline provided by CONFIG_CMDLINE are always used. This allows CONFIG_CMDLINE to be used regardless of the result of device tree scanning. This especially fixes the case where a device tree without the chosen node is supplied to the kernel. In such cases, early_init_dt_scan would return true. But inside early_init_dt_scan_chosen, the cmdline won't be updated as there is no chosen node in the device tree. As a result, CONFIG_CMDLINE is not copied into boot_command_line even if CONFIG_CMDLINE_FORCE is enabled. This commit allows properly update boot_command_line in this situation. Fixes: 8fd6e05c7463 ("arch: riscv: support kernel command line forcing when no DTB passed") Signed-off-by: Wenting Zhang Reviewed-by: Björn Töpel Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/PSBPR04MB399135DFC54928AB958D0638B1829@PSBPR04MB3991.apcprd04.prod.outlook.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- arch/riscv/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 5d17d3ce36fd..cc85858f7fe8 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -61,10 +61,10 @@ static void __init parse_dtb(void) pr_info("Machine model: %s\n", name); dump_stack_set_arch_desc("%s (DT)", name); } - return; + } else { + pr_err("No DTB passed to the kernel\n"); } - pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); -- Gitee From 5a2f75990db3c223f81ab60099927c034ba821b5 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 10 Mar 2021 13:11:38 +0800 Subject: [PATCH 62/79] perf pmu: Validate raw event with sysfs exported format bits stable inclusion from stable-5.10.152 commit dea47fefa6aa87256c8a46137c742060940a4197 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit e40647762fb5881360874e08e03e972d58d63c42 ] A raw PMU event (eventsel+umask) in the form of rNNN is supported by perf but lacks of checking for the validity of raw encoding. For example, bit 16 and bit 17 are not valid on KBL but perf doesn't report warning when encoding with these bits. Before: # ./perf stat -e cpu/r031234/ -a -- sleep 1 Performance counter stats for 'system wide': 0 cpu/r031234/ 1.003798924 seconds time elapsed It may silently measure the wrong event! The kernel supported bits have been exported through /sys/devices//format/. Perf collects the information to 'struct perf_pmu_format' and links it to 'pmu->format' list. The 'struct perf_pmu_format' has a bitmap which records the valid bits for this format. For example, root@kbl-ppc:/sys/devices/cpu/format# cat umask config:8-15 The valid bits (bit8-bit15) are recorded in bitmap of format 'umask'. We collect total valid bits of all formats, save to a local variable 'masks' and reverse it. Now '~masks' represents total invalid bits. bits = config & ~masks; The set bits in 'bits' indicate the invalid bits used in config. Finally we use bitmap_scnprintf to report the invalid bits. Some architectures may not export supported bits through sysfs, so if masks is 0, perf_pmu__warn_invalid_config directly returns. After: Single event without name: # ./perf stat -e cpu/r031234/ -a -- sleep 1 WARNING: event 'N/A' not valid (bits 16-17 of config '31234' not supported by kernel)! Performance counter stats for 'system wide': 0 cpu/r031234/ 1.001597373 seconds time elapsed Multiple events with names: # ./perf stat -e cpu/rf01234,name=aaa/,cpu/r031234,name=bbb/ -a -- sleep 1 WARNING: event 'aaa' not valid (bits 20,22 of config 'f01234' not supported by kernel)! WARNING: event 'bbb' not valid (bits 16-17 of config '31234' not supported by kernel)! Performance counter stats for 'system wide': 0 aaa 0 bbb 1.001573787 seconds time elapsed Warnings are reported for invalid bits. Co-developed-by: Jiri Olsa Signed-off-by: Jin Yao Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210310051138.12154-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo Stable-dep-of: e552b7be12ed ("perf: Skip and warn on unknown format 'configN' attrs") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- tools/perf/util/parse-events.c | 3 +++ tools/perf/util/pmu.c | 33 +++++++++++++++++++++++++++++++++ tools/perf/util/pmu.h | 3 +++ 3 files changed, 39 insertions(+) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 733a06ea596a..ae1a6f67a03a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu && attr->type == PERF_TYPE_RAW) + perf_pmu__warn_invalid_config(pmu, attr->config, name); + if (init_attr) event_attr_init(attr); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d41caeb35cf6..349012f7defb 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1716,3 +1716,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) return nr_caps; } + +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name) +{ + struct perf_pmu_format *format; + __u64 masks = 0, bits; + char buf[100]; + unsigned int i; + + list_for_each_entry(format, &pmu->format, list) { + if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG) + continue; + + for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS) + masks |= 1ULL << i; + } + + /* + * Kernel doesn't export any valid format bits. + */ + if (masks == 0) + return; + + bits = config & ~masks; + if (bits == 0) + return; + + bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf)); + + pr_warning("WARNING: event '%s' not valid (bits %s of config " + "'%llx' not supported by kernel)!\n", + name ?: "N/A", buf, config); +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a64e9c9ce731..d9aa8c958d21 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -120,4 +120,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name); + #endif /* __PMU_H */ -- Gitee From 456bfaac41e196354f47d893aead3171b33aa392 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 4 Oct 2022 14:12:35 -0500 Subject: [PATCH 63/79] perf: Skip and warn on unknown format 'configN' attrs stable inclusion from stable-5.10.152 commit ca4c49838278344854792bec2645b01e50471ccf category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit e552b7be12ed62357df84392efa525ecb01910fb ] If the kernel exposes a new perf_event_attr field in a format attr, perf will return an error stating the specified PMU can't be found. For example, a format attr with 'config3:0-63' causes an error as config3 is unknown to perf. This causes a compatibility issue between a newer kernel with older perf tool. Before this change with a kernel adding 'config3' I get: $ perf record -e arm_spe// -- true event syntax error: 'arm_spe//' \___ Cannot find PMU `arm_spe'. Missing kernel support? Run 'perf list' for a list of valid events Usage: perf record [] [] or: perf record [] -- [] -e, --event event selector. use 'perf list' to list available events After this change, I get: $ perf record -e arm_spe// -- true WARNING: 'arm_spe_0' format 'inv_event_filter' requires 'perf_event_attr::config3' which is not supported by this version of perf! [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.091 MB perf.data ] To support unknown configN formats, rework the YACC implementation to pass any config[0-9]+ format to perf_pmu__new_format() to handle with a warning. Reviewed-by: Namhyung Kim Signed-off-by: Rob Herring Tested-by: Leo Yan Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220914-arm-perf-tool-spe1-2-v2-v4-1-83c098e6212e@kernel.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- tools/perf/util/parse-events.c | 3 +++ tools/perf/util/pmu.c | 17 +++++++++++++++++ tools/perf/util/pmu.h | 2 ++ tools/perf/util/pmu.l | 2 -- tools/perf/util/pmu.y | 15 ++++----------- 5 files changed, 26 insertions(+), 13 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index ae1a6f67a03a..d4299a73cde0 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu) + perf_pmu__warn_invalid_formats(pmu); + if (pmu && attr->type == PERF_TYPE_RAW) perf_pmu__warn_invalid_config(pmu, attr->config, name); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 349012f7defb..ac45da0302a7 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -862,6 +862,23 @@ static struct perf_pmu *pmu_lookup(const char *name) return pmu; } +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) +{ + struct perf_pmu_format *format; + + /* fake pmu doesn't have format list */ + if (pmu == &perf_pmu__fake) + return; + + list_for_each_entry(format, &pmu->format, list) + if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) { + pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'" + "which is not supported by this version of perf!\n", + pmu->name, format->name, format->value); + return; + } +} + static struct perf_pmu *pmu_find(const char *name) { struct perf_pmu *pmu; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index d9aa8c958d21..7d208b850769 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -15,6 +15,7 @@ enum { PERF_PMU_FORMAT_VALUE_CONFIG, PERF_PMU_FORMAT_VALUE_CONFIG1, PERF_PMU_FORMAT_VALUE_CONFIG2, + PERF_PMU_FORMAT_VALUE_CONFIG_END, }; #define PERF_PMU_FORMAT_BITS 64 @@ -122,5 +123,6 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu); void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, char *name); +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); #endif /* __PMU_H */ diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l index a15d9fbd7c0e..58b4926cfaca 100644 --- a/tools/perf/util/pmu.l +++ b/tools/perf/util/pmu.l @@ -27,8 +27,6 @@ num_dec [0-9]+ {num_dec} { return value(10); } config { return PP_CONFIG; } -config1 { return PP_CONFIG1; } -config2 { return PP_CONFIG2; } - { return '-'; } : { return ':'; } , { return ','; } diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index bfd7e8509869..283efe059819 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -20,7 +20,7 @@ do { \ %} -%token PP_CONFIG PP_CONFIG1 PP_CONFIG2 +%token PP_CONFIG %token PP_VALUE PP_ERROR %type PP_VALUE %type bit_term @@ -47,18 +47,11 @@ PP_CONFIG ':' bits $3)); } | -PP_CONFIG1 ':' bits +PP_CONFIG PP_VALUE ':' bits { ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG1, - $3)); -} -| -PP_CONFIG2 ':' bits -{ - ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG2, - $3)); + $2, + $4)); } bits: -- Gitee From 56307fe9bc32e67cb4a38b5b4f1fe0bb38acefb7 Mon Sep 17 00:00:00 2001 From: Pavel Tikhomirov Date: Wed, 3 Feb 2021 15:41:56 +0300 Subject: [PATCH 64/79] fcntl: make F_GETOWN(EX) return 0 on dead owner task stable inclusion from stable-5.10.152 commit b1efc196446ae0e331045ad0ae9149021bc1642f category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit cc4a3f885e8f2bc3c86a265972e94fef32d68f67 ] Currently there is no way to differentiate the file with alive owner from the file with dead owner but pid of the owner reused. That's why CRIU can't actually know if it needs to restore file owner or not, because if it restores owner but actual owner was dead, this can introduce unexpected signals to the "false"-owner (which reused the pid). Let's change the api, so that F_GETOWN(EX) returns 0 in case actual owner is dead already. This comports with the POSIX spec, which states that a PID of 0 indicates that no signal will be sent. Cc: Jeff Layton Cc: "J. Bruce Fields" Cc: Alexander Viro Cc: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Cyrill Gorcunov Cc: Andrei Vagin Signed-off-by: Pavel Tikhomirov Signed-off-by: Jeff Layton Stable-dep-of: f671a691e299 ("fcntl: fix potential deadlocks for &fown_struct.lock") Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/fcntl.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/fs/fcntl.c b/fs/fcntl.c index 3eebcbead8bf..11bf039b0da9 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -148,11 +148,15 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { - pid_t pid; + pid_t pid = 0; read_lock(&filp->f_owner.lock); - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) - pid = -pid; + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { + pid = pid_vnr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + } + rcu_read_unlock(); read_unlock(&filp->f_owner.lock); return pid; } @@ -200,11 +204,14 @@ static int f_setown_ex(struct file *filp, unsigned long arg) static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; - struct f_owner_ex owner; + struct f_owner_ex owner = {}; int ret = 0; read_lock(&filp->f_owner.lock); - owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) + owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; -- Gitee From d9f3c4729ce779d0e4cc333b660347e71e2a1d3e Mon Sep 17 00:00:00 2001 From: Desmond Cheong Zhi Xi Date: Fri, 2 Jul 2021 17:18:30 +0800 Subject: [PATCH 65/79] fcntl: fix potential deadlocks for &fown_struct.lock stable inclusion from stable-5.10.152 commit f687e2111b6f1745bb32b7575224fe564d45b8b8 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- [ Upstream commit f671a691e299f58835d4660d642582bf0e8f6fda ] Syzbot reports a potential deadlock in do_fcntl: ======================================================== WARNING: possible irq lock inversion dependency detected 5.12.0-syzkaller #0 Not tainted -------------------------------------------------------- syz-executor132/8391 just changed the state of lock: ffff888015967bf8 (&f->f_owner.lock){.+..}-{2:2}, at: f_getown_ex fs/fcntl.c:211 [inline] ffff888015967bf8 (&f->f_owner.lock){.+..}-{2:2}, at: do_fcntl+0x8b4/0x1200 fs/fcntl.c:395 but this lock was taken by another, HARDIRQ-safe lock in the past: (&dev->event_lock){-...}-{2:2} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Chain exists of: &dev->event_lock --> &new->fa_lock --> &f->f_owner.lock Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&f->f_owner.lock); local_irq_disable(); lock(&dev->event_lock); lock(&new->fa_lock); lock(&dev->event_lock); *** DEADLOCK *** This happens because there is a lock hierarchy of &dev->event_lock --> &new->fa_lock --> &f->f_owner.lock from the following call chain: input_inject_event(): spin_lock_irqsave(&dev->event_lock,...); input_handle_event(): input_pass_values(): input_to_handler(): evdev_events(): evdev_pass_values(): spin_lock(&client->buffer_lock); __pass_event(): kill_fasync(): kill_fasync_rcu(): read_lock(&fa->fa_lock); send_sigio(): read_lock_irqsave(&fown->lock,...); However, since &dev->event_lock is HARDIRQ-safe, interrupts have to be disabled while grabbing &f->f_owner.lock, otherwise we invert the lock hierarchy. Hence, we replace calls to read_lock/read_unlock on &f->f_owner.lock, with read_lock_irq/read_unlock_irq. Reported-and-tested-by: syzbot+e6d5398a02c516ce5e70@syzkaller.appspotmail.com Signed-off-by: Desmond Cheong Zhi Xi Signed-off-by: Jeff Layton Signed-off-by: Sasha Levin Signed-off-by: wanxiaoqing --- fs/fcntl.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/fcntl.c b/fs/fcntl.c index 11bf039b0da9..fc000d40f235 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -149,7 +149,8 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { pid_t pid = 0; - read_lock(&filp->f_owner.lock); + + read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); @@ -157,7 +158,7 @@ pid_t f_getown(struct file *filp) pid = -pid; } rcu_read_unlock(); - read_unlock(&filp->f_owner.lock); + read_unlock_irq(&filp->f_owner.lock); return pid; } @@ -207,7 +208,7 @@ static int f_getown_ex(struct file *filp, unsigned long arg) struct f_owner_ex owner = {}; int ret = 0; - read_lock(&filp->f_owner.lock); + read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); @@ -230,7 +231,7 @@ static int f_getown_ex(struct file *filp, unsigned long arg) ret = -EINVAL; break; } - read_unlock(&filp->f_owner.lock); + read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); @@ -248,10 +249,10 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) uid_t src[2]; int err; - read_lock(&filp->f_owner.lock); + read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); - read_unlock(&filp->f_owner.lock); + read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); -- Gitee From fabc140e1aa7ebb22d96a496fbb0cddbb21c5dce Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Thu, 15 Oct 2020 23:57:56 +0530 Subject: [PATCH 66/79] arm64: dts: qcom: sc7180-trogdor: Fixup modem memory region stable inclusion from stable-5.10.152 commit cb1024d8a4d09198985adb252905b2f4039d79d5 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit ef9a5d188d663753e73a3c8e8910ceab8e9305c4 upstream. The modem firmware memory requirements vary between 32M/140M on no-lte/lte skus respectively, so fixup the modem memory region to reflect the requirements. Reviewed-by: Evan Green Signed-off-by: Sibi Sankar Link: https://lore.kernel.org/r/1602786476-27833-1-git-send-email-sibis@codeaurora.org Signed-off-by: Bjorn Andersson Acked-by: Alex Elder Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi | 4 ++++ arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi index 44956e3165a1..469aad4e5948 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lte-sku.dtsi @@ -9,6 +9,10 @@ &ap_sar_sensor { label = "proximity-wifi-lte"; }; +&mpss_mem { + reg = <0x0 0x86000000 0x0 0x8c00000>; +}; + &remoteproc_mpss { firmware-name = "qcom/sc7180-trogdor/modem/mba.mbn", "qcom/sc7180-trogdor/modem/qdsp6sw.mbn"; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index 5b2a616c6257..cb2c47f13a8a 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -39,7 +39,7 @@ atf_mem: memory@80b00000 { }; mpss_mem: memory@86000000 { - reg = <0x0 0x86000000 0x0 0x8c00000>; + reg = <0x0 0x86000000 0x0 0x2000000>; no-map; }; -- Gitee From 168b45f08004e86b4ffa37efa69caf0f01cd4735 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 19 Oct 2022 13:53:02 +0100 Subject: [PATCH 67/79] arm64: topology: move store_cpu_topology() to shared code stable inclusion from stable-5.10.152 commit a6e770733dc4ce616ff77f43f50507fa2034ff49 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 456797da792fa7cbf6698febf275fe9b36691f78 upstream. arm64's method of defining a default cpu topology requires only minimal changes to apply to RISC-V also. The current arm64 implementation exits early in a uniprocessor configuration by reading MPIDR & claiming that uniprocessor can rely on the default values. This is appears to be a hangover from prior to '3102bc0e6ac7 ("arm64: topology: Stop using MPIDR for topology information")', because the current code just assigns default values for multiprocessor systems. With the MPIDR references removed, store_cpu_topolgy() can be moved to the common arch_topology code. Reviewed-by: Sudeep Holla Acked-by: Catalin Marinas Reviewed-by: Atish Patra Signed-off-by: Conor Dooley Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/arm64/kernel/topology.c | 40 ------------------------------------ drivers/base/arch_topology.c | 19 +++++++++++++++++ 2 files changed, 19 insertions(+), 40 deletions(-) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 4358bc319306..f35af19b7055 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -22,46 +22,6 @@ #include #include -void store_cpu_topology(unsigned int cpuid) -{ - struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; - u64 mpidr; - - if (cpuid_topo->package_id != -1) - goto topology_populated; - - mpidr = read_cpuid_mpidr(); - - /* Uniprocessor systems can rely on default topology values */ - if (mpidr & MPIDR_UP_BITMASK) - return; - - /* - * This would be the place to create cpu topology based on MPIDR. - * - * However, it cannot be trusted to depict the actual topology; some - * pieces of the architecture enforce an artificial cap on Aff0 values - * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an - * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up - * having absolutely no relationship to the actual underlying system - * topology, and cannot be reasonably used as core / package ID. - * - * If the MT bit is set, Aff0 *could* be used to define a thread ID, but - * we still wouldn't be able to obtain a sane core ID. This means we - * need to entirely ignore MPIDR for any topology deduction. - */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = cpuid; - cpuid_topo->package_id = cpu_to_node(cpuid); - - pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", - cpuid, cpuid_topo->package_id, cpuid_topo->core_id, - cpuid_topo->thread_id, mpidr); - -topology_populated: - update_siblings_masks(cpuid); -} - #ifdef CONFIG_ACPI static bool __init acpi_cpu_is_threaded(int cpu) { diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 8272a3a002a3..51647926e605 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -596,4 +596,23 @@ void __init init_cpu_topology(void) else if (of_have_populated_dt() && parse_dt_topology()) reset_cpu_topology(); } + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); +} #endif -- Gitee From 5dafcd8533a997b231f58d202a89773fa8a93302 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 19 Oct 2022 13:53:03 +0100 Subject: [PATCH 68/79] riscv: topology: fix default topology reporting stable inclusion from stable-5.10.152 commit 79c3482fbe20e39630b0f95e1ffeb846aa945c41 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit fbd92809997a391f28075f1c8b5ee314c225557c upstream. RISC-V has no sane defaults to fall back on where there is no cpu-map in the devicetree. Without sane defaults, the package, core and thread IDs are all set to -1. This causes user-visible inaccuracies for tools like hwloc/lstopo which rely on the sysfs cpu topology files to detect a system's topology. On a PolarFire SoC, which should have 4 harts with a thread each, lstopo currently reports: Machine (793MB total) Package L#0 NUMANode L#0 (P#0 793MB) Core L#0 L1d L#0 (32KB) + L1i L#0 (32KB) + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + PU L#1 (P#1) L1d L#2 (32KB) + L1i L#2 (32KB) + PU L#2 (P#2) L1d L#3 (32KB) + L1i L#3 (32KB) + PU L#3 (P#3) Adding calls to store_cpu_topology() in {boot,smp} hart bringup code results in the correct topolgy being reported: Machine (793MB total) Package L#0 NUMANode L#0 (P#0 793MB) L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1 + PU L#1 (P#1) L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2 + PU L#2 (P#2) L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3 + PU L#3 (P#3) CC: stable@vger.kernel.org # 456797da792f: arm64: topology: move store_cpu_topology() to shared code Fixes: 03f11f03dbfe ("RISC-V: Parse cpu topology during boot.") Reported-by: Brice Goglin Link: https://github.com/open-mpi/hwloc/issues/536 Reviewed-by: Sudeep Holla Reviewed-by: Atish Patra Signed-off-by: Conor Dooley Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/riscv/Kconfig | 2 +- arch/riscv/kernel/smpboot.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 1b894c327578..557c4a8c4087 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -35,7 +35,7 @@ config RISCV select CLINT_TIMER if !MMU select COMMON_CLK select EDAC_SUPPORT - select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS select GENERIC_EARLY_IOREMAP diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 0b04e0eae3ab..0e0aed380e28 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -46,6 +46,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int cpuid; int ret; + store_cpu_topology(smp_processor_id()); + /* This covers non-smp usecase mandated by "nosmp" option */ if (max_cpus == 0) return; @@ -152,8 +154,8 @@ asmlinkage __visible void smp_callin(void) mmgrab(mm); current->active_mm = mm; + store_cpu_topology(curr_cpuid); notify_cpu_starting(curr_cpuid); - update_siblings_masks(curr_cpuid); set_cpu_online(curr_cpuid, 1); /* -- Gitee From 3a9e4203592842963d85bdda5ca401ca2280002d Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 31 Jan 2022 09:24:49 +0200 Subject: [PATCH 69/79] perf/x86/intel/pt: Relax address filter validation stable inclusion from stable-5.10.152 commit da54c5f4b5b547bab4c38f3356d0f779d9ad2098 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit c243cecb58e3905baeace8827201c14df8481e2a upstream. The requirement for 64-bit address filters is that they are canonical addresses. In other respects any address range is allowed which would include user space addresses. That can be useful for tracing virtual machine guests because address filtering can be used to advantage in place of current privilege level (CPL) filtering. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220131072453.2839535-2-adrian.hunter@intel.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/x86/events/intel/pt.c | 63 ++++++++++++++++++++++++++++++-------- 1 file changed, 50 insertions(+), 13 deletions(-) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index cc3b79c06685..95234f46b0fb 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -13,6 +13,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include +#include #include #include @@ -1348,11 +1350,37 @@ static void pt_addr_filters_fini(struct perf_event *event) event->hw.addr_filters = NULL; } -static inline bool valid_kernel_ip(unsigned long ip) +#ifdef CONFIG_X86_64 +static u64 canonical_address(u64 vaddr, u8 vaddr_bits) { - return virt_addr_valid(ip) && kernel_ip(ip); + return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } +static u64 is_canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return canonical_address(vaddr, vaddr_bits) == vaddr; +} + +/* Clamp to a canonical address greater-than-or-equal-to the address given */ +static u64 clamp_to_ge_canonical_addr(u64 vaddr, u8 vaddr_bits) +{ + return is_canonical_address(vaddr, vaddr_bits) ? + vaddr : + -BIT_ULL(vaddr_bits - 1); +} + +/* Clamp to a canonical address less-than-or-equal-to the address given */ +static u64 clamp_to_le_canonical_addr(u64 vaddr, u8 vaddr_bits) +{ + return is_canonical_address(vaddr, vaddr_bits) ? + vaddr : + BIT_ULL(vaddr_bits - 1) - 1; +} +#else +#define clamp_to_ge_canonical_addr(x, y) (x) +#define clamp_to_le_canonical_addr(x, y) (x) +#endif + static int pt_event_addr_filters_validate(struct list_head *filters) { struct perf_addr_filter *filter; @@ -1367,14 +1395,6 @@ static int pt_event_addr_filters_validate(struct list_head *filters) filter->action == PERF_ADDR_FILTER_ACTION_START) return -EOPNOTSUPP; - if (!filter->path.dentry) { - if (!valid_kernel_ip(filter->offset)) - return -EINVAL; - - if (!valid_kernel_ip(filter->offset + filter->size)) - return -EINVAL; - } - if (++range > intel_pt_validate_hw_cap(PT_CAP_num_address_ranges)) return -EOPNOTSUPP; } @@ -1398,9 +1418,26 @@ static void pt_event_addr_filters_sync(struct perf_event *event) if (filter->path.dentry && !fr[range].start) { msr_a = msr_b = 0; } else { - /* apply the offset */ - msr_a = fr[range].start; - msr_b = msr_a + fr[range].size - 1; + unsigned long n = fr[range].size - 1; + unsigned long a = fr[range].start; + unsigned long b; + + if (a > ULONG_MAX - n) + b = ULONG_MAX; + else + b = a + n; + /* + * Apply the offset. 64-bit addresses written to the + * MSRs must be canonical, but the range can encompass + * non-canonical addresses. Since software cannot + * execute at non-canonical addresses, adjusting to + * canonical addresses does not affect the result of the + * address filter. + */ + msr_a = clamp_to_ge_canonical_addr(a, boot_cpu_data.x86_virt_bits); + msr_b = clamp_to_le_canonical_addr(b, boot_cpu_data.x86_virt_bits); + if (msr_b < msr_a) + msr_a = msr_b = 0; } filters->filter[range].msr_a = msr_a; -- Gitee From ca62008744473724708967f29bf3da4a6d4cb730 Mon Sep 17 00:00:00 2001 From: Gaurav Kohli Date: Wed, 5 Oct 2022 22:52:59 -0700 Subject: [PATCH 70/79] hv_netvsc: Fix race between VF offering and VF association message from host stable inclusion from stable-5.10.152 commit dcaf6313202a02cee13302a04a9b0503352ddef2 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 365e1ececb2905f94cc10a5817c5b644a32a3ae2 upstream. During vm boot, there might be possibility that vf registration call comes before the vf association from host to vm. And this might break netvsc vf path, To prevent the same block vf registration until vf bind message comes from host. Cc: stable@vger.kernel.org Fixes: 00d7ddba11436 ("hv_netvsc: pair VF based on serial number") Reviewed-by: Haiyang Zhang Signed-off-by: Gaurav Kohli Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/net/hyperv/hyperv_net.h | 3 ++- drivers/net/hyperv/netvsc.c | 4 ++++ drivers/net/hyperv/netvsc_drv.c | 20 ++++++++++++++++++++ 3 files changed, 26 insertions(+), 1 deletion(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index a0f338cf1424..367878493e70 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -977,7 +977,8 @@ struct net_device_context { u32 vf_alloc; /* Serial number of the VF to team with */ u32 vf_serial; - + /* completion variable to confirm vf association */ + struct completion vf_add; /* Is the current data path through the VF NIC? */ bool data_path_is_vf; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 6a7ab930ef70..d15da8287df3 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1327,6 +1327,10 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + + if (net_device_ctx->vf_alloc) + complete(&net_device_ctx->vf_add); + netdev_info(ndev, "VF slot %u %s\n", net_device_ctx->vf_serial, net_device_ctx->vf_alloc ? "added" : "removed"); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 18484370da0d..f2020be43cfe 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2290,6 +2290,7 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) { struct device *parent = vf_netdev->dev.parent; struct net_device_context *ndev_ctx; + struct net_device *ndev; struct pci_dev *pdev; u32 serial; @@ -2316,6 +2317,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) return hv_get_drvdata(ndev_ctx->device_ctx); } + /* Fallback path to check synthetic vf with + * help of mac addr + */ + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) { + netdev_notice(vf_netdev, + "falling back to mac addr based matching\n"); + return ndev; + } + } + netdev_notice(vf_netdev, "no netdev found for vf serial:%u\n", serial); return NULL; @@ -2406,6 +2419,11 @@ static int netvsc_vf_changed(struct net_device *vf_netdev) return NOTIFY_OK; net_device_ctx->data_path_is_vf = vf_is_up; + if (vf_is_up && !net_device_ctx->vf_alloc) { + netdev_info(ndev, "Waiting for the VF association from host\n"); + wait_for_completion(&net_device_ctx->vf_add); + } + netvsc_switch_datapath(ndev, vf_is_up); netdev_info(ndev, "Data path switched %s VF: %s\n", vf_is_up ? "to" : "from", vf_netdev->name); @@ -2429,6 +2447,7 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) netvsc_vf_setxdp(vf_netdev, NULL); + reinit_completion(&net_device_ctx->vf_add); netdev_rx_handler_unregister(vf_netdev); netdev_upper_dev_unlink(vf_netdev, ndev); RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL); @@ -2466,6 +2485,7 @@ static int netvsc_probe(struct hv_device *dev, INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); + init_completion(&net_device_ctx->vf_add); spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup); -- Gitee From 7dbc6ebba1296ce8ac62eb319304b029b5928372 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Wed, 26 Oct 2022 17:22:46 +0200 Subject: [PATCH 71/79] ACPI: video: Force backlight native for more TongFang devices stable inclusion from stable-5.10.152 commit 67dafece56b6e78ccf956064b50f08c80dd6134e category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 3dbc80a3e4c55c4a5b89ef207bed7b7de36157b4 upstream. This commit is very different from the upstream commit! It fixes the same issue by adding more quirks, rather then the general fix from the 6.1 kernel, because the general fix from the 6.1 kernel is part of a larger refactoring of the backlight code which is not suitable for the stable series. As described in "ACPI: video: Drop NL5x?U, PF4NU1F and PF5?U?? acpi_backlight=native quirks" (10212754a0d2) the upstream commit "ACPI: video: Make backlight class device registration a separate step (v2)" (3dbc80a3e4c5) makes these quirks unnecessary. However as mentioned in this bugtracker ticket https://bugzilla.kernel.org/show_bug.cgi?id=215683#c17 the upstream fix is part of a larger patchset that is overall too complex for stable. The TongFang GKxNRxx, GMxNGxx, GMxZGxx, and GMxRGxx / TUXEDO Stellaris/Polaris Gen 1-4, have the same problem as the Clevo NL5xRU and NL5xNU / TUXEDO Aura 15 Gen1 and Gen2: They have a working native and video interface for screen backlight. However the default detection mechanism first registers the video interface before unregistering it again and switching to the native interface during boot. This results in a dangling SBIOS request for backlight change for some reason, causing the backlight to switch to ~2% once per boot on the first power cord connect or disconnect event. Setting the native interface explicitly circumvents this buggy behaviour by avoiding the unregistering process. Reviewed-by: Hans de Goede Signed-off-by: Werner Sembach Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/acpi/video_detect.c | 64 +++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index e39d59ad6496..b13713199ad9 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -500,6 +500,70 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "PF5LUXG"), }, }, + /* + * More Tongfang devices with the same issue as the Clevo NL5xRU and + * NL5xNU/TUXEDO Aura 15 Gen1 and Gen2. See the description above. + */ + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GKxNRxx"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1501A1650TI"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1501A2060"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1701A1650TI"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GKxNRxx", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "POLARIS1701A2060"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GMxNGxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxNGxx"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GMxZGxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxZGxx"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang GMxRGxx", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), + }, + }, /* * Desktops which falsely report a backlight and which our heuristics * for this do not catch. -- Gitee From 765272804d91286338eced2ccfeb6b490edc70ef Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 29 Sep 2022 08:20:10 -0700 Subject: [PATCH 72/79] x86/Kconfig: Drop check for -mabi=ms for CONFIG_EFI_STUB stable inclusion from stable-5.10.152 commit 6ab2287b26f133891aaaa8ac0623266775d51b0c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 33806e7cb8d50379f55c3e8f335e91e1b359dc7b upstream. A recent change in LLVM made CONFIG_EFI_STUB unselectable because it no longer pretends to support -mabi=ms, breaking the dependency in Kconfig. Lack of CONFIG_EFI_STUB can prevent kernels from booting via EFI in certain circumstances. This check was added by 8f24f8c2fc82 ("efi/libstub: Annotate firmware routines as __efiapi") to ensure that __attribute__((ms_abi)) was available, as -mabi=ms is not actually used in any cflags. According to the GCC documentation, this attribute has been supported since GCC 4.4.7. The kernel currently requires GCC 5.1 so this check is not necessary; even when that change landed in 5.6, the kernel required GCC 4.9 so it was unnecessary then as well. Clang supports __attribute__((ms_abi)) for all versions that are supported for building the kernel so no additional check is needed. Remove the 'depends on' line altogether to allow CONFIG_EFI_STUB to be selected when CONFIG_EFI is enabled, regardless of compiler. Fixes: 8f24f8c2fc82 ("efi/libstub: Annotate firmware routines as __efiapi") Signed-off-by: Nathan Chancellor Signed-off-by: Borislav Petkov Reviewed-by: Nick Desaulniers Acked-by: Ard Biesheuvel Cc: stable@vger.kernel.org Link: https://github.com/llvm/llvm-project/commit/d1ad006a8f64bdc17f618deffa9e7c91d82c444d [nathan: Fix conflict due to lack of c6dbd3e5e69c in older trees] Signed-off-by: Nathan Chancellor Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- arch/x86/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 159646da3c6b..d64e69013995 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1945,7 +1945,6 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI && !X86_USE_3DNOW - depends on $(cc-option,-mabi=ms) || X86_32 select RELOCATABLE help This kernel feature allows a bzImage to be loaded directly -- Gitee From 30636cd608738095cca1435d0054515345a0073b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 24 Oct 2022 13:34:14 -0700 Subject: [PATCH 73/79] Makefile.debug: re-enable debug info for .S files stable inclusion from stable-5.10.152 commit 3a260e9844c97c220603696b0bc225a8acf44d9c category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- This is _not_ an upstream commit and just for 5.10.y only. It is based on commit 32ef9e5054ec0321b9336058c58ec749e9c6b0fe upstream. Alexey reported that the fraction of unknown filename instances in kallsyms grew from ~0.3% to ~10% recently; Bill and Greg tracked it down to assembler defined symbols, which regressed as a result of: commit b8a9092330da ("Kbuild: do not emit debug info for assembly with LLVM_IAS=1") In that commit, I allude to restoring debug info for assembler defined symbols in a follow up patch, but it seems I forgot to do so in commit a66049e2cf0e ("Kbuild: make DWARF version a choice") Fixes: b8a9092330da ("Kbuild: do not emit debug info for assembly with LLVM_IAS=1") Signed-off-by: Nick Desaulniers Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- Makefile | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 21ffa61b6af7..fe1238c3d874 100644 --- a/Makefile +++ b/Makefile @@ -844,7 +844,9 @@ else DEBUG_CFLAGS += -g endif -ifneq ($(LLVM_IAS),1) +ifeq ($(LLVM_IAS),1) +KBUILD_AFLAGS += -g +else KBUILD_AFLAGS += -Wa,-gdwarf-2 endif -- Gitee From cd63b54de63f3275d7f84d9cbca3bf8733f4d646 Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 28 Sep 2022 12:57:44 +0300 Subject: [PATCH 74/79] mmc: core: Add SD card quirk for broken discard stable inclusion from stable-5.10.152 commit e2f9b62ead9a69f5f605bb8777be5c97f292972d category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 07d2872bf4c864eb83d034263c155746a2fb7a3b upstream. Some SD-cards from Sandisk that are SDA-6.0 compliant reports they supports discard, while they actually don't. This might cause mk2fs to fail while trying to format the card and revert it to a read-only mode. To fix this problem, let's add a card quirk (MMC_QUIRK_BROKEN_SD_DISCARD) to indicate that we shall fall-back to use the legacy erase command instead. Signed-off-by: Avri Altman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220928095744.16455-1-avri.altman@wdc.com [Ulf: Updated the commit message] Signed-off-by: Ulf Hansson Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- drivers/mmc/core/block.c | 7 ++++++- drivers/mmc/core/card.h | 6 ++++++ drivers/mmc/core/quirks.h | 6 ++++++ include/linux/mmc/card.h | 1 + 4 files changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 66a00b7c751f..6622e3262187 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1069,6 +1069,11 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) nr = blk_rq_sectors(req); do { + unsigned int erase_arg = card->erase_arg; + + if (mmc_card_broken_sd_discard(card)) + erase_arg = SD_ERASE_ARG; + err = 0; if (card->quirks & MMC_QUIRK_INAND_CMD38) { err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, @@ -1079,7 +1084,7 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) card->ext_csd.generic_cmd6_time); } if (!err) - err = mmc_erase(card, from, nr, card->erase_arg); + err = mmc_erase(card, from, nr, erase_arg); } while (err == -EIO && !mmc_blk_reset(md, card->host, type)); if (err) status = BLK_STS_IOERR; diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h index 7bd392d55cfa..5c6986131faf 100644 --- a/drivers/mmc/core/card.h +++ b/drivers/mmc/core/card.h @@ -70,6 +70,7 @@ struct mmc_fixup { #define EXT_CSD_REV_ANY (-1u) #define CID_MANFID_SANDISK 0x2 +#define CID_MANFID_SANDISK_SD 0x3 #define CID_MANFID_ATP 0x9 #define CID_MANFID_TOSHIBA 0x11 #define CID_MANFID_MICRON 0x13 @@ -222,4 +223,9 @@ static inline int mmc_card_broken_hpi(const struct mmc_card *c) return c->quirks & MMC_QUIRK_BROKEN_HPI; } +static inline int mmc_card_broken_sd_discard(const struct mmc_card *c) +{ + return c->quirks & MMC_QUIRK_BROKEN_SD_DISCARD; +} + #endif diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index d68e6e513a4f..c8c0f50a2076 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -99,6 +99,12 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_FIXUP("V10016", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc, MMC_QUIRK_TRIM_BROKEN), + /* + * Some SD cards reports discard support while they don't + */ + MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd, + MMC_QUIRK_BROKEN_SD_DISCARD), + END_FIXUP }; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 42df06c6b19c..ef870d1f4f5f 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -270,6 +270,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ -- Gitee From 9a64a238b2c1e423835450af256f91bf23634696 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sun, 9 Oct 2022 18:10:38 +0800 Subject: [PATCH 75/79] blk-wbt: fix that 'rwb->wc' is always set to 1 in wbt_init() stable inclusion from stable-5.10.152 commit 31b1570677e8bf85f48be8eb95e21804399b8295 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 285febabac4a16655372d23ff43e89ff6f216691 upstream. commit 8c5035dfbb94 ("blk-wbt: call rq_qos_add() after wb_normal is initialized") moves wbt_set_write_cache() before rq_qos_add(), which is wrong because wbt_rq_qos() is still NULL. Fix the problem by removing wbt_set_write_cache() and setting 'rwb->wc' directly. Noted that this patch also remove the redundant setting of 'rab->wc'. Fixes: 8c5035dfbb94 ("blk-wbt: call rq_qos_add() after wb_normal is initialized") Reported-by: kernel test robot Link: https://lore.kernel.org/r/202210081045.77ddf59b-yujie.liu@intel.com Signed-off-by: Yu Kuai Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20221009101038.1692875-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- block/blk-wbt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index bafdb8098893..6f63920f073c 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -838,12 +838,11 @@ int wbt_init(struct request_queue *q) rwb->last_comp = rwb->last_issue = jiffies; rwb->win_nsec = RWB_WINDOW_NSEC; rwb->enable_state = WBT_STATE_ON_DEFAULT; - rwb->wc = 1; + rwb->wc = test_bit(QUEUE_FLAG_WC, &q->queue_flags); rwb->rq_depth.default_depth = RWB_DEF_DEPTH; rwb->min_lat_nsec = wbt_default_latency_nsec(q); wbt_queue_depth_changed(&rwb->rqos); - wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); /* * Assign rwb and add the stats callback. -- Gitee From 94f50ae5b316f83a87dc0ce26431efe5942f0cae Mon Sep 17 00:00:00 2001 From: Seth Jenkins Date: Thu, 27 Oct 2022 11:36:52 -0400 Subject: [PATCH 76/79] mm: /proc/pid/smaps_rollup: fix no vma's null-deref stable inclusion from stable-5.10.152 commit a50ed2d28727ff605d95fb9a53be8ff94e8eaaf4 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- Commit 258f669e7e88 ("mm: /proc/pid/smaps_rollup: convert to single value seq_file") introduced a null-deref if there are no vma's in the task in show_smaps_rollup. Fixes: 258f669e7e88 ("mm: /proc/pid/smaps_rollup: convert to single value seq_file") Signed-off-by: Seth Jenkins Reviewed-by: Alexey Dobriyan Tested-by: Alexey Dobriyan Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- fs/proc/task_mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ff6cb51a5278..5b486198a968 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -974,7 +974,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v) vma = vma->vm_next; } - show_vma_header_prefix(m, priv->mm->mmap->vm_start, + show_vma_header_prefix(m, priv->mm->mmap ? priv->mm->mmap->vm_start : 0, last_vma_end, 0, 0, 0, 0); seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); -- Gitee From c99f3745ea18eecdf9fd7b4464c36565d16f5c41 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 14 Oct 2022 11:26:25 -0700 Subject: [PATCH 77/79] udp: Update reuse->has_conns under reuseport_lock. stable inclusion from stable-5.10.152 commit 43d5109296fab30b7467d7d399bb51f1bb27eff4 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- commit 69421bf98482d089e50799f45e48b25ce4a8d154 upstream. When we call connect() for a UDP socket in a reuseport group, we have to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket. However, the current way to set has_conns is illegal and possible to trigger that problem. reuseport_has_conns() changes has_conns under rcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock, reuseport_lock, but it doesn't for now. For this reason, there is a race below where we fail to set has_conns resulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking. cpu1 cpu2 +----+ +----+ __ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHED Note the likely(reuse) in reuseport_has_conns_set() is always true, but we put the test there for ease of review. [0] For the record, usually, sk_reuseport_cb is changed under lock_sock(). The only exception is reuseport_grow() & TCP reqsk migration case. 1) shutdown() TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk. 2) New listen() overflows reuse->socks[] and call reuseport_grow(). 3) reuse->max_socks overflows u16 with the new listener. 4) reuseport_grow() pops the old shutdown()ed listener from the array and update its sk->sk_reuseport_cb as NULL without lock_sock(). shutdown()ed TCP sk->sk_reuseport_cb can be changed without lock_sock(), but, reuseport_has_conns_set() is called only for UDP under lock_sock(), so likely(reuse) never be false in reuseport_has_conns_set(). [0]: https://lore.kernel.org/netdev/CANn89iLja=eQHbsM_Ta2sQF0tOGU8vAGrh_izRuuHjuO1ouUag@mail.gmail.com/ Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20221014182625.89913-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 16 ++++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 25 insertions(+), 10 deletions(-) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 505f1e18e9bf..3eac185ae2e8 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -38,21 +38,20 @@ extern struct sock *reuseport_select_sock(struct sock *sk, extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); -static inline bool reuseport_has_conns(struct sock *sk, bool set) +static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); - if (reuse) { - if (set) - reuse->has_conns = 1; - ret = reuse->has_conns; - } + if (reuse && reuse->has_conns) + ret = true; rcu_read_unlock(); return ret; } +void reuseport_has_conns_set(struct sock *sk); + #endif /* _SOCK_REUSEPORT_H */ diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index b065f0a103ed..49f9c2c4ffd5 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -18,6 +18,22 @@ DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); +void reuseport_has_conns_set(struct sock *sk) +{ + struct sock_reuseport *reuse; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (likely(reuse)) + reuse->has_conns = 1; + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_has_conns_set); + static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { unsigned int size = sizeof(struct sock_reuseport) + diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4a8550c49202..112c6e892d30 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = prandom_u32(); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4446aa8237ff..b093daaa3deb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -446,7 +446,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 206f66310a88..f4559e5bc84b 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -256,7 +256,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9b504bf49214..514e6a55959f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -179,7 +179,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; -- Gitee From 220d38c8cc6365642e37719fc342983f5545d03a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 30 Oct 2022 09:41:19 +0100 Subject: [PATCH 78/79] Linux 5.10.152 stable inclusion from stable-5.10.152^0 commit 7d51b4c67cfb95a069ccbe52f13963bfd9fe85b0 category: bugfix issue: #I4UU4A CVE: NA Signed-off-by: wanxiaoqing --------------------------------------- Link: https://lore.kernel.org/r/20221027165054.270676357@linuxfoundation.org Tested-by: Sudip Mukherjee Tested-by: Jon Hunter Tested-by: Pavel Machek (CIP) Tested-by: Linux Kernel Functional Testing Link: https://lore.kernel.org/r/20221028120232.344548477@linuxfoundation.org Tested-by: Rudi Heitbaum Tested-by: Pavel Machek (CIP) Tested-by: Sudip Mukherjee Tested-by: Florian Fainelli Tested-by: Guenter Roeck Tested-by: Linux Kernel Functional Testing Tested-by: Salvatore Bonaccorso Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index fe1238c3d874..6ff585d9301b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 151 +SUBLEVEL = 152 EXTRAVERSION = NAME = Dare mighty things -- Gitee From 147f7618369e5c2725986e520cb1df471ebccff8 Mon Sep 17 00:00:00 2001 From: wanxiaoqing Date: Tue, 7 Mar 2023 15:49:41 +0800 Subject: [PATCH 79/79] version uptade 5.10.150==>5.10.152 Signed-off-by: wanxiaoqing --- README.OpenSource | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.OpenSource b/README.OpenSource index 42c78144a02b..b1eec9c3045c 100644 --- a/README.OpenSource +++ b/README.OpenSource @@ -3,7 +3,7 @@ "Name": "linux-5.10", "License": "GPL-2.0+", "License File": "COPYING", - "Version Number": "5.10.150", + "Version Number": "5.10.152", "Owner": "liuyu82@huawei.com", "Upstream URL": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/log/?h=linux-5.10.y", "Description": "linux kernel 5.10" -- Gitee