From 9fad9d560af5c654bb38e0b07ee54a4e9acdc5cd Mon Sep 17 00:00:00 2001 From: Justin Stitt Date: Wed, 8 May 2024 17:22:51 +0000 Subject: scsi: sr: Fix unintentional arithmetic wraparound Running syzkaller with the newly reintroduced signed integer overflow sanitizer produces this report: [ 65.194362] ------------[ cut here ]------------ [ 65.197752] UBSAN: signed-integer-overflow in ../drivers/scsi/sr_ioctl.c:436:9 [ 65.203607] -2147483648 * 177 cannot be represented in type 'int' [ 65.207911] CPU: 2 PID: 10416 Comm: syz-executor.1 Not tainted 6.8.0-rc2-00035-gb3ef86b5a957 #1 [ 65.213585] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 65.219923] Call Trace: [ 65.221556] [ 65.223029] dump_stack_lvl+0x93/0xd0 [ 65.225573] handle_overflow+0x171/0x1b0 [ 65.228219] sr_select_speed+0xeb/0xf0 [ 65.230786] ? __pm_runtime_resume+0xe6/0x130 [ 65.233606] sr_block_ioctl+0x15d/0x1d0 ... Historically, the signed integer overflow sanitizer did not work in the kernel due to its interaction with `-fwrapv` but this has since been changed [1] in the newest version of Clang. It was re-enabled in the kernel with Commit 557f8c582a9b ("ubsan: Reintroduce signed overflow sanitizer"). Firstly, let's change the type of "speed" to unsigned long as sr_select_speed()'s only caller passes in an unsigned long anyways. $ git grep '\.select_speed' | drivers/scsi/sr.c: .select_speed = sr_select_speed, ... | static int cdrom_ioctl_select_speed(struct cdrom_device_info *cdi, | unsigned long arg) | { | ... | return cdi->ops->select_speed(cdi, arg); | } Next, let's add an extra check to make sure we don't exceed 0xffff/177 (350) since 0xffff is the max speed. This has two benefits: 1) we deal with integer overflow before it happens and 2) we properly respect the max speed of 0xffff. There are some "magic" numbers here but I did not want to change more than what was necessary. Link: https://github.com/llvm/llvm-project/pull/82432 [1] Closes: https://github.com/KSPP/linux/issues/357 Cc: linux-hardening@vger.kernel.org Signed-off-by: Justin Stitt Link: https://lore.kernel.org/r/20240508-b4-b4-sio-sr_select_speed-v2-1-00b68f724290@google.com Reviewed-by: Kees Cook Signed-off-by: Martin K. Petersen --- include/linux/cdrom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 98c6fd0b39b6..fdfb61ccf55a 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,7 @@ struct cdrom_device_ops { unsigned int clearing, int slot); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); - int (*select_speed) (struct cdrom_device_info *, int); + int (*select_speed) (struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, -- cgit From e61bcf42d290e73025bab38e0e55a5586c2d8ad5 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 15 Apr 2024 22:50:27 +0200 Subject: i2c: Remove I2C_CLASS_SPD Remove this class after all users have been gone. Signed-off-by: Heiner Kallweit Signed-off-by: Andi Shyti --- include/linux/i2c.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5e6cd43a6dbd..9709537370ee 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -852,7 +852,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) /* i2c adapter classes (bitmask) */ #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ -#define I2C_CLASS_SPD (1<<7) /* Memory modules */ /* Warn users that the adapter doesn't support classes anymore */ #define I2C_CLASS_DEPRECATED (1<<8) -- cgit From 79c137454815ba5554caa8eeb4ad5c94e96e45ce Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Tue, 21 May 2024 19:49:38 +0800 Subject: filemap: add helper mapping_max_folio_size() Add mapping_max_folio_size() to get the maximum folio size for this pagecache mapping. Fixes: 5d8edfb900d5 ("iomap: Copy larger chunks from userspace") Cc: stable@vger.kernel.org Reviewed-by: Darrick J. Wong Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20240521114939.2541461-1-xu.yang_2@nxp.com Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Christian Brauner --- include/linux/pagemap.h | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3d69589c00a4..ee633712bba0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -346,6 +346,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define MAX_PAGECACHE_ORDER 8 +#endif + /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The file. @@ -372,6 +385,14 @@ static inline bool mapping_large_folio_support(struct address_space *mapping) test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(struct address_space *mapping) +{ + if (mapping_large_folio_support(mapping)) + return PAGE_SIZE << MAX_PAGECACHE_ORDER; + return PAGE_SIZE; +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -530,19 +551,6 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else -- cgit From 1b9f86c6d53245dab087f1b2c05727b5982142ff Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 22 May 2024 22:26:54 +0300 Subject: net/mlx5: Fix MTMP register capability offset in MCAM register The MTMP register (0x900a) capability offset is off-by-one, move it to the right place. Fixes: 1f507e80c700 ("net/mlx5: Expose NIC temperature via hardware monitoring kernel API") Signed-off-by: Gal Pressman Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f468763478ae..5df52e15f7d6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10308,9 +10308,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mfrl[0x1]; u8 regs_39_to_32[0x8]; - u8 regs_31_to_10[0x16]; + u8 regs_31_to_11[0x15]; u8 mtmp[0x1]; - u8 regs_8_to_0[0x9]; + u8 regs_9_to_0[0xa]; }; struct mlx5_ifc_mcam_access_reg_bits1 { -- cgit From 3998d184267dfcff858aaa84d3de17429253629d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 24 May 2024 18:36:17 +0200 Subject: netkit: Fix pkt_type override upon netkit pass verdict When running Cilium connectivity test suite with netkit in L2 mode, we found that compared to tcx a few tests were failing which pushed traffic into an L7 proxy sitting in host namespace. The problem in particular is around the invocation of eth_type_trans() in netkit. In case of tcx, this is run before the tcx ingress is triggered inside host namespace and thus if the BPF program uses the bpf_skb_change_type() helper the newly set type is retained. However, in case of netkit, the late eth_type_trans() invocation overrides the earlier decision from the BPF program which eventually leads to the test failure. Instead of eth_type_trans(), split out the relevant parts, meaning, reset of mac header and call to eth_skb_pkt_type() before the BPF program is run in order to have the same behavior as with tcx, and refactor a small helper called eth_skb_pull_mac() which is run in case it's passed up the stack where the mac header must be pulled. With this all connectivity tests pass. Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device") Signed-off-by: Daniel Borkmann Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20240524163619.26001-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- drivers/net/netkit.c | 4 +++- include/linux/etherdevice.h | 8 ++++++++ net/ethernet/eth.c | 4 +--- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 272894053e2c..16789cd446e9 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet) skb_scrub_packet(skb, xnet); skb->priority = 0; nf_skip_egress(skb, true); + skb_reset_mac_header(skb); } static struct netkit *netkit_priv(const struct net_device *dev) @@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + eth_skb_pkt_type(skb, peer); skb->dev = peer; entry = rcu_dereference(nk->active); if (entry) @@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case NETKIT_NEXT: case NETKIT_PASS: - skb->protocol = eth_type_trans(skb, skb->dev); + eth_skb_pull_mac(skb); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { dev_sw_netstats_tx_add(dev, 1, len); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad1ffa4ccb9..0ed47d00549b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 049c3adeb850..4e3651101b86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - + eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* -- cgit From f89ea63f1c65d3e93b255f14f9d9e05df87955fa Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 24 May 2024 15:26:11 +0100 Subject: netfs, 9p: Fix race between umount and async request completion There's a problem in 9p's interaction with netfslib whereby a crash occurs because the 9p_fid structs get forcibly destroyed during client teardown (without paying attention to their refcounts) before netfslib has finished with them. However, it's not a simple case of deferring the clunking that p9_fid_put() does as that requires the p9_client record to still be present. The problem is that netfslib has to unlock pages and clear the IN_PROGRESS flag before destroying the objects involved - including the fid - and, in any case, nothing checks to see if writeback completed barring looking at the page flags. Fix this by keeping a count of outstanding I/O requests (of any type) and waiting for it to quiesce during inode eviction. Reported-by: syzbot+df038d463cca332e8414@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000005be0aa061846f8d6@google.com/ Reported-by: syzbot+d7c7a495a5e466c031b6@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/000000000000b86c5e06130da9c6@google.com/ Reported-by: syzbot+1527696d41a634cc1819@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/000000000000041f960618206d7e@google.com/ Signed-off-by: David Howells Link: https://lore.kernel.org/r/755891.1716560771@warthog.procyon.org.uk Tested-by: syzbot+d7c7a495a5e466c031b6@syzkaller.appspotmail.com Reviewed-by: Dominique Martinet cc: Eric Van Hensbergen cc: Latchesar Ionkov cc: Christian Schoenebeck cc: Jeff Layton cc: Steve French cc: Hillf Danton cc: v9fs@lists.linux.dev cc: linux-afs@lists.infradead.org cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Reported-and-tested-by: syzbot+d7c7a495a5e466c031b6@syzkaller.appspotmail.com Signed-off-by: Christian Brauner --- fs/9p/vfs_inode.c | 1 + fs/afs/inode.c | 1 + fs/netfs/objects.c | 5 +++++ fs/smb/client/cifsfs.c | 1 + include/linux/netfs.h | 18 ++++++++++++++++++ 5 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 7a3308d77606..fd72fc38c8f5 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -348,6 +348,7 @@ void v9fs_evict_inode(struct inode *inode) __le32 __maybe_unused version; if (!is_bad_inode(inode)) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); version = cpu_to_le32(v9inode->qid.version); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 94fc049aff58..15bb7989c387 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -648,6 +648,7 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); afs_set_cache_aux(vnode, &aux); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index c90d482b1650..f4a642727479 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -72,6 +72,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, } } + atomic_inc(&ctx->io_count); trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new); netfs_proc_add_rreq(rreq); netfs_stat(&netfs_n_rh_rreq); @@ -124,6 +125,7 @@ static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + struct netfs_inode *ictx = netfs_inode(rreq->inode); unsigned int i; trace_netfs_rreq(rreq, netfs_rreq_trace_free); @@ -142,6 +144,9 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } + + if (atomic_dec_and_test(&ictx->io_count)) + wake_up_var(&ictx->io_count); call_rcu(&rreq->rcu, netfs_free_request_rcu); } diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index ec5b639f421a..14810ffd15c8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -431,6 +431,7 @@ cifs_free_inode(struct inode *inode) static void cifs_evict_inode(struct inode *inode) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); if (inode->i_state & I_PINNING_NETFS_WB) cifs_fscache_unuse_inode_cookie(inode, true); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ca56a4428043..3b22ce0d064c 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -68,6 +68,7 @@ struct netfs_inode { loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ + atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ @@ -472,6 +473,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, ctx->remote_i_size = i_size_read(&ctx->inode); ctx->zero_point = LLONG_MAX; ctx->flags = 0; + atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif @@ -515,4 +517,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) #endif } +/** + * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete + * @ctx: The netfs inode to wait on + * + * Wait for outstanding I/O requests of any type to complete. This is intended + * to be called from inode eviction routines. This makes sure that any + * resources held by those requests are cleaned up before we let the inode get + * cleaned up. + */ +static inline void netfs_wait_for_outstanding_io(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0); +} + #endif /* _LINUX_NETFS_H */ -- cgit From 80e4e17ac9e05adba3f1f0e1793398086e6d4007 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 May 2024 15:16:06 -0700 Subject: block: remove blk_queue_max_integrity_segments This is unused now that all the atomic queue limit conversions are merged. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20240521221606.393040-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-integrity.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index e253e7bd0d17..7428cb43952d 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -66,12 +66,6 @@ blk_integrity_queue_supports_integrity(struct request_queue *q) return q->integrity.profile; } -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ - q->limits.max_integrity_segments = segs; -} - static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -151,10 +145,6 @@ static inline void blk_integrity_register(struct gendisk *d, static inline void blk_integrity_unregister(struct gendisk *d) { } -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ -} static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { -- cgit From f3d7ba9e1bc0c9080834f263d4887bd9c9ea491f Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Mon, 27 May 2024 13:56:27 +0300 Subject: tpm: Open code tpm_buf_parameters() With only single call site, this makes no sense (slipped out of the radar during the review). Open code and document the action directly to the site, to make it more readable. Fixes: 1b6d7f9eb150 ("tpm: add session encryption protection to tpm2_get_random()") Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-buf.c | 26 -------------------------- drivers/char/tpm/tpm2-cmd.c | 10 +++++++++- include/linux/tpm.h | 2 -- 3 files changed, 9 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c index 647c6ca92ac3..cad0048bcc3c 100644 --- a/drivers/char/tpm/tpm-buf.c +++ b/drivers/char/tpm/tpm-buf.c @@ -223,30 +223,4 @@ u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset) } EXPORT_SYMBOL_GPL(tpm_buf_read_u32); -static u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -/** - * tpm_buf_parameters - return the TPM response parameters area of the tpm_buf - * @buf: tpm_buf to use - * - * Where the parameters are located depends on the tag of a TPM - * command (it's immediately after the header for TPM_ST_NO_SESSIONS - * or 4 bytes after for TPM_ST_SESSIONS). Evaluate this and return a - * pointer to the first byte of the parameters area. - * - * @return: pointer to parameters area - */ -u8 *tpm_buf_parameters(struct tpm_buf *buf) -{ - int offset = TPM_HEADER_SIZE; - - if (tpm_buf_tag(buf) == TPM2_ST_SESSIONS) - offset += 4; - return &buf->data[offset]; -} diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 0cdf892ec2a7..1e856259219e 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -281,6 +281,7 @@ struct tpm2_get_random_out { int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) { struct tpm2_get_random_out *out; + struct tpm_header *head; struct tpm_buf buf; u32 recd; u32 num_bytes = max; @@ -288,6 +289,7 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) int total = 0; int retries = 5; u8 *dest_ptr = dest; + off_t offset; if (!num_bytes || max > TPM_MAX_RNG_DATA) return -EINVAL; @@ -320,7 +322,13 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) goto out; } - out = (struct tpm2_get_random_out *)tpm_buf_parameters(&buf); + head = (struct tpm_header *)buf.data; + offset = TPM_HEADER_SIZE; + /* Skip the parameter size field: */ + if (be16_to_cpu(head->tag) == TPM2_ST_SESSIONS) + offset += 4; + + out = (struct tpm2_get_random_out *)&buf.data[offset]; recd = min_t(u32, be16_to_cpu(out->size), num_bytes); if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + diff --git a/include/linux/tpm.h b/include/linux/tpm.h index c17e4efbb2e5..b3217200df28 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -437,8 +437,6 @@ u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); -u8 *tpm_buf_parameters(struct tpm_buf *buf); - /* * Check if TPM device is in the firmware upgrade mode. */ -- cgit From f09fc6cee0dcfc38148ee6b6dd04f93e353d22f2 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Tue, 28 May 2024 12:52:21 +0300 Subject: tpm: Rename TPM2_OA_TMPL to TPM2_OA_NULL_KEY and make it local Rename and document TPM2_OA_TMPL, as originally requested in the patch set review, but left unaddressed without any appropriate reasoning. The new name is TPM2_OA_NULL_KEY, has a documentation and is local only to tpm2-sessions.c. Link: https://lore.kernel.org/linux-integrity/ddbeb8111f48a8ddb0b8fca248dff6cc9d7079b2.camel@HansenPartnership.com/ Link: https://lore.kernel.org/linux-integrity/CZCKTWU6ZCC9.2UTEQPEVICYHL@suppilovahvero/ Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm2-sessions.c | 21 +++++++++++++++++++-- include/linux/tpm.h | 15 --------------- 2 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index ea8860661876..907ac9956a78 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -80,6 +80,9 @@ /* maximum number of names the TPM must remember for authorization */ #define AUTH_MAX_NAMES 3 +#define AES_KEY_BYTES AES_KEYSIZE_128 +#define AES_KEY_BITS (AES_KEY_BYTES*8) + static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, u32 *handle, u8 *name); @@ -954,6 +957,20 @@ int tpm2_start_auth_session(struct tpm_chip *chip) } EXPORT_SYMBOL(tpm2_start_auth_session); +/* + * A mask containing the object attributes for the kernel held null primary key + * used in HMAC encryption. For more information on specific attributes look up + * to "8.3 TPMA_OBJECT (Object Attributes)". + */ +#define TPM2_OA_NULL_KEY ( \ + TPM2_OA_NO_DA | \ + TPM2_OA_FIXED_TPM | \ + TPM2_OA_FIXED_PARENT | \ + TPM2_OA_SENSITIVE_DATA_ORIGIN | \ + TPM2_OA_USER_WITH_AUTH | \ + TPM2_OA_DECRYPT | \ + TPM2_OA_RESTRICTED) + /** * tpm2_parse_create_primary() - parse the data returned from TPM_CC_CREATE_PRIMARY * @@ -1018,7 +1035,7 @@ static int tpm2_parse_create_primary(struct tpm_chip *chip, struct tpm_buf *buf, val = tpm_buf_read_u32(buf, &offset_t); /* object properties */ - if (val != TPM2_OA_TMPL) + if (val != TPM2_OA_NULL_KEY) return -EINVAL; /* auth policy (empty) */ @@ -1178,7 +1195,7 @@ static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, tpm_buf_append_u16(&template, TPM_ALG_SHA256); /* object properties */ - tpm_buf_append_u32(&template, TPM2_OA_TMPL); + tpm_buf_append_u32(&template, TPM2_OA_NULL_KEY); /* sauth policy (empty) */ tpm_buf_append_u16(&template, 0); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index b3217200df28..21a67dc9efe8 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -394,21 +394,6 @@ enum tpm2_object_attributes { TPM2_OA_SIGN = BIT(18), }; -/* - * definitions for the canonical template. These are mandated - * by the TCG key template documents - */ - -#define AES_KEY_BYTES AES_KEYSIZE_128 -#define AES_KEY_BITS (AES_KEY_BYTES*8) -#define TPM2_OA_TMPL (TPM2_OA_NO_DA | \ - TPM2_OA_FIXED_TPM | \ - TPM2_OA_FIXED_PARENT | \ - TPM2_OA_SENSITIVE_DATA_ORIGIN | \ - TPM2_OA_USER_WITH_AUTH | \ - TPM2_OA_DECRYPT | \ - TPM2_OA_RESTRICTED) - enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), -- cgit From c7a5096781732e0f9784551309484f3e103f6750 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 28 May 2024 13:25:02 +0300 Subject: PNP: Make dev_is_pnp() to be a function and export it for modules Since we have a dev_is_pnp() macro that utilises the address of the pnp_bus_type variable, the users, which can be compiled as modules, will fail to build. Convert the macro to be a function and export it to the modules to prevent build breakage. Reported-by: Woody Suwalski Closes: https://lore.kernel.org/r/cc8a93b2-2504-9754-e26c-5d5c3bd1265c@gmail.com Fixes: 2a49b45cd0e7 ("PNP: Add dev_is_pnp() macro") Signed-off-by: Andy Shevchenko Reviewed-by: Christoph Hellwig Signed-off-by: Rafael J. Wysocki --- drivers/pnp/driver.c | 6 ++++++ include/linux/pnp.h | 4 ++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c index 0a5d0d8befa8..3483e52e3a81 100644 --- a/drivers/pnp/driver.c +++ b/drivers/pnp/driver.c @@ -266,6 +266,12 @@ const struct bus_type pnp_bus_type = { .dev_groups = pnp_dev_groups, }; +bool dev_is_pnp(const struct device *dev) +{ + return dev->bus == &pnp_bus_type; +} +EXPORT_SYMBOL_GPL(dev_is_pnp); + int pnp_register_driver(struct pnp_driver *drv) { drv->driver.name = drv->name; diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 82561242cda4..a8def1cea32c 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -469,7 +469,7 @@ int compare_pnp_id(struct pnp_id *pos, const char *id); int pnp_register_driver(struct pnp_driver *drv); void pnp_unregister_driver(struct pnp_driver *drv); -#define dev_is_pnp(d) ((d)->bus == &pnp_bus_type) +bool dev_is_pnp(const struct device *dev); #else @@ -502,7 +502,7 @@ static inline int compare_pnp_id(struct pnp_id *pos, const char *id) { return -E static inline int pnp_register_driver(struct pnp_driver *drv) { return -ENODEV; } static inline void pnp_unregister_driver(struct pnp_driver *drv) { } -#define dev_is_pnp(d) false +static inline bool dev_is_pnp(const struct device *dev) { return false; } #endif /* CONFIG_PNP */ -- cgit From edcde848c01eb071a91d479a6b3101d9cf48e905 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 28 May 2024 13:25:03 +0300 Subject: PNP: Hide pnp_bus_type from the non-PNP code The pnp_bus_type is defined only when CONFIG_PNP=y, while being not guarded by ifdeffery in the header. Moreover, it's not used outside of the PNP code. Move it to the internal header to make sure no-one will try to (ab)use it. Signed-off-by: Andy Shevchenko Reviewed-by: Christoph Hellwig Signed-off-by: Rafael J. Wysocki --- drivers/pnp/base.h | 1 + include/linux/pnp.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pnp/base.h b/drivers/pnp/base.h index e74a0f6a3157..4e80273dfb1e 100644 --- a/drivers/pnp/base.h +++ b/drivers/pnp/base.h @@ -6,6 +6,7 @@ extern struct mutex pnp_lock; extern const struct attribute_group *pnp_dev_groups[]; +extern const struct bus_type pnp_bus_type; int pnp_register_protocol(struct pnp_protocol *protocol); void pnp_unregister_protocol(struct pnp_protocol *protocol); diff --git a/include/linux/pnp.h b/include/linux/pnp.h index a8def1cea32c..7f2ff95d2deb 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -435,8 +435,6 @@ struct pnp_protocol { #define protocol_for_each_dev(protocol, dev) \ list_for_each_entry(dev, &(protocol)->devices, protocol_list) -extern const struct bus_type pnp_bus_type; - #if defined(CONFIG_PNP) /* device management */ -- cgit From 779b8a14afde110dd3502566be907289eba72447 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 May 2024 14:09:23 +0200 Subject: cpufreq: amd-pstate: remove global header file When extra warnings are enabled, gcc points out a global variable definition in a header: In file included from drivers/cpufreq/amd-pstate-ut.c:29: include/linux/amd-pstate.h:123:27: error: 'amd_pstate_mode_string' defined but not used [-Werror=unused-const-variable=] 123 | static const char * const amd_pstate_mode_string[] = { | ^~~~~~~~~~~~~~~~~~~~~~ This header is only included from two files in the same directory, and one of them uses only a single definition from it, so clean it up by moving most of the contents into the driver that uses them, and making shared bits a local header file. Fixes: 36c5014e5460 ("cpufreq: amd-pstate: optimize driver working mode selection in amd_pstate_param()") Signed-off-by: Arnd Bergmann Acked-by: Mario Limonciello Signed-off-by: Rafael J. Wysocki --- MAINTAINERS | 1 - drivers/cpufreq/amd-pstate-ut.c | 3 +- drivers/cpufreq/amd-pstate.c | 34 +++++++++- drivers/cpufreq/amd-pstate.h | 104 ++++++++++++++++++++++++++++++ include/linux/amd-pstate.h | 137 ---------------------------------------- 5 files changed, 139 insertions(+), 140 deletions(-) create mode 100644 drivers/cpufreq/amd-pstate.h delete mode 100644 include/linux/amd-pstate.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index d6c90161c7bf..fc31870379f8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1107,7 +1107,6 @@ L: linux-pm@vger.kernel.org S: Supported F: Documentation/admin-guide/pm/amd-pstate.rst F: drivers/cpufreq/amd-pstate* -F: include/linux/amd-pstate.h F: tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py AMD PTDMA DRIVER diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index f04ae67dda37..fc275d41d51e 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -26,10 +26,11 @@ #include #include #include -#include #include +#include "amd-pstate.h" + /* * Abbreviations: * amd_pstate_ut: used as a shortform for AMD P-State unit test. diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 1b7e82a0ad2e..91993647e09e 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -36,7 +36,6 @@ #include #include #include -#include #include #include @@ -46,6 +45,8 @@ #include #include #include + +#include "amd-pstate.h" #include "amd-pstate-trace.h" #define AMD_PSTATE_TRANSITION_LATENCY 20000 @@ -53,6 +54,37 @@ #define CPPC_HIGHEST_PERF_PERFORMANCE 196 #define CPPC_HIGHEST_PERF_DEFAULT 166 +#define AMD_CPPC_EPP_PERFORMANCE 0x00 +#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 +#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF +#define AMD_CPPC_EPP_POWERSAVE 0xFF + +/* + * enum amd_pstate_mode - driver working mode of amd pstate + */ +enum amd_pstate_mode { + AMD_PSTATE_UNDEFINED = 0, + AMD_PSTATE_DISABLE, + AMD_PSTATE_PASSIVE, + AMD_PSTATE_ACTIVE, + AMD_PSTATE_GUIDED, + AMD_PSTATE_MAX, +}; + +static const char * const amd_pstate_mode_string[] = { + [AMD_PSTATE_UNDEFINED] = "undefined", + [AMD_PSTATE_DISABLE] = "disable", + [AMD_PSTATE_PASSIVE] = "passive", + [AMD_PSTATE_ACTIVE] = "active", + [AMD_PSTATE_GUIDED] = "guided", + NULL, +}; + +struct quirk_entry { + u32 nominal_freq; + u32 lowest_freq; +}; + /* * TODO: We need more time to fine tune processors with shared memory solution * with community together. diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h new file mode 100644 index 000000000000..e6a28e7f4dbf --- /dev/null +++ b/drivers/cpufreq/amd-pstate.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * + * Author: Meng Li + */ + +#ifndef _LINUX_AMD_PSTATE_H +#define _LINUX_AMD_PSTATE_H + +#include + +/********************************************************************* + * AMD P-state INTERFACE * + *********************************************************************/ +/** + * struct amd_aperf_mperf + * @aperf: actual performance frequency clock count + * @mperf: maximum performance frequency clock count + * @tsc: time stamp counter + */ +struct amd_aperf_mperf { + u64 aperf; + u64 mperf; + u64 tsc; +}; + +/** + * struct amd_cpudata - private CPU data for AMD P-State + * @cpu: CPU number + * @req: constraint request to apply + * @cppc_req_cached: cached performance request hints + * @highest_perf: the maximum performance an individual processor may reach, + * assuming ideal conditions + * For platforms that do not support the preferred core feature, the + * highest_pef may be configured with 166 or 255, to avoid max frequency + * calculated wrongly. we take the fixed value as the highest_perf. + * @nominal_perf: the maximum sustained performance level of the processor, + * assuming ideal operating conditions + * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power + * savings are achieved + * @lowest_perf: the absolute lowest performance level of the processor + * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher + * priority. + * @min_limit_perf: Cached value of the performance corresponding to policy->min + * @max_limit_perf: Cached value of the performance corresponding to policy->max + * @min_limit_freq: Cached value of policy->min (in khz) + * @max_limit_freq: Cached value of policy->max (in khz) + * @max_freq: the frequency (in khz) that mapped to highest_perf + * @min_freq: the frequency (in khz) that mapped to lowest_perf + * @nominal_freq: the frequency (in khz) that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency (in khz) that mapped to lowest_nonlinear_perf + * @cur: Difference of Aperf/Mperf/tsc count between last and current sample + * @prev: Last Aperf/Mperf/tsc count value read from register + * @freq: current cpu frequency value (in khz) + * @boost_supported: check whether the Processor or SBIOS supports boost mode + * @hw_prefcore: check whether HW supports preferred core featue. + * Only when hw_prefcore and early prefcore param are true, + * AMD P-State driver supports preferred core featue. + * @epp_policy: Last saved policy used to set energy-performance preference + * @epp_cached: Cached CPPC energy-performance preference value + * @policy: Cpufreq policy value + * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value + * + * The amd_cpudata is key private data for each CPU thread in AMD P-State, and + * represents all the attributes and goals that AMD P-State requests at runtime. + */ +struct amd_cpudata { + int cpu; + + struct freq_qos_request req[2]; + u64 cppc_req_cached; + + u32 highest_perf; + u32 nominal_perf; + u32 lowest_nonlinear_perf; + u32 lowest_perf; + u32 prefcore_ranking; + u32 min_limit_perf; + u32 max_limit_perf; + u32 min_limit_freq; + u32 max_limit_freq; + + u32 max_freq; + u32 min_freq; + u32 nominal_freq; + u32 lowest_nonlinear_freq; + + struct amd_aperf_mperf cur; + struct amd_aperf_mperf prev; + + u64 freq; + bool boost_supported; + bool hw_prefcore; + + /* EPP feature related attributes*/ + s16 epp_policy; + s16 epp_cached; + u32 policy; + u64 cppc_cap1_cached; + bool suspended; +}; + +#endif /* _LINUX_AMD_PSTATE_H */ diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h deleted file mode 100644 index d58fc022ec46..000000000000 --- a/include/linux/amd-pstate.h +++ /dev/null @@ -1,137 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * linux/include/linux/amd-pstate.h - * - * Copyright (C) 2022 Advanced Micro Devices, Inc. - * - * Author: Meng Li - */ - -#ifndef _LINUX_AMD_PSTATE_H -#define _LINUX_AMD_PSTATE_H - -#include - -#define AMD_CPPC_EPP_PERFORMANCE 0x00 -#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 -#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF -#define AMD_CPPC_EPP_POWERSAVE 0xFF - -/********************************************************************* - * AMD P-state INTERFACE * - *********************************************************************/ -/** - * struct amd_aperf_mperf - * @aperf: actual performance frequency clock count - * @mperf: maximum performance frequency clock count - * @tsc: time stamp counter - */ -struct amd_aperf_mperf { - u64 aperf; - u64 mperf; - u64 tsc; -}; - -/** - * struct amd_cpudata - private CPU data for AMD P-State - * @cpu: CPU number - * @req: constraint request to apply - * @cppc_req_cached: cached performance request hints - * @highest_perf: the maximum performance an individual processor may reach, - * assuming ideal conditions - * For platforms that do not support the preferred core feature, the - * highest_pef may be configured with 166 or 255, to avoid max frequency - * calculated wrongly. we take the fixed value as the highest_perf. - * @nominal_perf: the maximum sustained performance level of the processor, - * assuming ideal operating conditions - * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power - * savings are achieved - * @lowest_perf: the absolute lowest performance level of the processor - * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher - * priority. - * @min_limit_perf: Cached value of the performance corresponding to policy->min - * @max_limit_perf: Cached value of the performance corresponding to policy->max - * @min_limit_freq: Cached value of policy->min (in khz) - * @max_limit_freq: Cached value of policy->max (in khz) - * @max_freq: the frequency (in khz) that mapped to highest_perf - * @min_freq: the frequency (in khz) that mapped to lowest_perf - * @nominal_freq: the frequency (in khz) that mapped to nominal_perf - * @lowest_nonlinear_freq: the frequency (in khz) that mapped to lowest_nonlinear_perf - * @cur: Difference of Aperf/Mperf/tsc count between last and current sample - * @prev: Last Aperf/Mperf/tsc count value read from register - * @freq: current cpu frequency value (in khz) - * @boost_supported: check whether the Processor or SBIOS supports boost mode - * @hw_prefcore: check whether HW supports preferred core featue. - * Only when hw_prefcore and early prefcore param are true, - * AMD P-State driver supports preferred core featue. - * @epp_policy: Last saved policy used to set energy-performance preference - * @epp_cached: Cached CPPC energy-performance preference value - * @policy: Cpufreq policy value - * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value - * - * The amd_cpudata is key private data for each CPU thread in AMD P-State, and - * represents all the attributes and goals that AMD P-State requests at runtime. - */ -struct amd_cpudata { - int cpu; - - struct freq_qos_request req[2]; - u64 cppc_req_cached; - - u32 highest_perf; - u32 nominal_perf; - u32 lowest_nonlinear_perf; - u32 lowest_perf; - u32 prefcore_ranking; - u32 min_limit_perf; - u32 max_limit_perf; - u32 min_limit_freq; - u32 max_limit_freq; - - u32 max_freq; - u32 min_freq; - u32 nominal_freq; - u32 lowest_nonlinear_freq; - - struct amd_aperf_mperf cur; - struct amd_aperf_mperf prev; - - u64 freq; - bool boost_supported; - bool hw_prefcore; - - /* EPP feature related attributes*/ - s16 epp_policy; - s16 epp_cached; - u32 policy; - u64 cppc_cap1_cached; - bool suspended; -}; - -/* - * enum amd_pstate_mode - driver working mode of amd pstate - */ -enum amd_pstate_mode { - AMD_PSTATE_UNDEFINED = 0, - AMD_PSTATE_DISABLE, - AMD_PSTATE_PASSIVE, - AMD_PSTATE_ACTIVE, - AMD_PSTATE_GUIDED, - AMD_PSTATE_MAX, -}; - -static const char * const amd_pstate_mode_string[] = { - [AMD_PSTATE_UNDEFINED] = "undefined", - [AMD_PSTATE_DISABLE] = "disable", - [AMD_PSTATE_PASSIVE] = "passive", - [AMD_PSTATE_ACTIVE] = "active", - [AMD_PSTATE_GUIDED] = "guided", - NULL, -}; - -struct quirk_entry { - u32 nominal_freq; - u32 lowest_freq; -}; - -#endif /* _LINUX_AMD_PSTATE_H */ -- cgit From 29459c3eaa5c6261fbe0dea7bdeb9b48d35d862a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 30 May 2024 14:40:34 +0900 Subject: block: Fix zone write plugging handling of devices with a runt zone A zoned device may have a last sequential write required zone that is smaller than other zones. However, all tests to check if a zone write plug write offset exceeds the zone capacity use the same capacity value stored in the gendisk zone_capacity field. This is incorrect for a zoned device with a last runt (smaller) zone. Add the new field last_zone_capacity to struct gendisk to store the capacity of the last zone of the device. blk_revalidate_seq_zone() and blk_revalidate_conv_zone() are both modified to get this value when disk_zone_is_last() returns true. Similarly to zone_capacity, the value is first stored using the last_zone_capacity field of struct blk_revalidate_zone_args. Once zone revalidation of all zones is done, this is used to set the gendisk last_zone_capacity field. The checks to determine if a zone is full or if a sector offset in a zone exceeds the zone capacity in disk_should_remove_zone_wplug(), disk_zone_wplug_abort_unaligned(), blk_zone_write_plug_init_request(), and blk_zone_wplug_prepare_bio() are modified to use the new helper functions disk_zone_is_full() and disk_zone_wplug_is_full(). disk_zone_is_full() uses the zone index to determine if the zone being tested is the last one of the disk and uses the either the disk zone_capacity or last_zone_capacity accordingly. Fixes: dd291d77cc90 ("block: Introduce zone write plugging") Signed-off-by: Damien Le Moal Reviewed-by: Bart Van Assche Reviewed-by: Niklas Cassel Link: https://lore.kernel.org/r/20240530054035.491497-4-dlemoal@kernel.org Signed-off-by: Jens Axboe --- block/blk-zoned.c | 35 +++++++++++++++++++++++++++-------- include/linux/blkdev.h | 1 + 2 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 402a50a1ac4d..52abebf56027 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -455,6 +455,20 @@ static bool disk_zone_is_last(struct gendisk *disk, struct blk_zone *zone) return zone->start + zone->len >= get_capacity(disk); } +static bool disk_zone_is_full(struct gendisk *disk, + unsigned int zno, unsigned int offset_in_zone) +{ + if (zno < disk->nr_zones - 1) + return offset_in_zone >= disk->zone_capacity; + return offset_in_zone >= disk->last_zone_capacity; +} + +static bool disk_zone_wplug_is_full(struct gendisk *disk, + struct blk_zone_wplug *zwplug) +{ + return disk_zone_is_full(disk, zwplug->zone_no, zwplug->wp_offset); +} + static bool disk_insert_zone_wplug(struct gendisk *disk, struct blk_zone_wplug *zwplug) { @@ -548,7 +562,7 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, return false; /* We can remove zone write plugs for zones that are empty or full. */ - return !zwplug->wp_offset || zwplug->wp_offset >= disk->zone_capacity; + return !zwplug->wp_offset || disk_zone_wplug_is_full(disk, zwplug); } static void disk_remove_zone_wplug(struct gendisk *disk, @@ -669,13 +683,12 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) static void disk_zone_wplug_abort_unaligned(struct gendisk *disk, struct blk_zone_wplug *zwplug) { - unsigned int zone_capacity = disk->zone_capacity; unsigned int wp_offset = zwplug->wp_offset; struct bio_list bl = BIO_EMPTY_LIST; struct bio *bio; while ((bio = bio_list_pop(&zwplug->bio_list))) { - if (wp_offset >= zone_capacity || + if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) || (bio_op(bio) != REQ_OP_ZONE_APPEND && bio_offset_from_zone_start(bio) != wp_offset)) { blk_zone_wplug_bio_io_error(zwplug, bio); @@ -914,7 +927,6 @@ void blk_zone_write_plug_init_request(struct request *req) sector_t req_back_sector = blk_rq_pos(req) + blk_rq_sectors(req); struct request_queue *q = req->q; struct gendisk *disk = q->disk; - unsigned int zone_capacity = disk->zone_capacity; struct blk_zone_wplug *zwplug = disk_get_zone_wplug(disk, blk_rq_pos(req)); unsigned long flags; @@ -938,7 +950,7 @@ void blk_zone_write_plug_init_request(struct request *req) * into the back of the request. */ spin_lock_irqsave(&zwplug->lock, flags); - while (zwplug->wp_offset < zone_capacity) { + while (!disk_zone_wplug_is_full(disk, zwplug)) { bio = bio_list_peek(&zwplug->bio_list); if (!bio) break; @@ -984,7 +996,7 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, * We know such BIO will fail, and that would potentially overflow our * write pointer offset beyond the end of the zone. */ - if (zwplug->wp_offset >= disk->zone_capacity) + if (disk_zone_wplug_is_full(disk, zwplug)) goto err; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { @@ -1561,6 +1573,7 @@ void disk_free_zone_resources(struct gendisk *disk) kfree(disk->conv_zones_bitmap); disk->conv_zones_bitmap = NULL; disk->zone_capacity = 0; + disk->last_zone_capacity = 0; disk->nr_zones = 0; } @@ -1605,6 +1618,7 @@ struct blk_revalidate_zone_args { unsigned long *conv_zones_bitmap; unsigned int nr_zones; unsigned int zone_capacity; + unsigned int last_zone_capacity; sector_t sector; }; @@ -1622,6 +1636,7 @@ static int disk_update_zone_resources(struct gendisk *disk, disk->nr_zones = args->nr_zones; disk->zone_capacity = args->zone_capacity; + disk->last_zone_capacity = args->last_zone_capacity; swap(disk->conv_zones_bitmap, args->conv_zones_bitmap); if (disk->conv_zones_bitmap) nr_conv_zones = bitmap_weight(disk->conv_zones_bitmap, @@ -1673,6 +1688,9 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx, return -ENODEV; } + if (disk_zone_is_last(disk, zone)) + args->last_zone_capacity = zone->capacity; + if (!disk_need_zone_resources(disk)) return 0; @@ -1703,8 +1721,9 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx, */ if (!args->zone_capacity) args->zone_capacity = zone->capacity; - if (!disk_zone_is_last(disk, zone) && - zone->capacity != args->zone_capacity) { + if (disk_zone_is_last(disk, zone)) { + args->last_zone_capacity = zone->capacity; + } else if (zone->capacity != args->zone_capacity) { pr_warn("%s: Invalid variable zone capacity\n", disk->disk_name); return -ENODEV; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aefdda9f4ec7..24c36929920b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -186,6 +186,7 @@ struct gendisk { */ unsigned int nr_zones; unsigned int zone_capacity; + unsigned int last_zone_capacity; unsigned long *conv_zones_bitmap; unsigned int zone_wplugs_hash_bits; spinlock_t zone_wplugs_lock; -- cgit From 89e8a2366e3bce584b6c01549d5019c5cda1205e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 28 May 2024 12:25:28 +0800 Subject: iommu: Return right value in iommu_sva_bind_device() iommu_sva_bind_device() should return either a sva bond handle or an ERR_PTR value in error cases. Existing drivers (idxd and uacce) only check the return value with IS_ERR(). This could potentially lead to a kernel NULL pointer dereference issue if the function returns NULL instead of an error pointer. In reality, this doesn't cause any problems because iommu_sva_bind_device() only returns NULL when the kernel is not configured with CONFIG_IOMMU_SVA. In this case, iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) will return an error, and the device drivers won't call iommu_sva_bind_device() at all. Fixes: 26b25a2b98e4 ("iommu: Bind process address spaces to devices") Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Vasant Hegde Link: https://lore.kernel.org/r/20240528042528.71396-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7bc8dff7cf6d..17b3f36ad843 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1533,7 +1533,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_sva_unbind_device(struct iommu_sva *handle) -- cgit From c9d52fb313d3719d69a040f4ca78a3e2e95fba21 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 30 May 2024 18:04:24 -0700 Subject: PCI: Revert the cfg_access_lock lockdep mechanism While the experiment did reveal that there are additional places that are missing the lock during secondary bus reset, one of the places that needs to take cfg_access_lock (pci_bus_lock()) is not prepared for lockdep annotation. Specifically, pci_bus_lock() takes pci_dev_lock() recursively and is currently dependent on the fact that the device_lock() is marked lockdep_set_novalidate_class(&dev->mutex). Otherwise, without that annotation, pci_bus_lock() would need to use something like a new pci_dev_lock_nested() helper, a scheme to track a PCI device's depth in the topology, and a hope that the depth of a PCI tree never exceeds the max value for a lockdep subclass. The alternative to ripping out the lockdep coverage would be to deploy a dynamic lock key for every PCI device. Unfortunately, there is evidence that increasing the number of keys that lockdep needs to track to be per-PCI-device is prohibitively expensive for something like the cfg_access_lock. The main motivation for adding the annotation in the first place was to catch unlocked secondary bus resets, not necessarily catch lock ordering problems between cfg_access_lock and other locks. Solve that narrower problem with follow-on patches, and just due to targeted revert for now. Link: https://lore.kernel.org/r/171711746402.1628941.14575335981264103013.stgit@dwillia2-xfh.jf.intel.com Fixes: 7e89efc6e9e4 ("PCI: Lock upstream bridge for pci_reset_function()") Reported-by: Imre Deak Closes: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_134186v1/shard-dg2-1/igt@device_reset@unbind-reset-rebind.html Signed-off-by: Dan Williams Signed-off-by: Bjorn Helgaas Tested-by: Hans de Goede Tested-by: Kalle Valo Reviewed-by: Dave Jiang Cc: Jani Saarinen --- drivers/pci/access.c | 4 ---- drivers/pci/pci.c | 1 - drivers/pci/probe.c | 3 --- include/linux/lockdep.h | 5 ----- include/linux/pci.h | 2 -- 5 files changed, 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 30f031de9cfe..b123da16b63b 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -289,8 +289,6 @@ void pci_cfg_access_lock(struct pci_dev *dev) { might_sleep(); - lock_map_acquire(&dev->cfg_access_lock); - raw_spin_lock_irq(&pci_lock); if (dev->block_cfg_access) pci_wait_cfg(dev); @@ -345,8 +343,6 @@ void pci_cfg_access_unlock(struct pci_dev *dev) raw_spin_unlock_irqrestore(&pci_lock, flags); wake_up_all(&pci_cfg_wait); - - lock_map_release(&dev->cfg_access_lock); } EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 59e0949fb079..35fb1f17a589 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4883,7 +4883,6 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) { - lock_map_assert_held(&dev->cfg_access_lock); pcibios_reset_secondary_bus(dev); return pci_bridge_wait_for_secondary_bus(dev, "bus reset"); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 8e696e547565..5fbabb4e3425 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2546,9 +2546,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.dma_mask = &dev->dma_mask; dev->dev.dma_parms = &dev->dma_parms; dev->dev.coherent_dma_mask = 0xffffffffull; - lockdep_register_key(&dev->cfg_access_key); - lockdep_init_map(&dev->cfg_access_lock, dev_name(&dev->dev), - &dev->cfg_access_key, 0); dma_set_max_seg_size(&dev->dev, 65536); dma_set_seg_boundary(&dev->dev, 0xffffffff); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 5e51b0de4c4b..08b0d1d9d78b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -297,9 +297,6 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); .wait_type_inner = _wait_type, \ .lock_type = LD_LOCK_WAIT_OVERRIDE, } -#define lock_map_assert_held(l) \ - lockdep_assert(lock_is_held(l) != LOCK_STATE_NOT_HELD) - #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -391,8 +388,6 @@ extern int lockdep_is_held(const void *); #define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ struct lockdep_map __maybe_unused _name = {} -#define lock_map_assert_held(l) do { (void)(l); } while (0) - #endif /* !LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING diff --git a/include/linux/pci.h b/include/linux/pci.h index fb004fd4e889..cafc5ab1cbcb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -413,8 +413,6 @@ struct pci_dev { struct resource driver_exclusive_resource; /* driver exclusive resource ranges */ bool match_driver; /* Skip attaching driver */ - struct lock_class_key cfg_access_key; - struct lockdep_map cfg_access_lock; unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int io_window:1; /* Bridge has I/O window */ -- cgit From f92a59f6d12e31ead999fee9585471b95a8ae8a3 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Wed, 15 May 2024 13:37:10 +0000 Subject: locking/atomic: scripts: fix ${atomic}_sub_and_test() kerneldoc For ${atomic}_sub_and_test() the @i parameter is the value to subtract, not add. Fix the typo in the kerneldoc template and generate the headers with this update. Fixes: ad8110706f38 ("locking/atomic: scripts: generate kerneldoc comments") Suggested-by: Mark Rutland Signed-off-by: Carlos Llamas Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20240515133844.3502360-1-cmllamas@google.com --- include/linux/atomic/atomic-arch-fallback.h | 6 +++--- include/linux/atomic/atomic-instrumented.h | 8 ++++---- include/linux/atomic/atomic-long.h | 4 ++-- scripts/atomic/kerneldoc/sub_and_test | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 956bcba5dbf2..2f9d36b72bd8 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2242,7 +2242,7 @@ raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4368,7 +4368,7 @@ raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4690,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 +// b565db590afeeff0d7c9485ccbca5bb6e155749f diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index debd487fe971..9409a6ddf3e0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1349,7 +1349,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -2927,7 +2927,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4505,7 +4505,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// ce5b65e0f1f8a276268b667194581d24bed219d4 +// 8829b337928e9508259079d32581775ececd415b diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 3ef844b3ab8a..f86b29d90877 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1535,7 +1535,7 @@ raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -1809,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a +// eadf183c3600b8b92b91839dd3be6bcc560c752d diff --git a/scripts/atomic/kerneldoc/sub_and_test b/scripts/atomic/kerneldoc/sub_and_test index d3760f7749d4..96615e50836b 100644 --- a/scripts/atomic/kerneldoc/sub_and_test +++ b/scripts/atomic/kerneldoc/sub_and_test @@ -1,7 +1,7 @@ cat < Date: Thu, 23 May 2024 10:36:39 +0800 Subject: mm: drop the 'anon_' prefix for swap-out mTHP counters The mTHP swap related counters: 'anon_swpout' and 'anon_swpout_fallback' are confusing with an 'anon_' prefix, since the shmem can swap out non-anonymous pages. So drop the 'anon_' prefix to keep consistent with the old swap counter names. This is needed in 6.10-rcX to avoid having an inconsistent ABI out in the field. Link: https://lkml.kernel.org/r/7a8989c13299920d7589007a30065c3e2c19f0e0.1716431702.git.baolin.wang@linux.alibaba.com Fixes: d0f048ac39f6 ("mm: add per-order mTHP anon_swpout and anon_swpout_fallback counters") Fixes: 42248b9d34ea ("mm: add docs for per-order mTHP counters and transhuge_page ABI") Signed-off-by: Baolin Wang Suggested-by: "Huang, Ying" Acked-by: Barry Song Cc: David Hildenbrand Cc: Lance Yang Cc: Matthew Wilcox (Oracle) Cc: Ryan Roberts Cc: Zi Yan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/transhuge.rst | 4 ++-- include/linux/huge_mm.h | 4 ++-- mm/huge_memory.c | 8 ++++---- mm/page_io.c | 2 +- mm/vmscan.c | 2 +- 5 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 076443cc10a6..d414d3f5592a 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -467,11 +467,11 @@ anon_fault_fallback_charge instead falls back to using huge pages with lower orders or small pages even though the allocation was successful. -anon_swpout +swpout is incremented every time a huge page is swapped out in one piece without splitting. -anon_swpout_fallback +swpout_fallback is incremented if a huge page has to be split before swapout. Usually because failed to allocate some continuous swap space for the huge page. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index c8d3ec116e29..8c72d3786583 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -269,8 +269,8 @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, - MTHP_STAT_ANON_SWPOUT, - MTHP_STAT_ANON_SWPOUT_FALLBACK, + MTHP_STAT_SWPOUT, + MTHP_STAT_SWPOUT_FALLBACK, __MTHP_STAT_COUNT }; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 317de2afd371..89932fd0f62e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -558,15 +558,15 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); -DEFINE_MTHP_STAT_ATTR(anon_swpout, MTHP_STAT_ANON_SWPOUT); -DEFINE_MTHP_STAT_ATTR(anon_swpout_fallback, MTHP_STAT_ANON_SWPOUT_FALLBACK); +DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); +DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); static struct attribute *stats_attrs[] = { &anon_fault_alloc_attr.attr, &anon_fault_fallback_attr.attr, &anon_fault_fallback_charge_attr.attr, - &anon_swpout_attr.attr, - &anon_swpout_fallback_attr.attr, + &swpout_attr.attr, + &swpout_fallback_attr.attr, NULL, }; diff --git a/mm/page_io.c b/mm/page_io.c index 46c603dddf04..0a150c240bf4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -217,7 +217,7 @@ static inline void count_swpout_vm_event(struct folio *folio) count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); } - count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_SWPOUT); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT); #endif count_vm_events(PSWPOUT, folio_nr_pages(folio)); } diff --git a/mm/vmscan.c b/mm/vmscan.c index d55e8d07ffc4..2e34de9cd0d4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1227,7 +1227,7 @@ retry: THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } - count_mthp_stat(order, MTHP_STAT_ANON_SWPOUT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; -- cgit From 94d46bf17916965e918bd2f3d2eec057f7c5578d Mon Sep 17 00:00:00 2001 From: Barry Song Date: Fri, 24 May 2024 08:50:48 +1200 Subject: mm: huge_mm: fix undefined reference to `mthp_stats' for CONFIG_SYSFS=n if CONFIG_SYSFS is not enabled in config, we get the below error, All errors (new ones prefixed by >>): s390-linux-ld: mm/memory.o: in function `count_mthp_stat': >> include/linux/huge_mm.h:285:(.text+0x191c): undefined reference to `mthp_stats' s390-linux-ld: mm/huge_memory.o:(.rodata+0x10): undefined reference to `mthp_stats' vim +285 include/linux/huge_mm.h 279 280 static inline void count_mthp_stat(int order, enum mthp_stat_item item) 281 { 282 if (order <= 0 || order > PMD_ORDER) 283 return; 284 > 285 this_cpu_inc(mthp_stats.stats[order][item]); 286 } 287 Link: https://lkml.kernel.org/r/20240523210045.40444-1-21cnbao@gmail.com Fixes: ec33687c6749 ("mm: add per-order mTHP anon_fault_alloc and anon_fault_fallback counters") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202405231728.tCAogiSI-lkp@intel.com/ Signed-off-by: Barry Song Tested-by: Yujie Liu Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8c72d3786583..2aa986a5cd1b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -278,6 +278,7 @@ struct mthp_stat { unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; }; +#ifdef CONFIG_SYSFS DECLARE_PER_CPU(struct mthp_stat, mthp_stats); static inline void count_mthp_stat(int order, enum mthp_stat_item item) @@ -287,6 +288,11 @@ static inline void count_mthp_stat(int order, enum mthp_stat_item item) this_cpu_inc(mthp_stats.stats[order][item]); } +#else +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ +} +#endif #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ -- cgit From c2dc78b86e0821ecf9a9d0c35dba2618279a5bb6 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Tue, 28 May 2024 13:15:22 +0800 Subject: mm/ksm: fix ksm_zero_pages accounting We normally ksm_zero_pages++ in ksmd when page is merged with zero page, but ksm_zero_pages-- is done from page tables side, where there is no any accessing protection of ksm_zero_pages. So we can read very exceptional value of ksm_zero_pages in rare cases, such as -1, which is very confusing to users. Fix it by changing to use atomic_long_t, and the same case with the mm->ksm_zero_pages. Link: https://lkml.kernel.org/r/20240528-b4-ksm-counters-v3-2-34bb358fdc13@linux.dev Fixes: e2942062e01d ("ksm: count all zero pages placed by KSM") Fixes: 6080d19f0704 ("ksm: add ksm zero pages for each process") Signed-off-by: Chengming Zhou Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Ran Xiaokai Cc: Stefan Roesch Cc: xu xin Cc: Yang Yang Cc: Signed-off-by: Andrew Morton --- fs/proc/base.c | 2 +- include/linux/ksm.h | 17 ++++++++++++++--- include/linux/mm_types.h | 2 +- mm/ksm.c | 11 +++++------ 4 files changed, 21 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index 18550c071d71..72a1acd03675 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3214,7 +3214,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); - seq_printf(m, "ksm_zero_pages %lu\n", mm->ksm_zero_pages); + seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); mmput(mm); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 52c63a9c5a9c..11690dacd986 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -33,16 +33,27 @@ void __ksm_exit(struct mm_struct *mm); */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) -extern unsigned long ksm_zero_pages; +extern atomic_long_t ksm_zero_pages; + +static inline void ksm_map_zero_page(struct mm_struct *mm) +{ + atomic_long_inc(&ksm_zero_pages); + atomic_long_inc(&mm->ksm_zero_pages); +} static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { - ksm_zero_pages--; - mm->ksm_zero_pages--; + atomic_long_dec(&ksm_zero_pages); + atomic_long_dec(&mm->ksm_zero_pages); } } +static inline long mm_ksm_zero_pages(struct mm_struct *mm) +{ + return atomic_long_read(&mm->ksm_zero_pages); +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 24323c7d0bd4..af3a0256fa93 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -985,7 +985,7 @@ struct mm_struct { * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ - unsigned long ksm_zero_pages; + atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { diff --git a/mm/ksm.c b/mm/ksm.c index 9e99cb12d330..34c4820e0d3d 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -296,7 +296,7 @@ static bool ksm_use_zero_pages __read_mostly; static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ -unsigned long ksm_zero_pages; +atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; @@ -1429,8 +1429,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); - ksm_zero_pages++; - mm->ksm_zero_pages++; + ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we @@ -3374,7 +3373,7 @@ static void wait_while_offlining(void) #ifdef CONFIG_PROC_FS long ksm_process_profit(struct mm_struct *mm) { - return (long)(mm->ksm_merging_pages + mm->ksm_zero_pages) * PAGE_SIZE - + return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ @@ -3663,7 +3662,7 @@ KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%ld\n", ksm_zero_pages); + return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); @@ -3672,7 +3671,7 @@ static ssize_t general_profit_show(struct kobject *kobj, { long general_profit; - general_profit = (ksm_pages_sharing + ksm_zero_pages) * PAGE_SIZE - + general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); -- cgit