From 9ca8581e79e51c57e60b3b8e3b89d816448f49fe Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 22 Jan 2022 10:47:22 +0900 Subject: [PATCH 01/43] ksmbd: fix SMB 3.11 posix extension mount failure cifs client set 4 to DataLength of create_posix context, which mean Mode variable of create_posix context is only available. So buffer validation of ksmbd should check only the size of Mode except for the size of Reserved variable. Fixes: 8f77150c15f8 ("ksmbd: add buffer validation for SMB2_CREATE_CONTEXT") Cc: stable@vger.kernel.org # v5.15+ Reported-by: Steve French Tested-by: Steve French Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 1866c81c5c99..3926ca18dca4 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2688,7 +2688,7 @@ int smb2_open(struct ksmbd_work *work) (struct create_posix *)context; if (le16_to_cpu(context->DataOffset) + le32_to_cpu(context->DataLength) < - sizeof(struct create_posix)) { + sizeof(struct create_posix) - 4) { rc = -EINVAL; goto err_out1; } From 40c67c291a93f8846c4a972c9ef1b7ba4544c8d0 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 12 Jan 2022 16:31:56 +0800 Subject: [PATCH 02/43] mmc: sdhci-of-esdhc: Check for error num after setting mask Because of the possible failure of the dma_supported(), the dma_set_mask_and_coherent() may return error num. Therefore, it should be better to check it and return the error if fails. And since the sdhci_setup_host() has already checked the return value of the enable_dma, we need not check it in sdhci_resume_host() again. Fixes: 5552d7ad596c ("mmc: sdhci-of-esdhc: set proper dma mask for ls104x chips") Signed-off-by: Jiasheng Jiang Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220112083156.1124782-1-jiasheng@iscas.ac.cn Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-of-esdhc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index a593b1fbd69e..0f3658b36513 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -524,12 +524,16 @@ static void esdhc_of_adma_workaround(struct sdhci_host *host, u32 intmask) static int esdhc_of_enable_dma(struct sdhci_host *host) { + int ret; u32 value; struct device *dev = mmc_dev(host->mmc); if (of_device_is_compatible(dev->of_node, "fsl,ls1043a-esdhc") || - of_device_is_compatible(dev->of_node, "fsl,ls1046a-esdhc")) - dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40)); + of_device_is_compatible(dev->of_node, "fsl,ls1046a-esdhc")) { + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40)); + if (ret) + return ret; + } value = sdhci_readl(host, ESDHC_DMA_SYSCTL); From 4d315357b3d6c315a7260420c6c6fc076e58d14b Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 19 Jan 2022 20:00:06 +0800 Subject: [PATCH 03/43] mmc: sh_mmcif: Check for null res pointer If there is no suitable resource, platform_get_resource() will return NULL. Therefore in order to avoid the dereference of the NULL pointer, it should be better to check the 'res'. Signed-off-by: Jiasheng Jiang Cc: stable@vger.kernel.org # v5.16+ Link: https://lore.kernel.org/r/20220119120006.1426964-1-jiasheng@iscas.ac.cn Signed-off-by: Ulf Hansson --- drivers/mmc/host/sh_mmcif.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index bcc595c70a9f..104dcd702870 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -405,6 +405,9 @@ static int sh_mmcif_dma_slave_config(struct sh_mmcif_host *host, struct dma_slave_config cfg = { 0, }; res = platform_get_resource(host->pd, IORESOURCE_MEM, 0); + if (!res) + return -EINVAL; + cfg.direction = direction; if (direction == DMA_DEV_TO_MEM) { From 379f56c24e698f14242f532b1d0a0f1747725e08 Mon Sep 17 00:00:00 2001 From: Andrey Skvortsov Date: Sat, 15 Jan 2022 15:14:46 +0300 Subject: [PATCH 04/43] mmc: core: Wait for command setting 'Power Off Notification' bit to complete SD card is allowed to signal busy on DAT0 up to 1s after the CMD49. According to SD spec (version 6.0 section 5.8.1.3) first host waits until busy of CMD49 is released and only then polls Power Management Status register up to 1s until the card indicates ready to power off. Without waiting for busy before polling status register sometimes card becomes unresponsive and system fails to suspend: [ 205.907459] Freezing remaining freezable tasks ... (elapsed 0.001 seconds) done. [ 206.421274] sunxi-mmc 1c0f000.mmc: data error, sending stop command [ 206.421321] sunxi-mmc 1c0f000.mmc: send stop command failed [ 206.421347] mmc0: error -110 reading status reg of PM func [ 206.421366] PM: dpm_run_callback(): mmc_bus_suspend+0x0/0x74 returns -110 [ 206.421402] mmcblk mmc0:aaaa: PM: failed to suspend async: error -110 [ 206.437064] PM: Some devices failed to suspend, or early wake event detected Tested with Sandisk Extreme PRO A2 64GB on Allwinner A64 system. Signed-off-by: Andrey Skvortsov Fixes: 2c5d42769038 ("mmc: core: Add support for Power Off Notification for SD cards") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220115121447.641524-1-andrej.skvortzov@gmail.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/sd.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 45f578793980..bd87012c220c 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -67,7 +67,7 @@ static const unsigned int sd_au_size[] = { __res & __mask; \ }) -#define SD_POWEROFF_NOTIFY_TIMEOUT_MS 2000 +#define SD_POWEROFF_NOTIFY_TIMEOUT_MS 1000 #define SD_WRITE_EXTR_SINGLE_TIMEOUT_MS 1000 struct sd_busy_data { @@ -1664,6 +1664,12 @@ static int sd_poweroff_notify(struct mmc_card *card) goto out; } + /* Find out when the command is completed. */ + err = mmc_poll_for_busy(card, SD_WRITE_EXTR_SINGLE_TIMEOUT_MS, false, + MMC_BUSY_EXTR_SINGLE); + if (err) + goto out; + cb_data.card = card; cb_data.reg_buf = reg_buf; err = __mmc_poll_for_busy(card->host, SD_POWEROFF_NOTIFY_TIMEOUT_MS, From 926fd9f23b27ca6587492c3f58f4c7f4cd01dad5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 13 Jan 2022 11:44:38 -0800 Subject: [PATCH 05/43] ima: fix reference leak in asymmetric_verify() Don't leak a reference to the key if its algorithm is unknown. Fixes: 947d70597236 ("ima: Support EC keys for signature verification") Cc: # v5.13+ Signed-off-by: Eric Biggers Reviewed-by: Stefan Berger Reviewed-by: Tianjia Zhang Signed-off-by: Mimi Zohar --- security/integrity/digsig_asymmetric.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c index 23240d793b07..895f4b9ce8c6 100644 --- a/security/integrity/digsig_asymmetric.c +++ b/security/integrity/digsig_asymmetric.c @@ -109,22 +109,25 @@ int asymmetric_verify(struct key *keyring, const char *sig, pk = asymmetric_key_public_key(key); pks.pkey_algo = pk->pkey_algo; - if (!strcmp(pk->pkey_algo, "rsa")) + if (!strcmp(pk->pkey_algo, "rsa")) { pks.encoding = "pkcs1"; - else if (!strncmp(pk->pkey_algo, "ecdsa-", 6)) + } else if (!strncmp(pk->pkey_algo, "ecdsa-", 6)) { /* edcsa-nist-p192 etc. */ pks.encoding = "x962"; - else if (!strcmp(pk->pkey_algo, "ecrdsa") || - !strcmp(pk->pkey_algo, "sm2")) + } else if (!strcmp(pk->pkey_algo, "ecrdsa") || + !strcmp(pk->pkey_algo, "sm2")) { pks.encoding = "raw"; - else - return -ENOPKG; + } else { + ret = -ENOPKG; + goto out; + } pks.digest = (u8 *)data; pks.digest_size = datalen; pks.s = hdr->sig; pks.s_size = siglen; ret = verify_signature(key, &pks); +out: key_put(key); pr_debug("%s() = %d\n", __func__, ret); return ret; From 47307c31d90ae7d52cebbbc7c1d4ff213213d4e9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jan 2022 12:38:11 -0800 Subject: [PATCH 06/43] crypto: octeontx2 - Avoid stack variable overflow Building with -Warray-bounds showed a stack variable array index overflow. Increase the expected size of the array to avoid the warning: In file included from ./include/linux/printk.h:555, from ./include/asm-generic/bug.h:22, from ./arch/x86/include/asm/bug.h:84, from ./include/linux/bug.h:5, from ./include/linux/mmdebug.h:5, from ./include/linux/gfp.h:5, from ./include/linux/firmware.h:7, from drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c:5: drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c: In function 'otx2_cpt_print_uc_dbg_info': ./include/linux/dynamic_debug.h:162:33: warning: array subscript 4 is above array bounds of 'u32[4]' {aka 'unsigned int[4]'} [-Warray-bounds] 162 | _dynamic_func_call(fmt, __dynamic_pr_debug, \ | ^ ./include/linux/dynamic_debug.h:134:17: note: in definition of macro '__dynamic_func_call' 134 | func(&id, ##__VA_ARGS__); \ | ^~~~ ./include/linux/dynamic_debug.h:162:9: note: in expansion of macro '_dynamic_func_call' 162 | _dynamic_func_call(fmt, __dynamic_pr_debug, \ | ^~~~~~~~~~~~~~~~~~ ./include/linux/printk.h:570:9: note: in expansion of macro 'dynamic_pr_debug' 570 | dynamic_pr_debug(fmt, ##__VA_ARGS__) | ^~~~~~~~~~~~~~~~ drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c:1807:41: note: in expansion of macro 'pr_debug' 1807 | pr_debug("Mask: %8.8x %8.8x %8.8x %8.8x %8.8x", | ^~~~~~~~ drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c:1765:13: note: while referencing 'mask' 1765 | u32 mask[4]; | ^~~~ This is justified because the mask size (eng_grps->engs_num) can be at most 144 (OTX2_CPT_MAX_ENGINES bits), which is larger than available storage. 4 * 32 == 128, so this must be 5: 5 * 32bit = 160. Additionally clear the mask before conversion so trailing bits are zero. Cc: Herbert Xu Cc: Boris Brezillon Cc: Arnaud Ebalard Cc: Srujana Challa Cc: "David S. Miller" Cc: Suheil Chandran Cc: Shijith Thotton Cc: Lukasz Bartosik Cc: linux-crypto@vger.kernel.org Fixes: d9d7749773e8 ("crypto: octeontx2 - add apis for custom engine groups") Acked-by: Ard Biesheuvel Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c index 4c8ebdf671ca..1b4d425bbf0e 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c @@ -1753,7 +1753,6 @@ void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf) char engs_info[2 * OTX2_CPT_NAME_LENGTH]; struct otx2_cpt_eng_grp_info *grp; struct otx2_cpt_engs_rsvd *engs; - u32 mask[4]; int i, j; pr_debug("Engine groups global info"); @@ -1785,6 +1784,8 @@ void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf) for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) { engs = &grp->engs[j]; if (engs->type) { + u32 mask[5] = { }; + get_engs_info(grp, engs_info, 2 * OTX2_CPT_NAME_LENGTH, j); pr_debug("Slot%d: %s", j, engs_info); From bd2db32e7c3e35bd4d9b8bbff689434a50893546 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 27 Jan 2022 08:16:38 +0100 Subject: [PATCH 07/43] moxart: fix potential use-after-free on remove path It was reported that the mmc host structure could be accessed after it was freed in moxart_remove(), so fix this by saving the base register of the device and using it instead of the pointer dereference. Cc: Ulf Hansson Cc: Xiyu Yang Cc: Xin Xiong Cc: Xin Tan Cc: Tony Lindgren Cc: Yang Li Cc: linux-mmc@vger.kernel.org Cc: stable Reported-by: whitehat002 Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220127071638.4057899-1-gregkh@linuxfoundation.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/moxart-mmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index 16d1c7a43d33..b6eb75f4bbfc 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -705,12 +705,12 @@ static int moxart_remove(struct platform_device *pdev) if (!IS_ERR_OR_NULL(host->dma_chan_rx)) dma_release_channel(host->dma_chan_rx); mmc_remove_host(mmc); - mmc_free_host(mmc); writel(0, host->base + REG_INTERRUPT_MASK); writel(0, host->base + REG_POWER_CONTROL); writel(readl(host->base + REG_CLOCK_CONTROL) | CLK_OFF, host->base + REG_CLOCK_CONTROL); + mmc_free_host(mmc); return 0; } From 2c212e1baedcd782b2535a3f86bc491977677c0e Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Fri, 28 Jan 2022 15:06:43 +0100 Subject: [PATCH 08/43] KVM: s390: Return error on SIDA memop on normal guest Refuse SIDA memops on guests which are not protected. For normal guests, the secure instruction data address designation, which determines the location we access, is not under control of KVM. Fixes: 19e122776886 (KVM: S390: protvirt: Introduce instruction data area bounce buffer) Signed-off-by: Janis Schoetterl-Glausch Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger --- arch/s390/kvm/kvm-s390.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 577f1ead6a51..2296b1ff1e02 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4667,6 +4667,8 @@ static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu, return -EINVAL; if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) return -E2BIG; + if (!kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; switch (mop->op) { case KVM_S390_MEMOP_SIDA_READ: From d9c4e39c1f8f8a8ebaccf00b8f22c14364b2d27e Mon Sep 17 00:00:00 2001 From: "trondmy@kernel.org" Date: Tue, 18 Jan 2022 19:25:42 -0500 Subject: [PATCH 09/43] NFS: Don't overfill uncached readdir pages If we're doing an uncached read of the directory, then we ideally want to read only the exact set of entries that will fit in the buffer supplied by the getdents() system call. So unlike the case where we're reading into the page cache, let's send only one READDIR call, before trying to fill up the buffer. Fixes: 35df59d3ef69 ("NFS: Reduce number of RPC calls when doing uncached readdir") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 848f3b8fb821..43df0b365b98 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -867,7 +867,8 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, status = nfs_readdir_page_filler(desc, entry, pages, pglen, arrays, narrays); - } while (!status && nfs_readdir_page_needs_filling(page)); + } while (!status && nfs_readdir_page_needs_filling(page) && + page_mapping(page)); nfs_readdir_free_pages(pages, array_size); out: From ce292d8faf41f62e0fb0c78476c6fce5d629235a Mon Sep 17 00:00:00 2001 From: "trondmy@kernel.org" Date: Tue, 18 Jan 2022 19:52:16 -0500 Subject: [PATCH 10/43] NFS: Don't skip directory entries when doing uncached readdir Ensure that we initialise desc->cache_entry_index correctly in uncached_readdir(). Fixes: d1bacf9eb2fd ("NFS: add readdir cache array") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 43df0b365b98..a3de586d21e2 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1042,6 +1042,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) goto out; desc->page_index = 0; + desc->cache_entry_index = 0; desc->last_cookie = desc->dir_cookie; desc->duped = 0; From e1d2699b96793d19388e302fa095e0da2c145701 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Jan 2022 22:10:52 -0500 Subject: [PATCH 11/43] NFS: Avoid duplicate uncached readdir calls on eof If we've reached the end of the directory, then cache that information in the context so that we don't need to do an uncached readdir in order to rediscover that fact. Fixes: 794092c57f89 ("NFS: Do uncached readdir when we're seeking a cookie in an empty page cache") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 20 +++++++++++++++----- include/linux/nfs_fs.h | 1 + 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a3de586d21e2..7bc7cf6b26f0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -80,6 +80,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir ctx->dir_cookie = 0; ctx->dup_cookie = 0; ctx->page_index = 0; + ctx->eof = false; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) @@ -168,6 +169,7 @@ struct nfs_readdir_descriptor { unsigned int cache_entry_index; signed char duped; bool plus; + bool eob; bool eof; }; @@ -989,7 +991,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->name, ent->name_len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { - desc->eof = true; + desc->eob = true; break; } memcpy(desc->verf, verf, sizeof(desc->verf)); @@ -1005,7 +1007,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, desc->duped = 1; } if (array->page_is_eof) - desc->eof = true; + desc->eof = !desc->eob; kunmap(desc->page); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n", @@ -1048,7 +1050,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz); - for (i = 0; !desc->eof && i < sz && arrays[i]; i++) { + for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { desc->page = arrays[i]; nfs_do_filldir(desc, verf); } @@ -1107,9 +1109,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->duped = dir_ctx->duped; page_index = dir_ctx->page_index; desc->attr_gencount = dir_ctx->attr_gencount; + desc->eof = dir_ctx->eof; memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); spin_unlock(&file->f_lock); + if (desc->eof) { + res = 0; + goto out_free; + } + if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && list_is_singular(&nfsi->open_files)) invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); @@ -1143,7 +1151,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) nfs_do_filldir(desc, nfsi->cookieverf); nfs_readdir_page_unlock_and_put_cached(desc); - } while (!desc->eof); + } while (!desc->eob && !desc->eof); spin_lock(&file->f_lock); dir_ctx->dir_cookie = desc->dir_cookie; @@ -1151,9 +1159,10 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) dir_ctx->duped = desc->duped; dir_ctx->attr_gencount = desc->attr_gencount; dir_ctx->page_index = desc->page_index; + dir_ctx->eof = desc->eof; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); - +out_free: kfree(desc); out: @@ -1195,6 +1204,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) if (offset == 0) memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf)); dir_ctx->duped = 0; + dir_ctx->eof = false; } spin_unlock(&filp->f_lock); return offset; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 02aa49323d1d..68f81d8d36de 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -107,6 +107,7 @@ struct nfs_open_dir_context { __u64 dup_cookie; pgoff_t page_index; signed char duped; + bool eof; }; /* From 83230351c523b04ff8a029a4bdf97d881ecb96fc Mon Sep 17 00:00:00 2001 From: Xiaoke Wang Date: Sat, 15 Jan 2022 09:11:11 +0800 Subject: [PATCH 12/43] integrity: check the return value of audit_log_start() audit_log_start() returns audit_buffer pointer on success or NULL on error, so it is better to check the return value of it. Fixes: 3323eec921ef ("integrity: IMA as an integrity service provider") Signed-off-by: Xiaoke Wang Cc: Reviewed-by: Paul Moore Signed-off-by: Mimi Zohar --- security/integrity/integrity_audit.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/security/integrity/integrity_audit.c b/security/integrity/integrity_audit.c index 29220056207f..0ec5e4c22cb2 100644 --- a/security/integrity/integrity_audit.c +++ b/security/integrity/integrity_audit.c @@ -45,6 +45,8 @@ void integrity_audit_message(int audit_msgno, struct inode *inode, return; ab = audit_log_start(audit_context(), GFP_KERNEL, audit_msgno); + if (!ab) + return; audit_log_format(ab, "pid=%d uid=%u auid=%u ses=%u", task_pid_nr(current), from_kuid(&init_user_ns, current_uid()), From f7333b9572d0559e00352a926c92f29f061b4569 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 25 Jan 2022 17:46:23 -0500 Subject: [PATCH 13/43] ima: Remove ima_policy file before directory The removal of ima_dir currently fails since ima_policy still exists, so remove the ima_policy file before removing the directory. Fixes: 4af4662fa4a9 ("integrity: IMA policy") Signed-off-by: Stefan Berger Cc: Acked-by: Christian Brauner Signed-off-by: Mimi Zohar --- security/integrity/ima/ima_fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 3d8e9d5db5aa..3ad8f7734208 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -496,12 +496,12 @@ int __init ima_fs_init(void) return 0; out: + securityfs_remove(ima_policy); securityfs_remove(violations); securityfs_remove(runtime_measurements_count); securityfs_remove(ascii_runtime_measurements); securityfs_remove(binary_runtime_measurements); securityfs_remove(ima_symlink); securityfs_remove(ima_dir); - securityfs_remove(ima_policy); return -1; } From bb8e52e4906f148c2faf6656b5106cf7233e9301 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 31 Jan 2022 18:11:39 +0100 Subject: [PATCH 14/43] ima: Allow template selection with ima_template[_fmt]= after ima_hash= Commit c2426d2ad5027 ("ima: added support for new kernel cmdline parameter ima_template_fmt") introduced an additional check on the ima_template variable to avoid multiple template selection. Unfortunately, ima_template could be also set by the setup function of the ima_hash= parameter, when it calls ima_template_desc_current(). This causes attempts to choose a new template with ima_template= or with ima_template_fmt=, after ima_hash=, to be ignored. Achieve the goal of the commit mentioned with the new static variable template_setup_done, so that template selection requests after ima_hash= are not ignored. Finally, call ima_init_template_list(), if not already done, to initialize the list of templates before lookup_template_desc() is called. Reported-by: Guo Zihua Signed-off-by: Roberto Sassu Cc: stable@vger.kernel.org Fixes: c2426d2ad5027 ("ima: added support for new kernel cmdline parameter ima_template_fmt") Signed-off-by: Mimi Zohar --- security/integrity/ima/ima_template.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index 694560396be0..db1ad6d7a57f 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -29,6 +29,7 @@ static struct ima_template_desc builtin_templates[] = { static LIST_HEAD(defined_templates); static DEFINE_SPINLOCK(template_list); +static int template_setup_done; static const struct ima_template_field supported_fields[] = { {.field_id = "d", .field_init = ima_eventdigest_init, @@ -101,10 +102,11 @@ static int __init ima_template_setup(char *str) struct ima_template_desc *template_desc; int template_len = strlen(str); - if (ima_template) + if (template_setup_done) return 1; - ima_init_template_list(); + if (!ima_template) + ima_init_template_list(); /* * Verify that a template with the supplied name exists. @@ -128,6 +130,7 @@ static int __init ima_template_setup(char *str) } ima_template = template_desc; + template_setup_done = 1; return 1; } __setup("ima_template=", ima_template_setup); @@ -136,7 +139,7 @@ static int __init ima_template_fmt_setup(char *str) { int num_templates = ARRAY_SIZE(builtin_templates); - if (ima_template) + if (template_setup_done) return 1; if (template_desc_init_fields(str, NULL, NULL) < 0) { @@ -147,6 +150,7 @@ static int __init ima_template_fmt_setup(char *str) builtin_templates[num_templates - 1].fmt = str; ima_template = builtin_templates + num_templates - 1; + template_setup_done = 1; return 1; } From 89677197ae709eb1ab3646952c44f6a171c9e74c Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Tue, 1 Feb 2022 15:37:10 -0500 Subject: [PATCH 15/43] ima: Do not print policy rule with inactive LSM labels Before printing a policy rule scan for inactive LSM labels in the policy rule. Inactive LSM labels are identified by args_p != NULL and rule == NULL. Fixes: 483ec26eed42 ("ima: ima/lsm policy rule loading logic bug fixes") Signed-off-by: Stefan Berger Cc: # v5.6+ Acked-by: Christian Brauner [zohar@linux.ibm.com: Updated "Fixes" tag] Signed-off-by: Mimi Zohar --- security/integrity/ima/ima_policy.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 320ca80aacab..2a1f6418b10a 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1967,6 +1967,14 @@ int ima_policy_show(struct seq_file *m, void *v) rcu_read_lock(); + /* Do not print rules with inactive LSM labels */ + for (i = 0; i < MAX_LSM_RULES; i++) { + if (entry->lsm[i].args_p && !entry->lsm[i].rule) { + rcu_read_unlock(); + return 0; + } + } + if (entry->action & MEASURE) seq_puts(m, pt(Opt_measure)); if (entry->action & DONT_MEASURE) From de4d73b16d5d9c3e5d03a66046e5410e1e74f903 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 27 Jan 2022 14:17:10 -0800 Subject: [PATCH 16/43] kunit: fix missing f in f-string in run_checks.py We're missing the `f` prefix to have python do string interpolation, so we'd never end up printing what the actual "unexpected" error is. Fixes: ee92ed38364e ("kunit: add run_checks.py script to validate kunit changes") Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- tools/testing/kunit/run_checks.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 4f32133ed77c..13d854afca9d 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -61,7 +61,7 @@ def main(argv: Sequence[str]) -> None: elif isinstance(ex, subprocess.CalledProcessError): print(f'{name}: FAILED') else: - print('{name}: unexpected exception: {ex}') + print(f'{name}: unexpected exception: {ex}') continue output = ex.output From 6d896d3b44cf64ab9b2483697e222098e7b72f70 Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Thu, 20 Jan 2022 21:10:11 +0900 Subject: [PATCH 17/43] ksmbd: smbd: validate buffer descriptor structures Check ChannelInfoOffset and ChannelInfoLength to validate buffer descriptor structures. And add a debug log to print the structures' content. Acked-by: Namjae Jeon Signed-off-by: Hyunchul Lee Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 36 ++++++++++++++++++++++++++++++------ 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 3926ca18dca4..6806994383d9 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -6126,13 +6126,26 @@ static int smb2_set_remote_key_for_rdma(struct ksmbd_work *work, __le16 ChannelInfoOffset, __le16 ChannelInfoLength) { + unsigned int i, ch_count; + if (work->conn->dialect == SMB30_PROT_ID && Channel != SMB2_CHANNEL_RDMA_V1) return -EINVAL; - if (ChannelInfoOffset == 0 || - le16_to_cpu(ChannelInfoLength) < sizeof(*desc)) + ch_count = le16_to_cpu(ChannelInfoLength) / sizeof(*desc); + if (ksmbd_debug_types & KSMBD_DEBUG_RDMA) { + for (i = 0; i < ch_count; i++) { + pr_info("RDMA r/w request %#x: token %#x, length %#x\n", + i, + le32_to_cpu(desc[i].token), + le32_to_cpu(desc[i].length)); + } + } + if (ch_count != 1) { + ksmbd_debug(RDMA, "RDMA multiple buffer descriptors %d are not supported yet\n", + ch_count); return -EINVAL; + } work->need_invalidate_rkey = (Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE); @@ -6185,9 +6198,15 @@ int smb2_read(struct ksmbd_work *work) if (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE || req->Channel == SMB2_CHANNEL_RDMA_V1) { + unsigned int ch_offset = le16_to_cpu(req->ReadChannelInfoOffset); + + if (ch_offset < offsetof(struct smb2_read_req, Buffer)) { + err = -EINVAL; + goto out; + } err = smb2_set_remote_key_for_rdma(work, (struct smb2_buffer_desc_v1 *) - &req->Buffer[0], + ((char *)req + ch_offset), req->Channel, req->ReadChannelInfoOffset, req->ReadChannelInfoLength); @@ -6428,11 +6447,16 @@ int smb2_write(struct ksmbd_work *work) if (req->Channel == SMB2_CHANNEL_RDMA_V1 || req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE) { - if (req->Length != 0 || req->DataOffset != 0) - return -EINVAL; + unsigned int ch_offset = le16_to_cpu(req->WriteChannelInfoOffset); + + if (req->Length != 0 || req->DataOffset != 0 || + ch_offset < offsetof(struct smb2_write_req, Buffer)) { + err = -EINVAL; + goto out; + } err = smb2_set_remote_key_for_rdma(work, (struct smb2_buffer_desc_v1 *) - &req->Buffer[0], + ((char *)req + ch_offset), req->Channel, req->WriteChannelInfoOffset, req->WriteChannelInfoLength); From 97550c7478a2da93e348d8c3075d92cddd473a78 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 30 Jan 2022 18:28:56 +0900 Subject: [PATCH 18/43] ksmbd: fix same UniqueId for dot and dotdot entries ksmbd sets the inode number to UniqueId. However, the same UniqueId for dot and dotdot entry is set to the inode number of the parent inode. This patch set them using the current inode and parent inode. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb_common.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index ef7f42b0290a..9a7e211dbf4f 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -308,14 +308,17 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, for (i = 0; i < 2; i++) { struct kstat kstat; struct ksmbd_kstat ksmbd_kstat; + struct dentry *dentry; if (!dir->dot_dotdot[i]) { /* fill dot entry info */ if (i == 0) { d_info->name = "."; d_info->name_len = 1; + dentry = dir->filp->f_path.dentry; } else { d_info->name = ".."; d_info->name_len = 2; + dentry = dir->filp->f_path.dentry->d_parent; } if (!match_pattern(d_info->name, d_info->name_len, @@ -327,7 +330,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, ksmbd_kstat.kstat = &kstat; ksmbd_vfs_fill_dentry_attrs(work, user_ns, - dir->filp->f_path.dentry->d_parent, + dentry, &ksmbd_kstat); rc = fn(conn, info_level, d_info, &ksmbd_kstat); if (rc) From 04e260948a160d3b7d622bf4c8a96fa4577c09bd Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 30 Jan 2022 18:31:01 +0900 Subject: [PATCH 19/43] ksmbd: don't align last entry offset in smb2 query directory When checking smb2 query directory packets from other servers, OutputBufferLength is different with ksmbd. Other servers add an unaligned next offset to OutputBufferLength for the last entry. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 7 ++++--- fs/ksmbd/vfs.h | 1 + 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 6806994383d9..67e8e28e3fc3 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -3422,9 +3422,9 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, goto free_conv_name; } - struct_sz = readdir_info_level_struct_sz(info_level); - next_entry_offset = ALIGN(struct_sz - 1 + conv_len, - KSMBD_DIR_INFO_ALIGNMENT); + struct_sz = readdir_info_level_struct_sz(info_level) - 1 + conv_len; + next_entry_offset = ALIGN(struct_sz, KSMBD_DIR_INFO_ALIGNMENT); + d_info->last_entry_off_align = next_entry_offset - struct_sz; if (next_entry_offset > d_info->out_buf_len) { d_info->out_buf_len = 0; @@ -3976,6 +3976,7 @@ int smb2_query_dir(struct ksmbd_work *work) ((struct file_directory_info *) ((char *)rsp->Buffer + d_info.last_entry_offset)) ->NextEntryOffset = 0; + d_info.data_count -= d_info.last_entry_off_align; rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index adf94a4f22fa..8c37aaf936ab 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -47,6 +47,7 @@ struct ksmbd_dir_info { int last_entry_offset; bool hide_dot_file; int flags; + int last_entry_off_align; }; struct ksmbd_readdir_data { From deae24b0b13ff5f46022124fbfc2c72fc534bc6a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 30 Jan 2022 18:28:11 +0900 Subject: [PATCH 20/43] ksmbd: reduce smb direct max read/write size ksmbd does not support more than one Buffer Descriptor V1 element in an smbdirect protocol request. Reducing the maximum read/write size to about 512KB allows interoperability with Windows over a wider variety of RDMA NICs, as an interim workaround. Reviewed-by: Tom Talpey Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/transport_rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index 3c1ec1ac0b27..ba5a22bc2e6d 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -80,7 +80,7 @@ static int smb_direct_max_fragmented_recv_size = 1024 * 1024; /* The maximum single-message size which can be received */ static int smb_direct_max_receive_size = 8192; -static int smb_direct_max_read_write_size = 1048512; +static int smb_direct_max_read_write_size = 524224; static int smb_direct_max_outstanding_rw_ops = 8; From f9929ef6a2a55f03aac61248c6a3a987b8546f2a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 1 Feb 2022 18:20:34 +0900 Subject: [PATCH 21/43] ksmbd: add support for key exchange When mounting cifs client, can see the following warning message. CIFS: decode_ntlmssp_challenge: authentication has been weakened as server does not support key exchange To remove this warning message, Add support for key exchange feature to ksmbd. This patch decrypts 16-byte ciphertext value sent by the client using RC4 with session key. The decrypted value is the recovered secondary key that will use instead of the session key for signing and sealing. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/Kconfig | 4 ++-- fs/ksmbd/auth.c | 27 +++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 2 deletions(-) diff --git a/fs/Kconfig b/fs/Kconfig index 7a2b11c0b803..6c7dc1387beb 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -369,8 +369,8 @@ source "fs/ksmbd/Kconfig" config SMBFS_COMMON tristate - default y if CIFS=y - default m if CIFS=m + default y if CIFS=y || SMB_SERVER=y + default m if CIFS=m || SMB_SERVER=m source "fs/coda/Kconfig" source "fs/afs/Kconfig" diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index dc3d061edda9..911444d21267 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -29,6 +29,7 @@ #include "mgmt/user_config.h" #include "crypto_ctx.h" #include "transport_ipc.h" +#include "../smbfs_common/arc4.h" /* * Fixed format data defining GSS header and fixed string @@ -336,6 +337,29 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, nt_len - CIFS_ENCPWD_SIZE, domain_name, conn->ntlmssp.cryptkey); kfree(domain_name); + + /* The recovered secondary session key */ + if (conn->ntlmssp.client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) { + struct arc4_ctx *ctx_arc4; + unsigned int sess_key_off, sess_key_len; + + sess_key_off = le32_to_cpu(authblob->SessionKey.BufferOffset); + sess_key_len = le16_to_cpu(authblob->SessionKey.Length); + + if (blob_len < (u64)sess_key_off + sess_key_len) + return -EINVAL; + + ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL); + if (!ctx_arc4) + return -ENOMEM; + + cifs_arc4_setkey(ctx_arc4, sess->sess_key, + SMB2_NTLMV2_SESSKEY_SIZE); + cifs_arc4_crypt(ctx_arc4, sess->sess_key, + (char *)authblob + sess_key_off, sess_key_len); + kfree_sensitive(ctx_arc4); + } + return ret; } @@ -408,6 +432,9 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob, (cflags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) flags |= NTLMSSP_NEGOTIATE_EXTENDED_SEC; + if (cflags & NTLMSSP_NEGOTIATE_KEY_XCH) + flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + chgblob->NegotiateFlags = cpu_to_le32(flags); len = strlen(ksmbd_netbios_name()); name = kmalloc(2 + UNICODE_LEN(len), GFP_KERNEL); From 4cbd93c3c110447adc66cb67c08af21f939ae2d7 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Thu, 27 Jan 2022 13:29:51 -0800 Subject: [PATCH 22/43] pidfd: fix test failure due to stack overflow on some arches When running the pidfd_fdinfo_test on arm64, it fails for me. After some digging, the reason is that the child exits due to SIGBUS, because it overflows the 1024 byte stack we've reserved for it. To fix the issue, increase the stack size to 8192 bytes (this number is somewhat arbitrary, and was arrived at through experimentation -- I kept doubling until the failure no longer occurred). Also, let's make the issue easier to debug. wait_for_pid() returns an ambiguous value: it may return -1 in all of these cases: 1. waitpid() itself returned -1 2. waitpid() returned success, but we found !WIFEXITED(status). 3. The child process exited, but it did so with a -1 exit code. There's no way for the caller to tell the difference. So, at least log which occurred, so the test runner can debug things. While debugging this, I found that we had !WIFEXITED(), because the child exited due to a signal. This seems like a reasonably common case, so also print out whether or not we have WIFSIGNALED(), and the associated WTERMSIG() (if any). This lets us see the SIGBUS I'm fixing clearly when it occurs. Finally, I'm suspicious of allocating the child's stack on our stack. man clone(2) suggests that the correct way to do this is with mmap(), and in particular by setting MAP_STACK. So, switch to doing it that way instead. Signed-off-by: Axel Rasmussen Acked-by: Christian Brauner Signed-off-by: Shuah Khan --- tools/testing/selftests/pidfd/pidfd.h | 13 ++++++++--- .../selftests/pidfd/pidfd_fdinfo_test.c | 22 +++++++++++++++---- 2 files changed, 28 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 01f8d3c0cf2c..6922d6417e1c 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -68,7 +68,7 @@ #define PIDFD_SKIP 3 #define PIDFD_XFAIL 4 -int wait_for_pid(pid_t pid) +static inline int wait_for_pid(pid_t pid) { int status, ret; @@ -78,13 +78,20 @@ again: if (errno == EINTR) goto again; + ksft_print_msg("waitpid returned -1, errno=%d\n", errno); return -1; } - if (!WIFEXITED(status)) + if (!WIFEXITED(status)) { + ksft_print_msg( + "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n", + WIFSIGNALED(status), WTERMSIG(status)); return -1; + } - return WEXITSTATUS(status); + ret = WEXITSTATUS(status); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); + return ret; } static inline int sys_pidfd_open(pid_t pid, unsigned int flags) diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 22558524f71c..3fd8e903118f 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "pidfd.h" #include "../kselftest.h" @@ -80,7 +81,10 @@ static inline int error_check(struct error *err, const char *test_name) return err->code; } +#define CHILD_STACK_SIZE 8192 + struct child { + char *stack; pid_t pid; int fd; }; @@ -89,17 +93,22 @@ static struct child clone_newns(int (*fn)(void *), void *args, struct error *err) { static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD; - size_t stack_size = 1024; - char *stack[1024] = { 0 }; struct child ret; if (!(flags & CLONE_NEWUSER) && geteuid() != 0) flags |= CLONE_NEWUSER; + ret.stack = mmap(NULL, CHILD_STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (ret.stack == MAP_FAILED) { + error_set(err, -1, "mmap of stack failed (errno %d)", errno); + return ret; + } + #ifdef __ia64__ - ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd); + ret.pid = __clone2(fn, ret.stack, CHILD_STACK_SIZE, flags, args, &ret.fd); #else - ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd); + ret.pid = clone(fn, ret.stack + CHILD_STACK_SIZE, flags, args, &ret.fd); #endif if (ret.pid < 0) { @@ -129,6 +138,11 @@ static inline int child_join(struct child *child, struct error *err) else if (r > 0) error_set(err, r, "child %d reported: %d", child->pid, r); + if (munmap(child->stack, CHILD_STACK_SIZE)) { + error_set(err, -1, "munmap of child stack failed (errno %d)", errno); + r = -1; + } + return r; } From e2aa5e650b07693477dff554053605976789fd68 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Thu, 27 Jan 2022 14:11:15 -0800 Subject: [PATCH 23/43] selftests: fixup build warnings in pidfd / clone3 tests These are some trivial fixups, which were needed to build the tests with clang and -Werror. The following issues are fixed: - Remove various unused variables. - In child_poll_leader_exit_test, clang isn't smart enough to realize syscall(SYS_exit, 0) won't return, so it complains we never return from a non-void function. Add an extra exit(0) to appease it. - In test_pidfd_poll_leader_exit, ret may be branched on despite being uninitialized, if we have !use_waitpid. Initialize it to zero to get the right behavior in that case. Signed-off-by: Axel Rasmussen Acked-by: Christian Brauner Signed-off-by: Shuah Khan --- tools/testing/selftests/clone3/clone3.c | 2 -- tools/testing/selftests/pidfd/pidfd_test.c | 6 +++--- tools/testing/selftests/pidfd/pidfd_wait.c | 5 ++--- 3 files changed, 5 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 076cf4325f78..cd4582129c7d 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -126,8 +126,6 @@ static void test_clone3(uint64_t flags, size_t size, int expected, int main(int argc, char *argv[]) { - pid_t pid; - uid_t uid = getuid(); ksft_print_header(); diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 529eb700ac26..9a2d64901d59 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -441,7 +441,6 @@ static void test_pidfd_poll_exec(int use_waitpid) { int pid, pidfd = 0; int status, ret; - pthread_t t1; time_t prog_start = time(NULL); const char *test_name = "pidfd_poll check for premature notification on child thread exec"; @@ -500,13 +499,14 @@ static int child_poll_leader_exit_test(void *args) */ *child_exit_secs = time(NULL); syscall(SYS_exit, 0); + /* Never reached, but appeases compiler thinking we should return. */ + exit(0); } static void test_pidfd_poll_leader_exit(int use_waitpid) { int pid, pidfd = 0; - int status, ret; - time_t prog_start = time(NULL); + int status, ret = 0; const char *test_name = "pidfd_poll check for premature notification on non-empty" "group leader exit"; diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index be2943f072f6..17999e082aa7 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -39,7 +39,7 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, TEST(wait_simple) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), @@ -47,7 +47,6 @@ TEST(wait_simple) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, @@ -88,7 +87,7 @@ TEST(wait_simple) TEST(wait_states) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), From 183f80fd72db42c9cc483aa7a5e8e881355d0b03 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Tue, 1 Feb 2022 18:38:36 +0000 Subject: [PATCH 24/43] selftests/ir: fix build with ancient kernel headers Since commit e2bcbd7769ee ("tools headers UAPI: remove stale lirc.h"), the build of the selftests fails on rhel 8 since its version of /usr/include/linux/lirc.h has no definition of RC_PROTO_RCMM32, etc [1]. [1] https://lkml.org/lkml/2022/1/28/275 Fixes: e2bcbd7769ee ("tools headers UAPI: remove stale lirc.h") Reviewed-by: Shuah Khan Reported-by: kernel test robot Signed-off-by: Sean Young Signed-off-by: Shuah Khan --- tools/testing/selftests/ir/ir_loopback.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index 06256c96df12..f4a15cbdd5ea 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -29,6 +29,16 @@ #define SYSFS_PATH_MAX 256 #define DNAME_PATH_MAX 256 +/* + * Support ancient lirc.h which does not have these values. Can be removed + * once RHEL 8 is no longer a relevant testing platform. + */ +#if RC_PROTO_MAX < 26 +#define RC_PROTO_RCMM12 24 +#define RC_PROTO_RCMM24 25 +#define RC_PROTO_RCMM32 26 +#endif + static const struct { enum rc_proto proto; const char *name; From c6ce9c5831cae515d375a01b97ae1778689acf19 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 2 Feb 2022 17:46:48 +1100 Subject: [PATCH 25/43] crypto: api - Move cryptomgr soft dependency into algapi The soft dependency on cryptomgr is only needed in algapi because if algapi isn't present then no algorithms can be loaded. This also fixes the case where api is built-in but algapi is built as a module as the soft dependency would otherwise get lost. Fixes: 8ab23d547f65 ("crypto: api - Add softdep on cryptomgr") Reported-by: Jan Beulich Signed-off-by: Herbert Xu Tested-by: Jan Beulich Signed-off-by: Herbert Xu --- crypto/algapi.c | 1 + crypto/api.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/algapi.c b/crypto/algapi.c index a366cb3e8aa1..76fdaa16bd4a 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -1324,3 +1324,4 @@ module_exit(crypto_algapi_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cryptographic algorithms API"); +MODULE_SOFTDEP("pre: cryptomgr"); diff --git a/crypto/api.c b/crypto/api.c index cf0869dd130b..7ddfe946dd56 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -643,4 +643,3 @@ EXPORT_SYMBOL_GPL(crypto_req_done); MODULE_DESCRIPTION("Cryptographic core API"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: cryptomgr"); From fda17afc6166e975bec1197bd94cd2a3317bce3f Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 7 Feb 2022 11:27:53 +0900 Subject: [PATCH 26/43] ata: libata-core: Fix ata_dev_config_cpr() The concurrent positioning ranges log page 47h is a general purpose log page and not a subpage of the indentify device log. Using ata_identify_page_supported() to test for concurrent positioning ranges support is thus wrong. ata_log_supported() must be used. Furthermore, unlike other advanced ATA features (e.g. NCQ priority), accesses to the concurrent positioning ranges log page are not gated by a feature bit from the device IDENTIFY data. Since many older drives react badly to the READ LOG EXT and/or READ LOG DMA EXT commands isued to read device log pages, avoid problems with older drives by limiting the concurrent positioning ranges support detection to drives implementing at least the ACS-4 ATA standard (major version 11). This additional condition effectively turns ata_dev_config_cpr() into a nop for older drives, avoiding problems in the field. Fixes: fe22e1c2f705 ("libata: support concurrent positioning ranges log") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215519 Cc: stable@vger.kernel.org Reviewed-by: Hannes Reinecke Tested-by: Abderraouf Adjal Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 14 ++++++-------- include/linux/ata.h | 2 +- 2 files changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e1b1dd215267..ba9273f80069 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2448,23 +2448,21 @@ static void ata_dev_config_cpr(struct ata_device *dev) struct ata_cpr_log *cpr_log = NULL; u8 *desc, *buf = NULL; - if (!ata_identify_page_supported(dev, - ATA_LOG_CONCURRENT_POSITIONING_RANGES)) + if (ata_id_major_version(dev->id) < 11 || + !ata_log_supported(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES)) goto out; /* - * Read IDENTIFY DEVICE data log, page 0x47 - * (concurrent positioning ranges). We can have at most 255 32B range - * descriptors plus a 64B header. + * Read the concurrent positioning ranges log (0x47). We can have at + * most 255 32B range descriptors plus a 64B header. */ buf_len = (64 + 255 * 32 + 511) & ~511; buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) goto out; - err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, - ATA_LOG_CONCURRENT_POSITIONING_RANGES, - buf, buf_len >> 9); + err_mask = ata_read_log_page(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES, + 0, buf, buf_len >> 9); if (err_mask) goto out; diff --git a/include/linux/ata.h b/include/linux/ata.h index 199e47e97d64..21292b5bbb55 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -324,12 +324,12 @@ enum { ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_IDENTIFY_DEVICE = 0x30, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, - ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, From 468d126dab45718feeb728319be20bd869a5eaa7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 2 Feb 2022 18:52:01 -0500 Subject: [PATCH 27/43] NFS: Fix initialisation of nfs_client cl_flags field For some long forgotten reason, the nfs_client cl_flags field is initialised in nfs_get_client() instead of being initialised at allocation time. This quirk was harmless until we moved the call to nfs_create_rpc_client(). Fixes: dd99e9f98fbf ("NFSv4: Initialise connection to the server in nfs4_alloc_client()") Cc: stable@vger.kernel.org # 4.8.x Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index f18e80fda9bf..d1f34229e11a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -177,6 +177,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) INIT_LIST_HEAD(&clp->cl_superblocks); clp->cl_rpcclient = ERR_PTR(-EINVAL); + clp->cl_flags = cl_init->init_flags; clp->cl_proto = cl_init->proto; clp->cl_nconnect = cl_init->nconnect; clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1; @@ -423,7 +424,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) list_add_tail(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); - new->cl_flags = cl_init->init_flags; return rpc_ops->init_client(new, cl_init); } From a9c10b5b3b67b3750a10c8b089b2e05f5e176e33 Mon Sep 17 00:00:00 2001 From: Dan Aloni Date: Tue, 25 Jan 2022 22:06:46 +0200 Subject: [PATCH 28/43] xprtrdma: fix pointer derefs in error cases of rpcrdma_ep_create If there are failures then we must not leave the non-NULL pointers with the error value, otherwise `rpcrdma_ep_destroy` gets confused and tries free them, resulting in an Oops. Signed-off-by: Dan Aloni Acked-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index f172d1298013..7b5fce2faa10 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -413,6 +413,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) IB_POLL_WORKQUEUE); if (IS_ERR(ep->re_attr.send_cq)) { rc = PTR_ERR(ep->re_attr.send_cq); + ep->re_attr.send_cq = NULL; goto out_destroy; } @@ -421,6 +422,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) IB_POLL_WORKQUEUE); if (IS_ERR(ep->re_attr.recv_cq)) { rc = PTR_ERR(ep->re_attr.recv_cq); + ep->re_attr.recv_cq = NULL; goto out_destroy; } ep->re_receive_count = 0; @@ -459,6 +461,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) ep->re_pd = ib_alloc_pd(device, 0); if (IS_ERR(ep->re_pd)) { rc = PTR_ERR(ep->re_pd); + ep->re_pd = NULL; goto out_destroy; } From 3d4a39404ba323b08fb42bcdca9a015144e213dd Mon Sep 17 00:00:00 2001 From: Yang Li Date: Thu, 13 Jan 2022 10:26:04 +0800 Subject: [PATCH 29/43] NFS: Fix nfs4_proc_get_locations() kernel-doc comment Add the description of @server and @fhandle, and remove the excess @inode in nfs4_proc_get_locations() kernel-doc comment to remove warnings found by running scripts/kernel-doc, which is caused by using 'make W=1'. fs/nfs/nfs4proc.c:8219: warning: Function parameter or member 'server' not described in 'nfs4_proc_get_locations' fs/nfs/nfs4proc.c:8219: warning: Function parameter or member 'fhandle' not described in 'nfs4_proc_get_locations' fs/nfs/nfs4proc.c:8219: warning: Excess function parameter 'inode' description in 'nfs4_proc_get_locations' Reported-by: Abaci Robot Signed-off-by: Yang Li Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b18f31b2c9e7..f5020828ab65 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8032,7 +8032,8 @@ static int _nfs41_proc_get_locations(struct nfs_server *server, /** * nfs4_proc_get_locations - discover locations for a migrated FSID - * @inode: inode on FSID that is migrating + * @server: pointer to nfs_server to process + * @fhandle: pointer to the kernel NFS client file handle * @locations: result of query * @page: buffer * @cred: credential to use for this operation From 63db37e99ac17f575766c9317f927c8d4c6e8cdf Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Mon, 7 Feb 2022 11:14:47 -0500 Subject: [PATCH 30/43] MAINTAINERS: Update my email address Signed-off-by: Anna Schumaker --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index f41088418aae..afff78665e0f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13566,7 +13566,7 @@ F: tools/testing/selftests/nci/ NFS, SUNRPC, AND LOCKD CLIENTS M: Trond Myklebust -M: Anna Schumaker +M: Anna Schumaker L: linux-nfs@vger.kernel.org S: Maintained W: http://client.linux-nfs.org From b49ea673e119f59c71645e2f65b3ccad857c90ee Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 17 Jan 2022 16:36:53 +1100 Subject: [PATCH 31/43] SUNRPC: lock against ->sock changing during sysfs read ->sock can be set to NULL asynchronously unless ->recv_mutex is held. So it is important to hold that mutex. Otherwise a sysfs read can trigger an oops. Commit 17f09d3f619a ("SUNRPC: Check if the xprt is connected before handling sysfs reads") appears to attempt to fix this problem, but it only narrows the race window. Fixes: 17f09d3f619a ("SUNRPC: Check if the xprt is connected before handling sysfs reads") Fixes: a8482488a7d6 ("SUNRPC query transport's source port") Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- net/sunrpc/sysfs.c | 5 ++++- net/sunrpc/xprtsock.c | 7 ++++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index b64a0286b182..05c758da6a92 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -115,11 +115,14 @@ static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj, } sock = container_of(xprt, struct sock_xprt, xprt); - if (kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) + mutex_lock(&sock->recv_mutex); + if (sock->sock == NULL || + kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) goto out; ret = sprintf(buf, "%pISc\n", &saddr); out: + mutex_unlock(&sock->recv_mutex); xprt_put(xprt); return ret + 1; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 69b6ee5a5fd1..0f39e08ee580 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1641,7 +1641,12 @@ static int xs_get_srcport(struct sock_xprt *transport) unsigned short get_srcport(struct rpc_xprt *xprt) { struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); - return xs_sock_getport(sock->sock); + unsigned short ret = 0; + mutex_lock(&sock->recv_mutex); + if (sock->sock) + ret = xs_sock_getport(sock->sock); + mutex_unlock(&sock->recv_mutex); + return ret; } EXPORT_SYMBOL(get_srcport); From 92a68053c3468705e2c7c752c9a3f256304a35a6 Mon Sep 17 00:00:00 2001 From: Akira Kawata Date: Mon, 7 Feb 2022 20:20:44 +0900 Subject: [PATCH 32/43] Documentation: KUnit: Fix usage bug Fix a bug of kunit documentation. Link: https://bugzilla.kernel.org/show_bug.cgi?id=205773 : Quoting Steve Pfetsch: : : kunit documentation is incorrect: : https://kunit.dev/third_party/stable_kernel/docs/usage.html : struct rectangle *self = container_of(this, struct shape, parent); : : : Shouldn't it be: : struct rectangle *self = container_of(this, struct rectangle, parent); : ? Signed-off-by: Akira Kawata Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- Documentation/dev-tools/kunit/usage.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 76af931a332c..1c83e7d60a8a 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -242,7 +242,7 @@ example: int rectangle_area(struct shape *this) { - struct rectangle *self = container_of(this, struct shape, parent); + struct rectangle *self = container_of(this, struct rectangle, parent); return self->length * self->width; }; From d9565bf40da22426d2f660cb31700b6858d1911d Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Wed, 2 Feb 2022 17:31:22 +0100 Subject: [PATCH 33/43] MIPS: DTS: CI20: fix how ddc power is enabled Originally we proposed a new hdmi-5v-supply regulator reference for CI20 device tree but that was superseded by a better idea to use the already defined "ddc-en-gpios" property of the "hdmi-connector". Since "MIPS: DTS: CI20: Add DT nodes for HDMI setup" has already been applied to v5.17-rc1, we add this on top. Fixes: ae1b8d2c2de9 ("MIPS: DTS: CI20: Add DT nodes for HDMI setup") Signed-off-by: H. Nikolaus Schaller Reviewed-by: Paul Cercueil Signed-off-by: Thomas Bogendoerfer --- arch/mips/boot/dts/ingenic/ci20.dts | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 3e336b3dbb10..ab6e3dc0bc1d 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -83,6 +83,8 @@ label = "HDMI OUT"; type = "a"; + ddc-en-gpios = <&gpa 25 GPIO_ACTIVE_HIGH>; + port { hdmi_con: endpoint { remote-endpoint = <&dw_hdmi_out>; @@ -114,17 +116,6 @@ gpio = <&gpf 14 GPIO_ACTIVE_LOW>; enable-active-high; }; - - hdmi_power: fixedregulator@3 { - compatible = "regulator-fixed"; - - regulator-name = "hdmi_power"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - - gpio = <&gpa 25 0>; - enable-active-high; - }; }; &ext { @@ -576,8 +567,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pins_hdmi_ddc>; - hdmi-5v-supply = <&hdmi_power>; - ports { #address-cells = <1>; #size-cells = <0>; From 0cb4d23ae08c48f6bf3c29a8e5c4a74b8388b960 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 Feb 2022 15:19:34 -0500 Subject: [PATCH 34/43] NFSD: Fix the behavior of READ near OFFSET_MAX Dan Aloni reports: > Due to commit 8cfb9015280d ("NFS: Always provide aligned buffers to > the RPC read layers") on the client, a read of 0xfff is aligned up > to server rsize of 0x1000. > > As a result, in a test where the server has a file of size > 0x7fffffffffffffff, and the client tries to read from the offset > 0x7ffffffffffff000, the read causes loff_t overflow in the server > and it returns an NFS code of EINVAL to the client. The client as > a result indefinitely retries the request. The Linux NFS client does not handle NFS?ERR_INVAL, even though all NFS specifications permit servers to return that status code for a READ. Instead of NFS?ERR_INVAL, have out-of-range READ requests succeed and return a short result. Set the EOF flag in the result to prevent the client from retrying the READ request. This behavior appears to be consistent with Solaris NFS servers. Note that NFSv3 and NFSv4 use u64 offset values on the wire. These must be converted to loff_t internally before use -- an implicit type cast is not adequate for this purpose. Otherwise VFS checks against sb->s_maxbytes do not work properly. Reported-by: Dan Aloni Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever --- fs/nfsd/nfs3proc.c | 8 ++++++-- fs/nfsd/nfs4proc.c | 8 ++++++-- fs/nfsd/nfs4xdr.c | 8 ++------ 3 files changed, 14 insertions(+), 10 deletions(-) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 2c681785186f..b5a52528f19f 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -150,13 +150,17 @@ nfsd3_proc_read(struct svc_rqst *rqstp) unsigned int len; int v; - argp->count = min_t(u32, argp->count, max_blocksize); - dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n", SVCFH_fmt(&argp->fh), (unsigned long) argp->count, (unsigned long long) argp->offset); + argp->count = min_t(u32, argp->count, max_blocksize); + if (argp->offset > (u64)OFFSET_MAX) + argp->offset = (u64)OFFSET_MAX; + if (argp->offset + argp->count > (u64)OFFSET_MAX) + argp->count = (u64)OFFSET_MAX - argp->offset; + v = 0; len = argp->count; resp->pages = rqstp->rq_next_page; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ed1ee25647be..71d735b125a0 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -782,12 +782,16 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; read->rd_nf = NULL; - if (read->rd_offset >= OFFSET_MAX) - return nfserr_inval; trace_nfsd_read_start(rqstp, &cstate->current_fh, read->rd_offset, read->rd_length); + read->rd_length = min_t(u32, read->rd_length, svc_max_payload(rqstp)); + if (read->rd_offset > (u64)OFFSET_MAX) + read->rd_offset = (u64)OFFSET_MAX; + if (read->rd_offset + read->rd_length > (u64)OFFSET_MAX) + read->rd_length = (u64)OFFSET_MAX - read->rd_offset; + /* * If we do a zero copy read, then a client will see read data * that reflects the state of the file *after* performing the diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 899de438e529..f5e3430bb6ff 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3986,10 +3986,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, } xdr_commit_encode(xdr); - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, + maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) @@ -4826,10 +4824,8 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr_resource; xdr_commit_encode(xdr); - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, + maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); count = maxcount; eof = read->rd_offset >= i_size_read(file_inode(file)); From e6faac3f58c7c4176b66f63def17a34232a17b0e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 31 Jan 2022 13:01:53 -0500 Subject: [PATCH 35/43] NFSD: Fix ia_size underflow iattr::ia_size is a loff_t, which is a signed 64-bit type. NFSv3 and NFSv4 both define file size as an unsigned 64-bit type. Thus there is a range of valid file size values an NFS client can send that is already larger than Linux can handle. Currently decode_fattr4() dumps a full u64 value into ia_size. If that value happens to be larger than S64_MAX, then ia_size underflows. I'm about to fix up the NFSv3 behavior as well, so let's catch the underflow in the common code path: nfsd_setattr(). Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever --- fs/nfsd/vfs.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 99c2b9dfbb10..0cccceb105e7 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -435,6 +435,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, .ia_size = iap->ia_size, }; + host_err = -EFBIG; + if (iap->ia_size < 0) + goto out_unlock; + host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); if (host_err) goto out_unlock; From a648fdeb7c0e17177a2280344d015dba3fbe3314 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 25 Jan 2022 15:59:57 -0500 Subject: [PATCH 36/43] NFSD: Fix NFSv3 SETATTR/CREATE's handling of large file sizes iattr::ia_size is a loff_t, so these NFSv3 procedures must be careful to deal with incoming client size values that are larger than s64_max without corrupting the value. Silently capping the value results in storing a different value than the client passed in which is unexpected behavior, so remove the min_t() check in decode_sattr3(). Note that RFC 1813 permits only the WRITE procedure to return NFS3ERR_FBIG. We believe that NFSv3 reference implementations also return NFS3ERR_FBIG when ia_size is too large. Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever --- fs/nfsd/nfs3xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 7c45ba4db61b..2e47a07029f1 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -254,7 +254,7 @@ svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (xdr_stream_decode_u64(xdr, &newsize) < 0) return false; iap->ia_valid |= ATTR_SIZE; - iap->ia_size = min_t(u64, newsize, NFS_OFFSET_MAX); + iap->ia_size = newsize; } if (xdr_stream_decode_u32(xdr, &set_it) < 0) return false; From 6260d9a56ab352b54891ec66ab0eced57d55abc6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 25 Jan 2022 16:36:22 -0500 Subject: [PATCH 37/43] NFSD: Clamp WRITE offsets Ensure that a client cannot specify a WRITE range that falls in a byte range outside what the kernel's internal types (such as loff_t, which is signed) can represent. The kiocb iterators, invoked in nfsd_vfs_write(), should properly limit write operations to within the underlying file system's s_maxbytes. Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever --- fs/nfsd/nfs3proc.c | 5 +++++ fs/nfsd/nfs4proc.c | 5 +++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index b5a52528f19f..aca38ed1526e 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -203,6 +203,11 @@ nfsd3_proc_write(struct svc_rqst *rqstp) (unsigned long long) argp->offset, argp->stable? " stable" : ""); + resp->status = nfserr_fbig; + if (argp->offset > (u64)OFFSET_MAX || + argp->offset + argp->len > (u64)OFFSET_MAX) + return rpc_success; + fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; nvecs = svc_fill_write_vector(rqstp, &argp->payload); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 71d735b125a0..b207c76a873f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1022,8 +1022,9 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned long cnt; int nvecs; - if (write->wr_offset >= OFFSET_MAX) - return nfserr_inval; + if (write->wr_offset > (u64)OFFSET_MAX || + write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX) + return nfserr_fbig; cnt = write->wr_buflen; trace_nfsd_write_start(rqstp, &cstate->current_fh, From 3f965021c8bc38965ecb1924f570c4842b33d408 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 24 Jan 2022 15:50:31 -0500 Subject: [PATCH 38/43] NFSD: COMMIT operations must not return NFS?ERR_INVAL Since, well, forever, the Linux NFS server's nfsd_commit() function has returned nfserr_inval when the passed-in byte range arguments were non-sensical. However, according to RFC 1813 section 3.3.21, NFSv3 COMMIT requests are permitted to return only the following non-zero status codes: NFS3ERR_IO NFS3ERR_STALE NFS3ERR_BADHANDLE NFS3ERR_SERVERFAULT NFS3ERR_INVAL is not included in that list. Likewise, NFS4ERR_INVAL is not listed in the COMMIT row of Table 6 in RFC 8881. RFC 7530 does permit COMMIT to return NFS4ERR_INVAL, but does not specify when it can or should be used. Instead of dropping or failing a COMMIT request in a byte range that is not supported, turn it into a valid request by treating one or both arguments as zero. Offset zero means start-of-file, count zero means until-end-of-file, so we only ever extend the commit range. NFS servers are always allowed to commit more and sooner than requested. The range check is no longer bounded by NFS_OFFSET_MAX, but rather by the value that is returned in the maxfilesize field of the NFSv3 FSINFO procedure or the NFSv4 maxfilesize file attribute. Note that this change results in a new pynfs failure: CMT4 st_commit.testCommitOverflow : RUNNING CMT4 st_commit.testCommitOverflow : FAILURE COMMIT with offset + count overflow should return NFS4ERR_INVAL, instead got NFS4_OK IMO the test is not correct as written: RFC 8881 does not allow the COMMIT operation to return NFS4ERR_INVAL. Reported-by: Dan Aloni Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever Reviewed-by: Bruce Fields --- fs/nfsd/nfs3proc.c | 6 ------ fs/nfsd/vfs.c | 53 +++++++++++++++++++++++++++++++--------------- fs/nfsd/vfs.h | 4 ++-- 3 files changed, 38 insertions(+), 25 deletions(-) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index aca38ed1526e..52ad1972cc33 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -663,15 +663,9 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) argp->count, (unsigned long long) argp->offset); - if (argp->offset > NFS_OFFSET_MAX) { - resp->status = nfserr_inval; - goto out; - } - fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count, resp->verf); -out: return rpc_success; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 0cccceb105e7..91600e71be19 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1114,42 +1114,61 @@ out: } #ifdef CONFIG_NFSD_V3 -/* - * Commit all pending writes to stable storage. +/** + * nfsd_commit - Commit pending writes to stable storage + * @rqstp: RPC request being processed + * @fhp: NFS filehandle + * @offset: raw offset from beginning of file + * @count: raw count of bytes to sync + * @verf: filled in with the server's current write verifier * - * Note: we only guarantee that data that lies within the range specified - * by the 'offset' and 'count' parameters will be synced. + * Note: we guarantee that data that lies within the range specified + * by the 'offset' and 'count' parameters will be synced. The server + * is permitted to sync data that lies outside this range at the + * same time. * * Unfortunately we cannot lock the file to make sure we return full WCC * data to the client, as locking happens lower down in the filesystem. + * + * Return values: + * An nfsstat value in network byte order. */ __be32 -nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, unsigned long count, __be32 *verf) +nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset, + u32 count, __be32 *verf) { + u64 maxbytes; + loff_t start, end; struct nfsd_net *nn; struct nfsd_file *nf; - loff_t end = LLONG_MAX; - __be32 err = nfserr_inval; - - if (offset < 0) - goto out; - if (count != 0) { - end = offset + (loff_t)count - 1; - if (end < offset) - goto out; - } + __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf); if (err) goto out; + + /* + * Convert the client-provided (offset, count) range to a + * (start, end) range. If the client-provided range falls + * outside the maximum file size of the underlying FS, + * clamp the sync range appropriately. + */ + start = 0; + end = LLONG_MAX; + maxbytes = (u64)fhp->fh_dentry->d_sb->s_maxbytes; + if (offset < maxbytes) { + start = offset; + if (count && (offset + count - 1 < maxbytes)) + end = offset + count - 1; + } + nn = net_generic(nf->nf_net, nfsd_net_id); if (EX_ISSYNC(fhp->fh_export)) { errseq_t since = READ_ONCE(nf->nf_file->f_wb_err); int err2; - err2 = vfs_fsync_range(nf->nf_file, offset, end, 0); + err2 = vfs_fsync_range(nf->nf_file, start, end, 0); switch (err2) { case 0: nfsd_copy_write_verifier(verf, nn); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 9f56dcb22ff7..2c43d10e3cab 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -74,8 +74,8 @@ __be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, struct svc_fh *res, int createmode, u32 *verifier, bool *truncp, bool *created); -__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, - loff_t, unsigned long, __be32 *verf); +__be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp, + u64 offset, u32 count, __be32 *verf); #endif /* CONFIG_NFSD_V3 */ #ifdef CONFIG_NFSD_V4 __be32 nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, From 6a4d333d540041d244b2fca29b8417bfde20af81 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 4 Feb 2022 17:05:24 -0500 Subject: [PATCH 39/43] NFSD: Fix offset type in I/O trace points NFSv3 and NFSv4 use u64 offset values on the wire. Record these values verbatim without the implicit type case to loff_t. Signed-off-by: Chuck Lever --- fs/nfsd/trace.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c4cf56327843..5889db66409d 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -306,14 +306,14 @@ TRACE_EVENT(nfsd_export_update, DECLARE_EVENT_CLASS(nfsd_io_class, TP_PROTO(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, - unsigned long len), + u64 offset, + u32 len), TP_ARGS(rqstp, fhp, offset, len), TP_STRUCT__entry( __field(u32, xid) __field(u32, fh_hash) - __field(loff_t, offset) - __field(unsigned long, len) + __field(u64, offset) + __field(u32, len) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); @@ -321,7 +321,7 @@ DECLARE_EVENT_CLASS(nfsd_io_class, __entry->offset = offset; __entry->len = len; ), - TP_printk("xid=0x%08x fh_hash=0x%08x offset=%lld len=%lu", + TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu len=%u", __entry->xid, __entry->fh_hash, __entry->offset, __entry->len) ) @@ -330,8 +330,8 @@ DECLARE_EVENT_CLASS(nfsd_io_class, DEFINE_EVENT(nfsd_io_class, nfsd_##name, \ TP_PROTO(struct svc_rqst *rqstp, \ struct svc_fh *fhp, \ - loff_t offset, \ - unsigned long len), \ + u64 offset, \ + u32 len), \ TP_ARGS(rqstp, fhp, offset, len)) DEFINE_NFSD_IO_EVENT(read_start); From c306d737691ef84305d4ed0d302c63db2932f0bb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 25 Jan 2022 15:57:45 -0500 Subject: [PATCH 40/43] NFSD: Deprecate NFS_OFFSET_MAX NFS_OFFSET_MAX was introduced way back in Linux v2.3.y before there was a kernel-wide OFFSET_MAX value. As a clean up, replace the last few uses of it with its generic equivalent, and get rid of it. Signed-off-by: Chuck Lever --- fs/nfsd/nfs3xdr.c | 2 +- fs/nfsd/nfs4xdr.c | 2 +- include/linux/nfs.h | 8 -------- 3 files changed, 2 insertions(+), 10 deletions(-) diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 2e47a07029f1..0293b8d65f10 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1060,7 +1060,7 @@ svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name, return false; /* cookie */ resp->cookie_offset = dirlist->len; - if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0) + if (xdr_stream_encode_u64(xdr, OFFSET_MAX) < 0) return false; return true; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index f5e3430bb6ff..714a3a3bd50c 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3495,7 +3495,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, p = xdr_reserve_space(xdr, 3*4 + namlen); if (!p) goto fail; - p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */ + p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */ p = xdr_encode_array(p, name, namlen); /* name length & name */ nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 0dc7ad38a0da..b06375e88e58 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -36,14 +36,6 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc memcpy(target->data, source->data, source->size); } - -/* - * This is really a general kernel constant, but since nothing like - * this is defined in the kernel headers, I have to do it here. - */ -#define NFS_OFFSET_MAX ((__s64)((~(__u64)0) >> 1)) - - enum nfs3_stable_how { NFS_UNSTABLE = 0, NFS_DATA_SYNC = 1, From b42bc9a3c5115c3102a4923776bbeed3b191f2db Mon Sep 17 00:00:00 2001 From: Domenico Andreoli Date: Wed, 9 Feb 2022 08:49:20 +0100 Subject: [PATCH 41/43] Fix regression due to "fs: move binfmt_misc sysctl to its own file" Commit 3ba442d5331f ("fs: move binfmt_misc sysctl to its own file") did not go unnoticed, binfmt-support stopped to work on my Debian system since v5.17-rc2 (did not check with -rc1). The existance of the /proc/sys/fs/binfmt_misc is a precondition for attempting to mount the binfmt_misc fs, which in turn triggers the autoload of the binfmt_misc module. Without it, no module is loaded and no binfmt is available at boot. Building as built-in or manually loading the module and mounting the fs works fine, it's therefore only a matter of interaction with user-space. I could try to improve the Debian systemd configuration but I can't say anything about the other distributions. This patch restores a working system right after boot. Fixes: 3ba442d5331f ("fs: move binfmt_misc sysctl to its own file") Signed-off-by: Domenico Andreoli Cc: Andrew Morton Cc: Luis Chamberlain Reviewed-by: Tong Zhang Signed-off-by: Linus Torvalds --- fs/binfmt_misc.c | 6 +----- fs/file_table.c | 2 ++ 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index c07f35719ee3..e1eae7ea823a 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -817,20 +817,16 @@ static struct file_system_type bm_fs_type = { }; MODULE_ALIAS_FS("binfmt_misc"); -static struct ctl_table_header *binfmt_misc_header; - static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); - binfmt_misc_header = register_sysctl_mount_point("fs/binfmt_misc"); - return 0; + return err; } static void __exit exit_misc_binfmt(void) { - unregister_sysctl_table(binfmt_misc_header); unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } diff --git a/fs/file_table.c b/fs/file_table.c index 57edef16dce4..4969021fa676 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -119,6 +119,8 @@ static struct ctl_table fs_stat_sysctls[] = { static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); + if (IS_ENABLED(CONFIG_BINFMT_MISC)) + register_sysctl_mount_point("fs/binfmt_misc"); return 0; } fs_initcall(init_fs_stat_sysctls); From 7a82f89de92aac5a244d3735b2bd162c1147620c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 9 Feb 2022 14:49:38 -0500 Subject: [PATCH 42/43] audit: don't deref the syscall args when checking the openat2 open_how::flags As reported by Jeff, dereferencing the openat2 syscall argument in audit_match_perm() to obtain the open_how::flags can result in an oops/page-fault. This patch fixes this by using the open_how struct that we store in the audit_context with audit_openat2_how(). Independent of this patch, Richard Guy Briggs posted a similar patch to the audit mailing list roughly 40 minutes after this patch was posted. Cc: stable@vger.kernel.org Fixes: 1c30e3af8a79 ("audit: add support for the openat2 syscall") Reported-by: Jeff Mahoney Signed-off-by: Paul Moore --- kernel/auditsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index fce5d43a933f..a83928cbdcb7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -185,7 +185,7 @@ static int audit_match_perm(struct audit_context *ctx, int mask) case AUDITSC_EXECVE: return mask & AUDIT_PERM_EXEC; case AUDITSC_OPENAT2: - return mask & ACC_MODE((u32)((struct open_how *)ctx->argv[2])->flags); + return mask & ACC_MODE((u32)ctx->openat2.flags); default: return 0; } From 9aa422ad326634b76309e8ff342c246800621216 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Sat, 5 Feb 2022 14:11:18 -0500 Subject: [PATCH 43/43] tipc: improve size validations for received domain records The function tipc_mon_rcv() allows a node to receive and process domain_record structs from peer nodes to track their views of the network topology. This patch verifies that the number of members in a received domain record does not exceed the limit defined by MAX_MON_DOMAIN, something that may otherwise lead to a stack overflow. tipc_mon_rcv() is called from the function tipc_link_proto_rcv(), where we are reading a 32 bit message data length field into a uint16. To avert any risk of bit overflow, we add an extra sanity check for this in that function. We cannot see that happen with the current code, but future designers being unaware of this risk, may introduce it by allowing delivery of very large (> 64k) sk buffers from the bearer layer. This potential problem was identified by Eric Dumazet. This fixes CVE-2022-0435 Reported-by: Samuel Page Reported-by: Eric Dumazet Fixes: 35c55c9877f8 ("tipc: add neighbor monitoring framework") Signed-off-by: Jon Maloy Reviewed-by: Xin Long Reviewed-by: Samuel Page Reviewed-by: Eric Dumazet Signed-off-by: Linus Torvalds --- net/tipc/link.c | 9 +++++++-- net/tipc/monitor.c | 2 ++ 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index 8d9e09f48f4c..1e14d7f8f28f 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2200,7 +2200,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u16 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2214,6 +2214,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, void *data; trace_tipc_proto_rcv(skb, false, l->name); + + if (dlen > U16_MAX) + goto exit; + if (tipc_link_is_blocked(l) || !xmitq) goto exit; @@ -2309,7 +2313,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, /* Receive Gap ACK blocks from peer if any */ glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); - + if(glen > dlen) + break; tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr, &l->mon_state, l->bearer_id); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 407619697292..2f4d23238a7e 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -496,6 +496,8 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, state->probing = false; /* Sanity check received domain record */ + if (new_member_cnt > MAX_MON_DOMAIN) + return; if (dlen < dom_rec_len(arrv_dom, 0)) return; if (dlen != dom_rec_len(arrv_dom, new_member_cnt))