December 2024 - Linux-stable-mirror

[PATCH v4] tpm: Map the ACPI provided event log

by Jarkko Sakkinen

The following failure was reported: [ 10.693310][ T1] tpm_tis STM0925:00: 2.0 TPM (device-id 0x3, rev-id 0) [ 10.848132][ T1] ------------[ cut here ]------------ [ 10.853559][ T1] WARNING: CPU: 59 PID: 1 at mm/page_alloc.c:4727 __alloc_pages_noprof+0x2ca/0x330 [ 10.862827][ T1] Modules linked in: [ 10.866671][ T1] CPU: 59 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0-lp155.2.g52785e2-default #1 openSUSE Tumbleweed (unreleased) 588cd98293a7c9eba9013378d807364c088c9375 [ 10.882741][ T1] Hardware name: HPE ProLiant DL320 Gen12/ProLiant DL320 Gen12, BIOS 1.20 10/28/2024 [ 10.892170][ T1] RIP: 0010:__alloc_pages_noprof+0x2ca/0x330 [ 10.898103][ T1] Code: 24 08 e9 4a fe ff ff e8 34 36 fa ff e9 88 fe ff ff 83 fe 0a 0f 86 b3 fd ff ff 80 3d 01 e7 ce 01 00 75 09 c6 05 f8 e6 ce 01 01 <0f> 0b 45 31 ff e9 e5 fe ff ff f7 c2 00 00 08 00 75 42 89 d9 80 e1 [ 10.917750][ T1] RSP: 0000:ffffb7cf40077980 EFLAGS: 00010246 [ 10.923777][ T1] RAX: 0000000000000000 RBX: 0000000000040cc0 RCX: 0000000000000000 [ 10.931727][ T1] RDX: 0000000000000000 RSI: 000000000000000c RDI: 0000000000040cc0 Above shows that ACPI pointed a 16 MiB buffer for the log events because RSI maps to the 'order' parameter of __alloc_pages_noprof(). Address the bug by mapping the region when needed instead of copying. --- Cc: stable(a)vger.kernel.org # v2.6.16+ Fixes: 55a82ab3181b ("[PATCH] tpm: add bios measurement log") Reported-by: Andy Liang <andy.liang(a)hpe.com> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219495 Suggested-by: Matthew Garrett <mjg59(a)srcf.ucam.org> Tested-by: Andy Liang <andy.liang(a)hpe.com> Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v4: * Added tested-by from Andy Liang. v3: * Flag mapping code in tpm{1,2}.c with CONFIG_ACPI (nios2 compilation fix). v2: * There was some extra cruft (irrelevant diff), which is now wiped away. * Added missing tags (fixes, stable). --- drivers/char/tpm/eventlog/acpi.c | 28 +++++++--------------- drivers/char/tpm/eventlog/common.c | 25 +++++++++++++------- drivers/char/tpm/eventlog/common.h | 28 ++++++++++++++++++++++ drivers/char/tpm/eventlog/tpm1.c | 30 ++++++++++++++--------- drivers/char/tpm/eventlog/tpm2.c | 38 +++++++++++++++++------------- include/linux/tpm.h | 1 + 6 files changed, 95 insertions(+), 55 deletions(-) diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 69533d0bfb51..2c4f7355b584 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -70,14 +70,11 @@ int tpm_read_log_acpi(struct tpm_chip *chip) acpi_status status; void __iomem *virt; u64 len, start; - struct tpm_bios_log *log; struct acpi_table_tpm2 *tbl; struct acpi_tpm2_phy *tpm2_phy; int format; int ret; - log = &chip->log; - /* Unfortuntely ACPI does not associate the event log with a specific * TPM, like PPI. Thus all ACPI TPMs will read the same log. */ @@ -135,36 +132,27 @@ int tpm_read_log_acpi(struct tpm_chip *chip) return -EIO; } - /* malloc EventLog space */ - log->bios_event_log = devm_kmalloc(&chip->dev, len, GFP_KERNEL); - if (!log->bios_event_log) - return -ENOMEM; - - log->bios_event_log_end = log->bios_event_log + len; - virt = acpi_os_map_iomem(start, len); if (!virt) { dev_warn(&chip->dev, "%s: Failed to map ACPI memory\n", __func__); /* try EFI log next */ - ret = -ENODEV; - goto err; + return -ENODEV; } - memcpy_fromio(log->bios_event_log, virt, len); - - acpi_os_unmap_iomem(virt, len); - - if (chip->flags & TPM_CHIP_FLAG_TPM2 && - !tpm_is_tpm2_log(log->bios_event_log, len)) { + if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_tpm2_log(virt, len)) { + acpi_os_unmap_iomem(virt, len); /* try EFI log next */ ret = -ENODEV; goto err; } + acpi_os_unmap_iomem(virt, len); + chip->flags |= TPM_CHIP_FLAG_ACPI_LOG; + chip->log.bios_event_log = (void *)start; + chip->log.bios_event_log_end = (void *)start + len; return format; err: - devm_kfree(&chip->dev, log->bios_event_log); - log->bios_event_log = NULL; + acpi_os_unmap_iomem(virt, len); return ret; } diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c index 4c0bbba64ee5..44340ca6e2ac 100644 --- a/drivers/char/tpm/eventlog/common.c +++ b/drivers/char/tpm/eventlog/common.c @@ -27,6 +27,7 @@ static int tpm_bios_measurements_open(struct inode *inode, { int err; struct seq_file *seq; + struct tpm_measurements *priv; struct tpm_chip_seqops *chip_seqops; const struct seq_operations *seqops; struct tpm_chip *chip; @@ -42,13 +43,18 @@ static int tpm_bios_measurements_open(struct inode *inode, get_device(&chip->dev); inode_unlock(inode); - /* now register seq file */ + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + priv->chip = chip; + err = seq_open(file, seqops); - if (!err) { - seq = file->private_data; - seq->private = chip; - } else { + if (err) { + kfree(priv); put_device(&chip->dev); + } else { + seq = file->private_data; + seq->private = priv; } return err; @@ -58,11 +64,14 @@ static int tpm_bios_measurements_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - struct tpm_chip *chip = seq->private; + struct tpm_measurements *priv = seq->private; + int ret; - put_device(&chip->dev); + put_device(&priv->chip->dev); + ret = seq_release(inode, file); + kfree(priv); - return seq_release(inode, file); + return ret; } static const struct file_operations tpm_bios_measurements_ops = { diff --git a/drivers/char/tpm/eventlog/common.h b/drivers/char/tpm/eventlog/common.h index 47ff8136ceb5..b98fd6d9a6e9 100644 --- a/drivers/char/tpm/eventlog/common.h +++ b/drivers/char/tpm/eventlog/common.h @@ -1,12 +1,40 @@ #ifndef __TPM_EVENTLOG_COMMON_H__ #define __TPM_EVENTLOG_COMMON_H__ +#include <linux/acpi.h> #include "../tpm.h" extern const struct seq_operations tpm1_ascii_b_measurements_seqops; extern const struct seq_operations tpm1_binary_b_measurements_seqops; extern const struct seq_operations tpm2_binary_b_measurements_seqops; +struct tpm_measurements { + struct tpm_chip *chip; + void *start; + void *end; +}; + +static inline bool tpm_measurements_map(struct tpm_measurements *measurements) +{ + struct tpm_chip *chip = measurements->chip; + struct tpm_bios_log *log = &chip->log; + size_t size; + + size = log->bios_event_log_end - log->bios_event_log; + measurements->start = log->bios_event_log; + +#ifdef CONFIG_ACPI + if (chip->flags & TPM_CHIP_FLAG_ACPI_LOG) + measurements->start = acpi_os_map_iomem((unsigned long)log->bios_event_log, size); +#endif + + if (!measurements->start) + return false; + + measurements->end = measurements->start + size; + return true; +} + #if defined(CONFIG_ACPI) int tpm_read_log_acpi(struct tpm_chip *chip); #else diff --git a/drivers/char/tpm/eventlog/tpm1.c b/drivers/char/tpm/eventlog/tpm1.c index 12ee42a31c71..aef6ee39423a 100644 --- a/drivers/char/tpm/eventlog/tpm1.c +++ b/drivers/char/tpm/eventlog/tpm1.c @@ -70,20 +70,23 @@ static const char* tcpa_pc_event_id_strings[] = { static void *tpm1_bios_measurements_start(struct seq_file *m, loff_t *pos) { loff_t i = 0; - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *addr = log->bios_event_log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; struct tcpa_event *event; u32 converted_event_size; u32 converted_event_type; + void *addr; + + if (!tpm_measurements_map(priv)) + return NULL; + + addr = priv->start; /* read over *pos measurements */ do { event = addr; /* check if current entry is valid */ - if (addr + sizeof(struct tcpa_event) > limit) + if (addr + sizeof(struct tcpa_event) > priv->end) return NULL; converted_event_size = @@ -93,7 +96,7 @@ static void *tpm1_bios_measurements_start(struct seq_file *m, loff_t *pos) if (((converted_event_type == 0) && (converted_event_size == 0)) || ((addr + sizeof(struct tcpa_event) + converted_event_size) - > limit)) + > priv->end)) return NULL; if (i++ == *pos) @@ -109,9 +112,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, loff_t *pos) { struct tcpa_event *event = v; - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; u32 converted_event_size; u32 converted_event_type; @@ -121,7 +122,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, v += sizeof(struct tcpa_event) + converted_event_size; /* now check if current entry is valid */ - if ((v + sizeof(struct tcpa_event)) > limit) + if ((v + sizeof(struct tcpa_event)) > priv->end) return NULL; event = v; @@ -130,7 +131,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, converted_event_type = do_endian_conversion(event->event_type); if (((converted_event_type == 0) && (converted_event_size == 0)) || - ((v + sizeof(struct tcpa_event) + converted_event_size) > limit)) + ((v + sizeof(struct tcpa_event) + converted_event_size) > priv->end)) return NULL; return v; @@ -138,6 +139,13 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, static void tpm1_bios_measurements_stop(struct seq_file *m, void *v) { +#ifdef CONFIG_ACPI + struct tpm_measurements *priv = m->private; + struct tpm_chip *chip = priv->chip; + + if (chip->flags & TPM_CHIP_FLAG_ACPI_LOG) + acpi_os_unmap_iomem(priv->start, priv->end - priv->start); +#endif } static int get_event_name(char *dest, struct tcpa_event *event, diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c index 37a05800980c..6289d8893e46 100644 --- a/drivers/char/tpm/eventlog/tpm2.c +++ b/drivers/char/tpm/eventlog/tpm2.c @@ -41,20 +41,22 @@ static size_t calc_tpm2_event_size(struct tcg_pcr_event2_head *event, static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) { - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *addr = log->bios_event_log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; struct tcg_pcr_event *event_header; struct tcg_pcr_event2_head *event; size_t size; + void *addr; int i; + if (!tpm_measurements_map(priv)) + return NULL; + + addr = priv->start; event_header = addr; size = struct_size(event_header, event, event_header->event_size); if (*pos == 0) { - if (addr + size < limit) { + if (addr + size < priv->end) { if ((event_header->event_type == 0) && (event_header->event_size == 0)) return NULL; @@ -66,7 +68,7 @@ static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) addr += size; event = addr; size = calc_tpm2_event_size(event, event_header); - if ((addr + size >= limit) || (size == 0)) + if ((addr + size >= priv->end) || !size) return NULL; } @@ -74,7 +76,7 @@ static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) event = addr; size = calc_tpm2_event_size(event, event_header); - if ((addr + size >= limit) || (size == 0)) + if ((addr + size >= priv->end) || !size) return NULL; addr += size; } @@ -87,14 +89,12 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v, { struct tcg_pcr_event *event_header; struct tcg_pcr_event2_head *event; - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; size_t event_size; void *marker; (*pos)++; - event_header = log->bios_event_log; + event_header = priv->start; if (v == SEQ_START_TOKEN) { event_size = struct_size(event_header, event, @@ -109,13 +109,13 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v, } marker = marker + event_size; - if (marker >= limit) + if (marker >= priv->end) return NULL; v = marker; event = v; event_size = calc_tpm2_event_size(event, event_header); - if (((v + event_size) >= limit) || (event_size == 0)) + if (((v + event_size) >= priv->end) || !event_size) return NULL; return v; @@ -123,13 +123,19 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v, static void tpm2_bios_measurements_stop(struct seq_file *m, void *v) { +#ifdef CONFIG_ACPI + struct tpm_measurements *priv = m->private; + struct tpm_chip *chip = priv->chip; + + if (chip->flags & TPM_CHIP_FLAG_ACPI_LOG) + acpi_os_unmap_iomem(priv->start, priv->end - priv->start); +#endif } static int tpm2_binary_bios_measurements_show(struct seq_file *m, void *v) { - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - struct tcg_pcr_event *event_header = log->bios_event_log; + struct tpm_measurements *priv = m->private; + struct tcg_pcr_event *event_header = priv->start; struct tcg_pcr_event2_head *event = v; void *temp_ptr; size_t size; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 20a40ade8030..f3d12738b93b 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -348,6 +348,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_SUSPENDED = BIT(8), TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), TPM_CHIP_FLAG_DISABLE = BIT(10), + TPM_CHIP_FLAG_ACPI_LOG = BIT(11), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- 2.47.1

8 months

1
0
0 0

+ mm-damon-core-fix-ignored-quota-goals-and-filters-of-newly-committed-schemes.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/core: fix ignored quota goals and filters of newly committed schemes has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-core-fix-ignored-quota-goals-and-filters-of-newly-committed-schemes.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/core: fix ignored quota goals and filters of newly committed schemes Date: Sun, 22 Dec 2024 15:12:22 -0800 damon_commit_schemes() ignores quota goals and filters of the newly committed schemes. This makes users confused about the behaviors. Correctly handle those inputs. Link: https://lkml.kernel.org/r/20241222231222.85060-3-sj@kernel.org Fixes: 9cb3d0b9dfce ("mm/damon/core: implement DAMON context commit function") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/core.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/mm/damon/core.c~mm-damon-core-fix-ignored-quota-goals-and-filters-of-newly-committed-schemes +++ a/mm/damon/core.c @@ -868,6 +868,11 @@ static int damon_commit_schemes(struct d NUMA_NO_NODE); if (!new_scheme) return -ENOMEM; + err = damos_commit(new_scheme, src_scheme); + if (err) { + damon_destroy_scheme(new_scheme); + return err; + } damon_add_scheme(dst, new_scheme); } return 0; _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-fix-new-damon_target-objects-leaks-on-damon_commit_targets.patch mm-damon-core-fix-ignored-quota-goals-and-filters-of-newly-committed-schemes.patch samples-add-a-skeleton-of-a-sample-damon-module-for-working-set-size-estimation.patch samples-damon-wsse-start-and-stop-damon-as-the-user-requests.patch samples-damon-wsse-implement-working-set-size-estimation-and-logging.patch samples-damon-introduce-a-skeleton-of-a-smaple-damon-module-for-proactive-reclamation.patch samples-damon-prcl-implement-schemes-setup.patch replace-free-hugepage-folios-after-migration-fix-2.patch

8 months

1
0
0 0

+ mm-damon-core-fix-new-damon_target-objects-leaks-on-damon_commit_targets.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/core: fix new damon_target objects leaks on damon_commit_targets() has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-damon-core-fix-new-damon_target-objects-leaks-on-damon_commit_targets.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/core: fix new damon_target objects leaks on damon_commit_targets() Date: Sun, 22 Dec 2024 15:12:21 -0800 Patch series "mm/damon/core: fix memory leaks and ignored inputs from damon_commit_ctx()". Due to two bugs in damon_commit_targets() and damon_commit_schemes(), which are called from damon_commit_ctx(), some user inputs can be ignored, and some mmeory objects can be leaked. Fix those. Note that only DAMON sysfs interface users are affected. Other DAMON core API user modules that more focused more on simple and dedicated production usages, including DAMON_RECLAIM and DAMON_LRU_SORT are not using the buggy function in the way, so not affected. This patch (of 2): When new DAMON targets are added via damon_commit_targets(), the newly created targets are not deallocated when updating the internal data (damon_commit_target()) is failed. Worse yet, even if the setup is successfully done, the new target is not linked to the context. Hence, the new targets are always leaked regardless of the internal data setup failure. Fix the leaks. Link: https://lkml.kernel.org/r/20241222231222.85060-2-sj@kernel.org Fixes: 9cb3d0b9dfce ("mm/damon/core: implement DAMON context commit function") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/mm/damon/core.c~mm-damon-core-fix-new-damon_target-objects-leaks-on-damon_commit_targets +++ a/mm/damon/core.c @@ -961,8 +961,11 @@ static int damon_commit_targets( return -ENOMEM; err = damon_commit_target(new_target, false, src_target, damon_target_has_pid(src)); - if (err) + if (err) { + damon_destroy_target(new_target); return err; + } + damon_add_target(dst, new_target); } return 0; } _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-core-fix-new-damon_target-objects-leaks-on-damon_commit_targets.patch mm-damon-core-fix-ignored-quota-goals-and-filters-of-newly-committed-schemes.patch samples-add-a-skeleton-of-a-sample-damon-module-for-working-set-size-estimation.patch samples-damon-wsse-start-and-stop-damon-as-the-user-requests.patch samples-damon-wsse-implement-working-set-size-estimation-and-logging.patch samples-damon-introduce-a-skeleton-of-a-smaple-damon-module-for-proactive-reclamation.patch samples-damon-prcl-implement-schemes-setup.patch replace-free-hugepage-folios-after-migration-fix-2.patch

8 months

1
0
0 0

[RFC PATCH] NFSD: Encode COMPOUND operation status on page boundaries

by cel＠kernel.org

From: Chuck Lever <chuck.lever(a)oracle.com> J. David reports an odd corruption of a READDIR reply sent to a FreeBSD client. xdr_reserve_space() has to do a special trick when the @nbytes value requests more space than there is in the current page of the XDR buffer. In that case, xdr_reserve_space() returns a pointer to the start of the next page, and then the next call to xdr_reserve_space() invokes __xdr_commit_encode() to copy enough of the data item back into the previous page to make that data item contiguous across the page boundary. But we need to be careful in the case where buffer space is reserved early for a data item that will be inserted into the buffer later. One such caller, nfsd4_encode_operation(), reserves 8 bytes in the encoding buffer for each COMPOUND operation. However, a READDIR result can sometimes encode file names so that there are only 4 bytes left at the end of the current XDR buffer page (though plenty of pages are left to handle the remaining encoding tasks). If a COMPOUND operation follows the READDIR result (say, a GETATTR), then nfsd4_encode_operation() will reserve 8 bytes for the op number (9) and the op status (usually NFS4_OK). In this weird case, xdr_reserve_space() returns a pointer to byte zero of the next buffer page, as it assumes the data item will be copied back into place (in the previous page) on the next call to xdr_reserve_space(). nfsd4_encode_operation() writes the op num into the buffer, then saves the next 4-byte location for the op's status code. The next xdr_reserve_space() call is part of GETATTR encoding, so the op num gets copied back into the previous page, but the saved location for the op status continues to point to the wrong spot in the current XDR buffer page because __xdr_commit_encode() moved that data item. After GETATTR encoding is complete, nfsd4_encode_operation() writes the op status over the first XDR data item in the GETATTR result. The NFS4_OK status code (0) makes it look like there are zero items in the GETATTR's attribute bitmask. The patch description of commit 2825a7f90753 ("nfsd4: allow encoding across page boundaries") [2014] remarks that NFSD "can't handle a new operation starting close to the end of a page." This behavior appears to be one reason for that remark. Break up the reservation of the COMPOUND op num and op status data items into two distinct 4-octet reservations. Thanks to XDR data item alignment restrictions, a 4-octet buffer reservation can never straddle a page boundary. Reported-by: J David <j.david.lists(a)gmail.com> Cc: stable(a)vger.kernel.org Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> --- fs/nfsd/nfs4xdr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 53fac037611c..8780da884197 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -5764,10 +5764,11 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) nfsd4_enc encoder; __be32 *p; - p = xdr_reserve_space(xdr, 8); + if (xdr_stream_encode_u32(xdr, op->opnum) != XDR_UNIT) + goto release; + p = xdr_reserve_space(xdr, XDR_UNIT); if (!p) goto release; - *p++ = cpu_to_be32(op->opnum); post_err_offset = xdr->buf->len; if (op->opnum == OP_ILLEGAL) -- 2.47.0

8 months

3
4
0 0

[PATCHSET v6.2 4/5] xfs: realtime reverse-mapping support

by Darrick J. Wong

Hi all, This is the latest revision of a patchset that adds to XFS kernel support for reverse mapping for the realtime device. This time around I've fixed some of the bitrot that I've noticed over the past few months, and most notably have converted rtrmapbt to use the metadata inode directory feature instead of burning more space in the superblock. At the beginning of the set are patches to implement storing B+tree leaves in an inode root, since the realtime rmapbt is rooted in an inode, unlike the regular rmapbt which is rooted in an AG block. Prior to this, the only btree that could be rooted in the inode fork was the block mapping btree; if all the extent records fit in the inode, format would be switched from 'btree' to 'extents'. The next few patches enhance the reverse mapping routines to handle the parts that are specific to rtgroups -- adding the new btree type, adding a new log intent item type, and wiring up the metadata directory tree entries. Finally, implement GETFSMAP with the rtrmapbt and scrub functionality for the rtrmapbt and rtbitmap and online fsck functionality. If you're going to start using this code, I strongly recommend pulling from my git trees, which are linked below. This has been running on the djcloud for months with no problems. Enjoy! Comments and questions are, as always, welcome. --D kernel git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=re… xfsprogs git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h… fstests git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfstests-dev.git/log/?h… xfsdocs git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-documentation.git/l… --- Commits in this patchset: * xfs: add some rtgroup inode helpers * xfs: prepare rmap btree cursor tracepoints for realtime * xfs: simplify the xfs_rmap_{alloc,free}_extent calling conventions * xfs: introduce realtime rmap btree ondisk definitions * xfs: realtime rmap btree transaction reservations * xfs: add realtime rmap btree operations * xfs: prepare rmap functions to deal with rtrmapbt * xfs: add a realtime flag to the rmap update log redo items * xfs: support recovering rmap intent items targetting realtime extents * xfs: pretty print metadata file types in error messages * xfs: support file data forks containing metadata btrees * xfs: add realtime reverse map inode to metadata directory * xfs: add metadata reservations for realtime rmap btrees * xfs: wire up a new metafile type for the realtime rmap * xfs: wire up rmap map and unmap to the realtime rmapbt * xfs: create routine to allocate and initialize a realtime rmap btree inode * xfs: wire up getfsmap to the realtime reverse mapping btree * xfs: check that the rtrmapbt maxlevels doesn't increase when growing fs * xfs: report realtime rmap btree corruption errors to the health system * xfs: allow queued realtime intents to drain before scrubbing * xfs: scrub the realtime rmapbt * xfs: cross-reference realtime bitmap to realtime rmapbt scrubber * xfs: cross-reference the realtime rmapbt * xfs: scan rt rmap when we're doing an intense rmap check of bmbt mappings * xfs: scrub the metadir path of rt rmap btree files * xfs: walk the rt reverse mapping tree when rebuilding rmap * xfs: online repair of realtime file bmaps * xfs: repair inodes that have realtime extents * xfs: repair rmap btree inodes * xfs: online repair of realtime bitmaps for a realtime group * xfs: support repairing metadata btrees rooted in metadir inodes * xfs: online repair of the realtime rmap btree * xfs: create a shadow rmap btree during realtime rmap repair * xfs: hook live realtime rmap operations during a repair operation * xfs: don't shut down the filesystem for media failures beyond end of log * xfs: react to fsdax failure notifications on the rt device * xfs: enable realtime rmap btree --- fs/xfs/Makefile | 3 fs/xfs/libxfs/xfs_btree.c | 73 +++ fs/xfs/libxfs/xfs_btree.h | 8 fs/xfs/libxfs/xfs_btree_mem.c | 1 fs/xfs/libxfs/xfs_btree_staging.c | 1 fs/xfs/libxfs/xfs_defer.h | 1 fs/xfs/libxfs/xfs_exchmaps.c | 4 fs/xfs/libxfs/xfs_format.h | 28 + fs/xfs/libxfs/xfs_fs.h | 7 fs/xfs/libxfs/xfs_health.h | 4 fs/xfs/libxfs/xfs_inode_buf.c | 32 + fs/xfs/libxfs/xfs_inode_fork.c | 25 + fs/xfs/libxfs/xfs_log_format.h | 6 fs/xfs/libxfs/xfs_log_recover.h | 2 fs/xfs/libxfs/xfs_metafile.c | 18 + fs/xfs/libxfs/xfs_metafile.h | 2 fs/xfs/libxfs/xfs_ondisk.h | 2 fs/xfs/libxfs/xfs_refcount.c | 6 fs/xfs/libxfs/xfs_rmap.c | 171 +++++- fs/xfs/libxfs/xfs_rmap.h | 12 fs/xfs/libxfs/xfs_rtbitmap.c | 2 fs/xfs/libxfs/xfs_rtbitmap.h | 9 fs/xfs/libxfs/xfs_rtgroup.c | 53 +- fs/xfs/libxfs/xfs_rtgroup.h | 49 ++ fs/xfs/libxfs/xfs_rtrmap_btree.c | 1011 +++++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_rtrmap_btree.h | 210 ++++++++ fs/xfs/libxfs/xfs_sb.c | 6 fs/xfs/libxfs/xfs_shared.h | 14 + fs/xfs/libxfs/xfs_trans_resv.c | 12 fs/xfs/libxfs/xfs_trans_space.h | 13 fs/xfs/scrub/alloc_repair.c | 5 fs/xfs/scrub/bmap.c | 108 +++- fs/xfs/scrub/bmap_repair.c | 129 +++++ fs/xfs/scrub/common.c | 160 ++++++ fs/xfs/scrub/common.h | 23 + fs/xfs/scrub/health.c | 1 fs/xfs/scrub/inode.c | 10 fs/xfs/scrub/inode_repair.c | 136 +++++ fs/xfs/scrub/metapath.c | 3 fs/xfs/scrub/newbt.c | 42 ++ fs/xfs/scrub/newbt.h | 1 fs/xfs/scrub/reap.c | 41 ++ fs/xfs/scrub/reap.h | 2 fs/xfs/scrub/repair.c | 191 +++++++ fs/xfs/scrub/repair.h | 17 + fs/xfs/scrub/rgsuper.c | 6 fs/xfs/scrub/rmap_repair.c | 84 +++ fs/xfs/scrub/rtbitmap.c | 75 ++- fs/xfs/scrub/rtbitmap.h | 55 ++ fs/xfs/scrub/rtbitmap_repair.c | 429 +++++++++++++++- fs/xfs/scrub/rtrmap.c | 271 ++++++++++ fs/xfs/scrub/rtrmap_repair.c | 903 +++++++++++++++++++++++++++++++++ fs/xfs/scrub/rtsummary.c | 17 - fs/xfs/scrub/rtsummary_repair.c | 3 fs/xfs/scrub/scrub.c | 11 fs/xfs/scrub/scrub.h | 14 + fs/xfs/scrub/stats.c | 1 fs/xfs/scrub/tempexch.h | 2 fs/xfs/scrub/tempfile.c | 20 - fs/xfs/scrub/trace.c | 1 fs/xfs/scrub/trace.h | 228 ++++++++ fs/xfs/xfs_buf.c | 1 fs/xfs/xfs_buf_item_recover.c | 4 fs/xfs/xfs_drain.c | 20 - fs/xfs/xfs_drain.h | 7 fs/xfs/xfs_fsmap.c | 174 ++++++ fs/xfs/xfs_fsops.c | 11 fs/xfs/xfs_health.c | 1 fs/xfs/xfs_inode.c | 19 + fs/xfs/xfs_inode_item.c | 2 fs/xfs/xfs_inode_item_recover.c | 44 +- fs/xfs/xfs_log_recover.c | 2 fs/xfs/xfs_mount.c | 5 fs/xfs/xfs_mount.h | 9 fs/xfs/xfs_notify_failure.c | 230 +++++--- fs/xfs/xfs_notify_failure.h | 11 fs/xfs/xfs_qm.c | 8 fs/xfs/xfs_rmap_item.c | 216 +++++++- fs/xfs/xfs_rtalloc.c | 82 ++- fs/xfs/xfs_rtalloc.h | 10 fs/xfs/xfs_stats.c | 4 fs/xfs/xfs_stats.h | 2 fs/xfs/xfs_super.c | 6 fs/xfs/xfs_super.h | 1 fs/xfs/xfs_trace.h | 104 ++-- 85 files changed, 5381 insertions(+), 366 deletions(-) create mode 100644 fs/xfs/libxfs/xfs_rtrmap_btree.c create mode 100644 fs/xfs/libxfs/xfs_rtrmap_btree.h create mode 100644 fs/xfs/scrub/rtrmap.c create mode 100644 fs/xfs/scrub/rtrmap_repair.c create mode 100644 fs/xfs/xfs_notify_failure.h

8 months

1
1
0 0

[PATCHSET 1/5] xfs: bug fixes for 6.13

by Darrick J. Wong

Hi all, Bug fixes for 6.13. If you're going to start using this code, I strongly recommend pulling from my git trees, which are linked below. This has been running on the djcloud for months with no problems. Enjoy! Comments and questions are, as always, welcome. --D kernel git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=xf… xfsprogs git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h… --- Commits in this patchset: * xfs: don't over-report free space or inodes in statvfs * xfs: release the dquot buf outside of qli_lock --- fs/xfs/xfs_dquot.c | 12 ++++++++---- fs/xfs/xfs_qm_bhv.c | 27 +++++++++++++++++---------- 2 files changed, 25 insertions(+), 14 deletions(-)

8 months

1
2
0 0

[GIT PULL 5/8] xfsprogs: new code for 6.13

by Darrick J. Wong

Hi Andrey, Please pull this branch with changes for xfsprogs for 6.11-rc1. As usual, I did a test-merge with the main upstream branch as of a few minutes ago, and didn't see any conflicts. Please let me know if you encounter any problems. --D The following changes since commit 513300e9565b0d446ac8e6a3a990444d766c728b: mkfs: add a utility to generate protofiles (2024-12-23 13:05:10 -0800) are available in the Git repository at: https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfsprogs-dev.git tags/xfs-6.13-merge_2024-12-23 for you to fetch changes up to 80b81c84f015ee01fed80c32184cc763ee1a655e: xfs: return from xfs_symlink_verify early on V4 filesystems (2024-12-23 13:05:13 -0800) ---------------------------------------------------------------- xfsprogs: new code for 6.13 [05/23] New code for 6.12. This has been running on the djcloud for months with no problems. Enjoy! Signed-off-by: "Darrick J. Wong" <djwong(a)kernel.org> ---------------------------------------------------------------- Christoph Hellwig (9): xfs: add a xfs_bmap_free_rtblocks helper xfs: move RT bitmap and summary information to the rtgroup xfs: support creating per-RTG files in growfs xfs: refactor xfs_rtbitmap_blockcount xfs: refactor xfs_rtsummary_blockcount xfs: make RT extent numbers relative to the rtgroup xfs: add a helper to prevent bmap merges across rtgroup boundaries xfs: make the RT allocator rtgroup aware xfs: don't call xfs_bmap_same_rtgroup in xfs_bmap_add_extent_hole_delay Darrick J. Wong (40): xfs: create incore realtime group structures xfs: define locking primitives for realtime groups xfs: add a lockdep class key for rtgroup inodes xfs: support caching rtgroup metadata inodes libfrog: add memchr_inv xfs: define the format of rt groups xfs: update realtime super every time we update the primary fs super xfs: export realtime group geometry via XFS_FSOP_GEOM xfs: check that rtblock extents do not break rtsupers or rtgroups xfs: add frextents to the lazysbcounters when rtgroups enabled xfs: record rt group metadata errors in the health system xfs: export the geometry of realtime groups to userspace xfs: add block headers to realtime bitmap and summary blocks xfs: encode the rtbitmap in big endian format xfs: encode the rtsummary in big endian format xfs: grow the realtime section when realtime groups are enabled xfs: support logging EFIs for realtime extents xfs: support error injection when freeing rt extents xfs: use realtime EFI to free extents when rtgroups are enabled xfs: don't merge ioends across RTGs xfs: scrub the realtime group superblock xfs: scrub metadir paths for rtgroup metadata xfs: mask off the rtbitmap and summary inodes when metadir in use xfs: create helpers to deal with rounding xfs_fileoff_t to rtx boundaries xfs: create helpers to deal with rounding xfs_filblks_t to rtx boundaries xfs: make xfs_rtblock_t a segmented address like xfs_fsblock_t xfs: adjust min_block usage in xfs_verify_agbno xfs: move the min and max group block numbers to xfs_group xfs: implement busy extent tracking for rtgroups xfs: use metadir for quota inodes xfs: scrub quota file metapaths xfs: enable metadata directory feature xfs: convert struct typedefs in xfs_ondisk.h xfs: separate space btree structures in xfs_ondisk.h xfs: port ondisk structure checks from xfs/122 to the kernel xfs: return a 64-bit block count from xfs_btree_count_blocks xfs: fix error bailout in xfs_rtginode_create xfs: update btree keys correctly when _insrec splits an inode root block xfs: fix sb_spino_align checks for large fsblock sizes xfs: return from xfs_symlink_verify early on V4 filesystems Dave Chinner (1): xfs: fix sparse inode limits on runt AG Jeff Layton (1): xfs: switch to multigrain timestamps Long Li (1): xfs: remove unknown compat feature check in superblock write validation db/block.c | 2 +- db/block.h | 16 - db/convert.c | 1 - db/faddr.c | 1 - include/libxfs.h | 2 + include/platform_defs.h | 33 +++ include/xfs_mount.h | 30 +- include/xfs_trace.h | 7 + include/xfs_trans.h | 1 + libfrog/util.c | 14 + libfrog/util.h | 4 + libxfs/Makefile | 2 + libxfs/init.c | 35 ++- libxfs/libxfs_api_defs.h | 16 + libxfs/libxfs_io.h | 1 + libxfs/libxfs_priv.h | 34 +-- libxfs/rdwr.c | 17 ++ libxfs/trans.c | 29 ++ libxfs/util.c | 8 +- libxfs/xfs_ag.c | 22 +- libxfs/xfs_ag.h | 16 +- libxfs/xfs_alloc.c | 15 +- libxfs/xfs_alloc.h | 12 +- libxfs/xfs_bmap.c | 124 ++++++-- libxfs/xfs_btree.c | 33 ++- libxfs/xfs_btree.h | 2 +- libxfs/xfs_defer.c | 6 + libxfs/xfs_defer.h | 1 + libxfs/xfs_dquot_buf.c | 190 ++++++++++++ libxfs/xfs_format.h | 80 ++++- libxfs/xfs_fs.h | 32 +- libxfs/xfs_group.h | 33 +++ libxfs/xfs_health.h | 42 +-- libxfs/xfs_ialloc.c | 16 +- libxfs/xfs_ialloc_btree.c | 6 +- libxfs/xfs_log_format.h | 6 +- libxfs/xfs_ondisk.h | 186 +++++++++--- libxfs/xfs_quota_defs.h | 43 +++ libxfs/xfs_rtbitmap.c | 405 +++++++++++++++++--------- libxfs/xfs_rtbitmap.h | 247 ++++++++++------ libxfs/xfs_rtgroup.c | 694 ++++++++++++++++++++++++++++++++++++++++++++ libxfs/xfs_rtgroup.h | 284 ++++++++++++++++++ libxfs/xfs_sb.c | 246 ++++++++++++++-- libxfs/xfs_sb.h | 6 +- libxfs/xfs_shared.h | 4 + libxfs/xfs_symlink_remote.c | 4 +- libxfs/xfs_trans_inode.c | 6 +- libxfs/xfs_trans_resv.c | 2 +- libxfs/xfs_types.c | 35 ++- libxfs/xfs_types.h | 8 +- mkfs/proto.c | 33 ++- mkfs/xfs_mkfs.c | 8 + repair/dinode.c | 4 +- repair/phase6.c | 203 +++++++------ repair/rt.c | 34 +-- repair/rt.h | 4 +- 56 files changed, 2728 insertions(+), 617 deletions(-) create mode 100644 libxfs/xfs_rtgroup.c create mode 100644 libxfs/xfs_rtgroup.h

8 months

1
0
0 0

[PATCHSET 5/8] xfsprogs: new code for 6.13

by Darrick J. Wong

Hi all, New code for 6.12. If you're going to start using this code, I strongly recommend pulling from my git trees, which are linked below. This has been running on the djcloud for months with no problems. Enjoy! Comments and questions are, as always, welcome. --D kernel git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=xf… xfsprogs git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfsprogs-dev.git/log/?h… --- Commits in this patchset: * xfs: create incore realtime group structures * xfs: define locking primitives for realtime groups * xfs: add a lockdep class key for rtgroup inodes * xfs: support caching rtgroup metadata inodes * xfs: add a xfs_bmap_free_rtblocks helper * xfs: move RT bitmap and summary information to the rtgroup * xfs: support creating per-RTG files in growfs * xfs: refactor xfs_rtbitmap_blockcount * xfs: refactor xfs_rtsummary_blockcount * xfs: make RT extent numbers relative to the rtgroup * libfrog: add memchr_inv * xfs: define the format of rt groups * xfs: update realtime super every time we update the primary fs super * xfs: export realtime group geometry via XFS_FSOP_GEOM * xfs: check that rtblock extents do not break rtsupers or rtgroups * xfs: add a helper to prevent bmap merges across rtgroup boundaries * xfs: add frextents to the lazysbcounters when rtgroups enabled * xfs: record rt group metadata errors in the health system * xfs: export the geometry of realtime groups to userspace * xfs: add block headers to realtime bitmap and summary blocks * xfs: encode the rtbitmap in big endian format * xfs: encode the rtsummary in big endian format * xfs: grow the realtime section when realtime groups are enabled * xfs: support logging EFIs for realtime extents * xfs: support error injection when freeing rt extents * xfs: use realtime EFI to free extents when rtgroups are enabled * xfs: don't merge ioends across RTGs * xfs: make the RT allocator rtgroup aware * xfs: scrub the realtime group superblock * xfs: scrub metadir paths for rtgroup metadata * xfs: mask off the rtbitmap and summary inodes when metadir in use * xfs: create helpers to deal with rounding xfs_fileoff_t to rtx boundaries * xfs: create helpers to deal with rounding xfs_filblks_t to rtx boundaries * xfs: make xfs_rtblock_t a segmented address like xfs_fsblock_t * xfs: adjust min_block usage in xfs_verify_agbno * xfs: move the min and max group block numbers to xfs_group * xfs: implement busy extent tracking for rtgroups * xfs: use metadir for quota inodes * xfs: scrub quota file metapaths * xfs: enable metadata directory feature * xfs: convert struct typedefs in xfs_ondisk.h * xfs: separate space btree structures in xfs_ondisk.h * xfs: port ondisk structure checks from xfs/122 to the kernel * xfs: remove unknown compat feature check in superblock write validation * xfs: fix sparse inode limits on runt AG * xfs: switch to multigrain timestamps * xfs: don't call xfs_bmap_same_rtgroup in xfs_bmap_add_extent_hole_delay * xfs: return a 64-bit block count from xfs_btree_count_blocks * xfs: fix error bailout in xfs_rtginode_create * xfs: update btree keys correctly when _insrec splits an inode root block * xfs: fix sb_spino_align checks for large fsblock sizes * xfs: return from xfs_symlink_verify early on V4 filesystems --- db/block.c | 2 db/block.h | 16 - db/convert.c | 1 db/faddr.c | 1 include/libxfs.h | 2 include/platform_defs.h | 33 ++ include/xfs_mount.h | 30 +- include/xfs_trace.h | 7 include/xfs_trans.h | 1 libfrog/util.c | 14 + libfrog/util.h | 4 libxfs/Makefile | 2 libxfs/init.c | 35 ++ libxfs/libxfs_api_defs.h | 16 + libxfs/libxfs_io.h | 1 libxfs/libxfs_priv.h | 34 -- libxfs/rdwr.c | 17 + libxfs/trans.c | 29 ++ libxfs/util.c | 8 libxfs/xfs_ag.c | 22 + libxfs/xfs_ag.h | 16 - libxfs/xfs_alloc.c | 15 + libxfs/xfs_alloc.h | 12 + libxfs/xfs_bmap.c | 124 ++++++-- libxfs/xfs_btree.c | 33 ++ libxfs/xfs_btree.h | 2 libxfs/xfs_defer.c | 6 libxfs/xfs_defer.h | 1 libxfs/xfs_dquot_buf.c | 190 ++++++++++++ libxfs/xfs_format.h | 80 +++++ libxfs/xfs_fs.h | 32 ++ libxfs/xfs_group.h | 33 ++ libxfs/xfs_health.h | 42 ++- libxfs/xfs_ialloc.c | 16 + libxfs/xfs_ialloc_btree.c | 6 libxfs/xfs_log_format.h | 6 libxfs/xfs_ondisk.h | 186 +++++++++--- libxfs/xfs_quota_defs.h | 43 +++ libxfs/xfs_rtbitmap.c | 405 +++++++++++++++++-------- libxfs/xfs_rtbitmap.h | 247 ++++++++++----- libxfs/xfs_rtgroup.c | 694 +++++++++++++++++++++++++++++++++++++++++++ libxfs/xfs_rtgroup.h | 284 ++++++++++++++++++ libxfs/xfs_sb.c | 246 ++++++++++++++- libxfs/xfs_sb.h | 6 libxfs/xfs_shared.h | 4 libxfs/xfs_symlink_remote.c | 4 libxfs/xfs_trans_inode.c | 6 libxfs/xfs_trans_resv.c | 2 libxfs/xfs_types.c | 35 ++ libxfs/xfs_types.h | 8 mkfs/proto.c | 33 +- mkfs/xfs_mkfs.c | 8 repair/dinode.c | 4 repair/phase6.c | 203 ++++++------- repair/rt.c | 34 -- repair/rt.h | 4 56 files changed, 2728 insertions(+), 617 deletions(-) create mode 100644 libxfs/xfs_rtgroup.c create mode 100644 libxfs/xfs_rtgroup.h

8 months

1
6
0 0

[PATCH net] net: ethernet: ti: am65-cpsw: default to round-robin for host port receive

by Siddharth Vadapalli

The Host Port (i.e. CPU facing port) of CPSW receives traffic from Linux via TX DMA Channels which are Hardware Queues consisting of traffic categorized according to their priority. The Host Port is configured to dequeue traffic from these Hardware Queues on the basis of priority i.e. as long as traffic exists on a Hardware Queue of a higher priority, the traffic on Hardware Queues of lower priority isn't dequeued. An alternate operation is also supported wherein traffic can be dequeued by the Host Port in a Round-Robin manner. Until [0], the am65-cpsw driver enabled a single TX DMA Channel, due to which, unless modified by user via "ethtool", all traffic from Linux is transmitted on DMA Channel 0. Therefore, configuring the Host Port for priority based dequeuing or Round-Robin operation is identical since there is a single DMA Channel. Since [0], all 8 TX DMA Channels are enabled by default. Additionally, the default "tc mapping" doesn't take into account the possibility of different traffic profiles which various users might have. This results in traffic starvation at the Host Port due to the priority based dequeuing which has been enabled by default since the inception of the driver. The traffic starvation triggers NETDEV WATCHDOG timeout for all TX DMA Channels that haven't been serviced due to the presence of traffic on the higher priority TX DMA Channels. Fix this by defaulting to Round-Robin dequeuing at the Host Port, which shall ensure that traffic is dequeued from all TX DMA Channels irrespective of the traffic profile. This will address the NETDEV WATCHDOG timeouts. At the same time, users can still switch from Round-Robin to Priority based dequeuing at the Host Port with the help of the "p0-rx-ptype-rrobin" private flag of "ethtool". Users are expected to setup an appropriate "tc mapping" that suits their traffic profile when switching to priority based dequeuing at the Host Port. [0] commit be397ea3473d ("net: ethernet: am65-cpsw: Set default TX channels to maximum") Fixes: be397ea3473d ("net: ethernet: am65-cpsw: Set default TX channels to maximum") Cc: <stable(a)vger.kernel.org> Signed-off-by: Siddharth Vadapalli <s-vadapalli(a)ti.com> --- Hello, This patch is based on commit 8faabc041a00 Merge tag 'net-6.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net of Mainline Linux. Regards, Siddharth. drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 14e1df721f2e..5465bf872734 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -3551,7 +3551,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) init_completion(&common->tdown_complete); common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS; common->rx_ch_num_flows = AM65_CPSW_DEFAULT_RX_CHN_FLOWS; - common->pf_p0_rx_ptype_rrobin = false; + common->pf_p0_rx_ptype_rrobin = true; common->default_vlan = 1; common->ports = devm_kcalloc(dev, common->port_num, -- 2.43.0

8 months

3
3
0 0

[PATCH v3] tpm: Map the ACPI provided event log

by Jarkko Sakkinen

The following failure was reported: [ 10.693310][ T1] tpm_tis STM0925:00: 2.0 TPM (device-id 0x3, rev-id 0) [ 10.848132][ T1] ------------[ cut here ]------------ [ 10.853559][ T1] WARNING: CPU: 59 PID: 1 at mm/page_alloc.c:4727 __alloc_pages_noprof+0x2ca/0x330 [ 10.862827][ T1] Modules linked in: [ 10.866671][ T1] CPU: 59 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0-lp155.2.g52785e2-default #1 openSUSE Tumbleweed (unreleased) 588cd98293a7c9eba9013378d807364c088c9375 [ 10.882741][ T1] Hardware name: HPE ProLiant DL320 Gen12/ProLiant DL320 Gen12, BIOS 1.20 10/28/2024 [ 10.892170][ T1] RIP: 0010:__alloc_pages_noprof+0x2ca/0x330 [ 10.898103][ T1] Code: 24 08 e9 4a fe ff ff e8 34 36 fa ff e9 88 fe ff ff 83 fe 0a 0f 86 b3 fd ff ff 80 3d 01 e7 ce 01 00 75 09 c6 05 f8 e6 ce 01 01 <0f> 0b 45 31 ff e9 e5 fe ff ff f7 c2 00 00 08 00 75 42 89 d9 80 e1 [ 10.917750][ T1] RSP: 0000:ffffb7cf40077980 EFLAGS: 00010246 [ 10.923777][ T1] RAX: 0000000000000000 RBX: 0000000000040cc0 RCX: 0000000000000000 [ 10.931727][ T1] RDX: 0000000000000000 RSI: 000000000000000c RDI: 0000000000040cc0 Above shows that ACPI pointed a 16 MiB buffer for the log events because RSI maps to the 'order' parameter of __alloc_pages_noprof(). Address the bug by mapping the region when needed instead of copying. Cc: stable(a)vger.kernel.org # v2.6.16+ Fixes: 55a82ab3181b ("[PATCH] tpm: add bios measurement log") Reported-by: Andy Liang <andy.liang(a)hpe.com> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219495 Suggested-by: Matthew Garrett <mjg59(a)srcf.ucam.org> Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v3: * Flag mapping code in tpm{1,2}.c with CONFIG_ACPI (nios2 compilation fix). v2: * There was some extra cruft (irrelevant diff), which is now wiped away. * Added missing tags (fixes, stable). --- drivers/char/tpm/eventlog/acpi.c | 28 +++++++--------------- drivers/char/tpm/eventlog/common.c | 25 +++++++++++++------- drivers/char/tpm/eventlog/common.h | 28 ++++++++++++++++++++++ drivers/char/tpm/eventlog/tpm1.c | 30 ++++++++++++++--------- drivers/char/tpm/eventlog/tpm2.c | 38 +++++++++++++++++------------- include/linux/tpm.h | 1 + 6 files changed, 95 insertions(+), 55 deletions(-) diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 69533d0bfb51..2c4f7355b584 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -70,14 +70,11 @@ int tpm_read_log_acpi(struct tpm_chip *chip) acpi_status status; void __iomem *virt; u64 len, start; - struct tpm_bios_log *log; struct acpi_table_tpm2 *tbl; struct acpi_tpm2_phy *tpm2_phy; int format; int ret; - log = &chip->log; - /* Unfortuntely ACPI does not associate the event log with a specific * TPM, like PPI. Thus all ACPI TPMs will read the same log. */ @@ -135,36 +132,27 @@ int tpm_read_log_acpi(struct tpm_chip *chip) return -EIO; } - /* malloc EventLog space */ - log->bios_event_log = devm_kmalloc(&chip->dev, len, GFP_KERNEL); - if (!log->bios_event_log) - return -ENOMEM; - - log->bios_event_log_end = log->bios_event_log + len; - virt = acpi_os_map_iomem(start, len); if (!virt) { dev_warn(&chip->dev, "%s: Failed to map ACPI memory\n", __func__); /* try EFI log next */ - ret = -ENODEV; - goto err; + return -ENODEV; } - memcpy_fromio(log->bios_event_log, virt, len); - - acpi_os_unmap_iomem(virt, len); - - if (chip->flags & TPM_CHIP_FLAG_TPM2 && - !tpm_is_tpm2_log(log->bios_event_log, len)) { + if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_tpm2_log(virt, len)) { + acpi_os_unmap_iomem(virt, len); /* try EFI log next */ ret = -ENODEV; goto err; } + acpi_os_unmap_iomem(virt, len); + chip->flags |= TPM_CHIP_FLAG_ACPI_LOG; + chip->log.bios_event_log = (void *)start; + chip->log.bios_event_log_end = (void *)start + len; return format; err: - devm_kfree(&chip->dev, log->bios_event_log); - log->bios_event_log = NULL; + acpi_os_unmap_iomem(virt, len); return ret; } diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c index 4c0bbba64ee5..44340ca6e2ac 100644 --- a/drivers/char/tpm/eventlog/common.c +++ b/drivers/char/tpm/eventlog/common.c @@ -27,6 +27,7 @@ static int tpm_bios_measurements_open(struct inode *inode, { int err; struct seq_file *seq; + struct tpm_measurements *priv; struct tpm_chip_seqops *chip_seqops; const struct seq_operations *seqops; struct tpm_chip *chip; @@ -42,13 +43,18 @@ static int tpm_bios_measurements_open(struct inode *inode, get_device(&chip->dev); inode_unlock(inode); - /* now register seq file */ + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + priv->chip = chip; + err = seq_open(file, seqops); - if (!err) { - seq = file->private_data; - seq->private = chip; - } else { + if (err) { + kfree(priv); put_device(&chip->dev); + } else { + seq = file->private_data; + seq->private = priv; } return err; @@ -58,11 +64,14 @@ static int tpm_bios_measurements_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - struct tpm_chip *chip = seq->private; + struct tpm_measurements *priv = seq->private; + int ret; - put_device(&chip->dev); + put_device(&priv->chip->dev); + ret = seq_release(inode, file); + kfree(priv); - return seq_release(inode, file); + return ret; } static const struct file_operations tpm_bios_measurements_ops = { diff --git a/drivers/char/tpm/eventlog/common.h b/drivers/char/tpm/eventlog/common.h index 47ff8136ceb5..b98fd6d9a6e9 100644 --- a/drivers/char/tpm/eventlog/common.h +++ b/drivers/char/tpm/eventlog/common.h @@ -1,12 +1,40 @@ #ifndef __TPM_EVENTLOG_COMMON_H__ #define __TPM_EVENTLOG_COMMON_H__ +#include <linux/acpi.h> #include "../tpm.h" extern const struct seq_operations tpm1_ascii_b_measurements_seqops; extern const struct seq_operations tpm1_binary_b_measurements_seqops; extern const struct seq_operations tpm2_binary_b_measurements_seqops; +struct tpm_measurements { + struct tpm_chip *chip; + void *start; + void *end; +}; + +static inline bool tpm_measurements_map(struct tpm_measurements *measurements) +{ + struct tpm_chip *chip = measurements->chip; + struct tpm_bios_log *log = &chip->log; + size_t size; + + size = log->bios_event_log_end - log->bios_event_log; + measurements->start = log->bios_event_log; + +#ifdef CONFIG_ACPI + if (chip->flags & TPM_CHIP_FLAG_ACPI_LOG) + measurements->start = acpi_os_map_iomem((unsigned long)log->bios_event_log, size); +#endif + + if (!measurements->start) + return false; + + measurements->end = measurements->start + size; + return true; +} + #if defined(CONFIG_ACPI) int tpm_read_log_acpi(struct tpm_chip *chip); #else diff --git a/drivers/char/tpm/eventlog/tpm1.c b/drivers/char/tpm/eventlog/tpm1.c index 12ee42a31c71..aef6ee39423a 100644 --- a/drivers/char/tpm/eventlog/tpm1.c +++ b/drivers/char/tpm/eventlog/tpm1.c @@ -70,20 +70,23 @@ static const char* tcpa_pc_event_id_strings[] = { static void *tpm1_bios_measurements_start(struct seq_file *m, loff_t *pos) { loff_t i = 0; - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *addr = log->bios_event_log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; struct tcpa_event *event; u32 converted_event_size; u32 converted_event_type; + void *addr; + + if (!tpm_measurements_map(priv)) + return NULL; + + addr = priv->start; /* read over *pos measurements */ do { event = addr; /* check if current entry is valid */ - if (addr + sizeof(struct tcpa_event) > limit) + if (addr + sizeof(struct tcpa_event) > priv->end) return NULL; converted_event_size = @@ -93,7 +96,7 @@ static void *tpm1_bios_measurements_start(struct seq_file *m, loff_t *pos) if (((converted_event_type == 0) && (converted_event_size == 0)) || ((addr + sizeof(struct tcpa_event) + converted_event_size) - > limit)) + > priv->end)) return NULL; if (i++ == *pos) @@ -109,9 +112,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, loff_t *pos) { struct tcpa_event *event = v; - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; u32 converted_event_size; u32 converted_event_type; @@ -121,7 +122,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, v += sizeof(struct tcpa_event) + converted_event_size; /* now check if current entry is valid */ - if ((v + sizeof(struct tcpa_event)) > limit) + if ((v + sizeof(struct tcpa_event)) > priv->end) return NULL; event = v; @@ -130,7 +131,7 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, converted_event_type = do_endian_conversion(event->event_type); if (((converted_event_type == 0) && (converted_event_size == 0)) || - ((v + sizeof(struct tcpa_event) + converted_event_size) > limit)) + ((v + sizeof(struct tcpa_event) + converted_event_size) > priv->end)) return NULL; return v; @@ -138,6 +139,13 @@ static void *tpm1_bios_measurements_next(struct seq_file *m, void *v, static void tpm1_bios_measurements_stop(struct seq_file *m, void *v) { +#ifdef CONFIG_ACPI + struct tpm_measurements *priv = m->private; + struct tpm_chip *chip = priv->chip; + + if (chip->flags & TPM_CHIP_FLAG_ACPI_LOG) + acpi_os_unmap_iomem(priv->start, priv->end - priv->start); +#endif } static int get_event_name(char *dest, struct tcpa_event *event, diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c index 37a05800980c..6289d8893e46 100644 --- a/drivers/char/tpm/eventlog/tpm2.c +++ b/drivers/char/tpm/eventlog/tpm2.c @@ -41,20 +41,22 @@ static size_t calc_tpm2_event_size(struct tcg_pcr_event2_head *event, static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) { - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *addr = log->bios_event_log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; struct tcg_pcr_event *event_header; struct tcg_pcr_event2_head *event; size_t size; + void *addr; int i; + if (!tpm_measurements_map(priv)) + return NULL; + + addr = priv->start; event_header = addr; size = struct_size(event_header, event, event_header->event_size); if (*pos == 0) { - if (addr + size < limit) { + if (addr + size < priv->end) { if ((event_header->event_type == 0) && (event_header->event_size == 0)) return NULL; @@ -66,7 +68,7 @@ static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) addr += size; event = addr; size = calc_tpm2_event_size(event, event_header); - if ((addr + size >= limit) || (size == 0)) + if ((addr + size >= priv->end) || !size) return NULL; } @@ -74,7 +76,7 @@ static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) event = addr; size = calc_tpm2_event_size(event, event_header); - if ((addr + size >= limit) || (size == 0)) + if ((addr + size >= priv->end) || !size) return NULL; addr += size; } @@ -87,14 +89,12 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v, { struct tcg_pcr_event *event_header; struct tcg_pcr_event2_head *event; - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - void *limit = log->bios_event_log_end; + struct tpm_measurements *priv = m->private; size_t event_size; void *marker; (*pos)++; - event_header = log->bios_event_log; + event_header = priv->start; if (v == SEQ_START_TOKEN) { event_size = struct_size(event_header, event, @@ -109,13 +109,13 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v, } marker = marker + event_size; - if (marker >= limit) + if (marker >= priv->end) return NULL; v = marker; event = v; event_size = calc_tpm2_event_size(event, event_header); - if (((v + event_size) >= limit) || (event_size == 0)) + if (((v + event_size) >= priv->end) || !event_size) return NULL; return v; @@ -123,13 +123,19 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v, static void tpm2_bios_measurements_stop(struct seq_file *m, void *v) { +#ifdef CONFIG_ACPI + struct tpm_measurements *priv = m->private; + struct tpm_chip *chip = priv->chip; + + if (chip->flags & TPM_CHIP_FLAG_ACPI_LOG) + acpi_os_unmap_iomem(priv->start, priv->end - priv->start); +#endif } static int tpm2_binary_bios_measurements_show(struct seq_file *m, void *v) { - struct tpm_chip *chip = m->private; - struct tpm_bios_log *log = &chip->log; - struct tcg_pcr_event *event_header = log->bios_event_log; + struct tpm_measurements *priv = m->private; + struct tcg_pcr_event *event_header = priv->start; struct tcg_pcr_event2_head *event = v; void *temp_ptr; size_t size; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 20a40ade8030..f3d12738b93b 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -348,6 +348,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_SUSPENDED = BIT(8), TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), TPM_CHIP_FLAG_DISABLE = BIT(10), + TPM_CHIP_FLAG_ACPI_LOG = BIT(11), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- 2.47.1

8 months

1
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2024