From: Jan Kara jack@suse.cz

commit d176b1f62f242ab259ff665a26fbac69db1aecba upstream.

ext4_setup_system_zone() can fail. Handle the failure in ext4_remount().

Reviewed-by: Lukas Czerner lczerner@redhat.com Signed-off-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20200728130437.7804-2-jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/super.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5364,7 +5364,10 @@ static int ext4_remount(struct super_blo ext4_register_li_request(sb, first_not_zeroed); }

- ext4_setup_system_zone(sb); + err = ext4_setup_system_zone(sb); + if (err) + goto restore_opts; + if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY)) ext4_commit_super(sb, 1);

From: Jan Kara jack@suse.cz

commit ce9f24cccdc019229b70a5c15e2b09ad9c0ab5d1 upstream.

Currently, system zones just track ranges of block, that are "important" fs metadata (bitmaps, group descriptors, journal blocks, etc.). This however complicates how extent tree (or indirect blocks) can be checked for inodes that actually track such metadata - currently the journal inode but arguably we should be treating quota files or resize inode similarly. We cannot run __ext4_ext_check() on such metadata inodes when loading their extents as that would immediately trigger the validity checks and so we just hack around that and special-case the journal inode. This however leads to a situation that a journal inode which has extent tree of depth at least one can have invalid extent tree that gets unnoticed until ext4_cache_extents() crashes.

To overcome this limitation, track inode number each system zone belongs to (0 is used for zones not belonging to any inode). We can then verify inode number matches the expected one when verifying extent tree and thus avoid the false errors. With this there's no need to to special-case journal inode during extent tree checking anymore so remove it.

Fixes: 0a944e8a6c66 ("ext4: don't perform block validity checks on the journal inode") Reported-by: Wolfgang Frisch wolfgang.frisch@suse.com Reviewed-by: Lukas Czerner lczerner@redhat.com Signed-off-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20200728130437.7804-4-jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/block_validity.c | 37 +++++++++++++++++++++---------------- fs/ext4/ext4.h | 6 +++--- fs/ext4/extents.c | 16 ++++++---------- fs/ext4/indirect.c | 6 ++---- fs/ext4/inode.c | 5 ++--- fs/ext4/mballoc.c | 4 ++-- 6 files changed, 36 insertions(+), 38 deletions(-)

--- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -24,6 +24,7 @@ struct ext4_system_zone { struct rb_node node; ext4_fsblk_t start_blk; unsigned int count; + u32 ino; };

static struct kmem_cache *ext4_system_zone_cachep; @@ -44,7 +45,8 @@ void ext4_exit_system_zone(void) static inline int can_merge(struct ext4_system_zone *entry1, struct ext4_system_zone *entry2) { - if ((entry1->start_blk + entry1->count) == entry2->start_blk) + if ((entry1->start_blk + entry1->count) == entry2->start_blk && + entry1->ino == entry2->ino) return 1; return 0; } @@ -56,7 +58,7 @@ static inline int can_merge(struct ext4_ */ static int add_system_zone(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, - unsigned int count) + unsigned int count, u32 ino) { struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &sbi->system_blks.rb_node, *node; @@ -79,6 +81,7 @@ static int add_system_zone(struct ext4_s return -ENOMEM; new_entry->start_blk = start_blk; new_entry->count = count; + new_entry->ino = ino; new_node = &new_entry->node;

rb_link_node(new_node, parent, n); @@ -154,16 +157,16 @@ static int ext4_protect_reserved_inode(s if (n == 0) { i++; } else { - if (!ext4_data_block_valid(sbi, map.m_pblk, n)) { - ext4_error(sb, "blocks %llu-%llu from inode %u " + err = add_system_zone(sbi, map.m_pblk, n, ino); + if (err < 0) { + if (err == -EFSCORRUPTED) { + ext4_error(sb, + "blocks %llu-%llu from inode %u " "overlap system zone", map.m_pblk, map.m_pblk + map.m_len - 1, ino); - err = -EFSCORRUPTED; + } break; } - err = add_system_zone(sbi, map.m_pblk, n); - if (err < 0) - break; i += n; } } @@ -192,16 +195,16 @@ int ext4_setup_system_zone(struct super_ if (ext4_bg_has_super(sb, i) && ((i < 5) || ((i % flex_size) == 0))) add_system_zone(sbi, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1); + ext4_bg_num_gdb(sb, i) + 1, 0); gdp = ext4_get_group_desc(sb, i, NULL); - ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); + ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1, 0); if (ret) return ret; - ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1); + ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1, 0); if (ret) return ret; ret = add_system_zone(sbi, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group); + sbi->s_itb_per_group, 0); if (ret) return ret; } @@ -234,10 +237,11 @@ void ext4_release_system_zone(struct sup * start_blk+count) is valid; 0 if some part of the block region * overlaps with filesystem metadata blocks. */ -int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, - unsigned int count) +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, + unsigned int count) { struct ext4_system_zone *entry; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *n = sbi->system_blks.rb_node;

if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || @@ -253,6 +257,8 @@ int ext4_data_block_valid(struct ext4_sb else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { + if (entry->ino == inode->i_ino) + return 1; sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); return 0; } @@ -275,8 +281,7 @@ int ext4_check_blockref(const char *func while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), - blk, 1))) { + unlikely(!ext4_inode_block_valid(inode, blk, 1))) { es->s_last_error_block = cpu_to_le64(blk); ext4_error_inode(inode, function, line, blk, "invalid block"); --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3151,9 +3151,9 @@ extern void ext4_release_system_zone(str extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); -extern int ext4_data_block_valid(struct ext4_sb_info *sbi, - ext4_fsblk_t start_blk, - unsigned int count); +extern int ext4_inode_block_valid(struct inode *inode, + ext4_fsblk_t start_blk, + unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int);

--- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -389,7 +389,7 @@ static int ext4_valid_extent(struct inod */ if (lblock + len <= lblock) return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); + return ext4_inode_block_valid(inode, block, len); }

static int ext4_valid_extent_idx(struct inode *inode, @@ -397,7 +397,7 @@ static int ext4_valid_extent_idx(struct { ext4_fsblk_t block = ext4_idx_pblock(ext_idx);

- return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); + return ext4_inode_block_valid(inode, block, 1); }

static int ext4_valid_extent_entries(struct inode *inode, @@ -554,14 +554,10 @@ __read_extent_tree_block(const char *fun } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - if (!ext4_has_feature_journal(inode->i_sb) || - (inode->i_ino != - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; - } + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -842,8 +842,7 @@ static int ext4_clear_blocks(handle_t *h else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET;

- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, - count)) { + if (!ext4_inode_block_valid(inode, block_to_free, count)) { EXT4_ERROR_INODE(inode, "attempt to clear invalid " "blocks %llu len %lu", (unsigned long long) block_to_free, count); @@ -1005,8 +1004,7 @@ static void ext4_free_branches(handle_t if (!nr) continue; /* A hole */

- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), - nr, 1)) { + if (!ext4_inode_block_valid(inode, nr, 1)) { EXT4_ERROR_INODE(inode, "invalid indirect mapped " "block %lu (level %d)", --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -420,8 +420,7 @@ static int __check_block_validity(struct (inode->i_ino == le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) return 0; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, - map->m_len)) { + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, @@ -4940,7 +4939,7 @@ struct inode *__ext4_iget(struct super_b

ret = 0; if (ei->i_file_acl && - !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { + !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { ext4_error_inode(inode, function, line, 0, "iget: bad extended attribute block %llu", ei->i_file_acl); --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3017,7 +3017,7 @@ ext4_mb_mark_diskspace_used(struct ext4_ block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);

len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (!ext4_data_block_valid(sbi, block, len)) { + if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error @@ -4783,7 +4783,7 @@ void ext4_free_blocks(handle_t *handle,

sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_data_block_valid(sbi, block, count)) { + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return;

From: Piotr Krysiuk piotras@gmail.com

commit b5871dca250cd391885218b99cc015aca1a51aea upstream.

Instead of having the mov32 with aux->alu_limit - 1 immediate, move this operation to retrieve_ptr_limit() instead to simplify the logic and to allow for subsequent sanity boundary checks inside retrieve_ptr_limit(). This avoids in future that at the time of the verifier masking rewrite we'd run into an underflow which would not sign extend due to the nature of mov32 instruction.

Signed-off-by: Piotr Krysiuk piotras@gmail.com Co-developed-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/verifier.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2035,16 +2035,16 @@ static int retrieve_ptr_limit(const stru case PTR_TO_STACK: off = ptr_reg->off + ptr_reg->var_off.value; if (mask_to_left) - *ptr_limit = MAX_BPF_STACK + off + 1; + *ptr_limit = MAX_BPF_STACK + off; else - *ptr_limit = -off; + *ptr_limit = -off - 1; return 0; case PTR_TO_MAP_VALUE: if (mask_to_left) { - *ptr_limit = ptr_reg->umax_value + ptr_reg->off + 1; + *ptr_limit = ptr_reg->umax_value + ptr_reg->off; } else { off = ptr_reg->smin_value + ptr_reg->off; - *ptr_limit = ptr_reg->map_ptr->value_size - off; + *ptr_limit = ptr_reg->map_ptr->value_size - off - 1; } return 0; default: @@ -4802,7 +4802,7 @@ static int fixup_bpf_calls(struct bpf_ve off_reg = issrc ? insn->src_reg : insn->dst_reg; if (isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); - *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);

From: Florian Fainelli f.fainelli@gmail.com

commit f9b3827ee66cfcf297d0acd6ecf33653a5f297ef upstream.

Add support for being able to set the learning attribute on port, and make sure that the standalone ports start up with learning disabled.

We can remove the code in bcm_sf2 that configured the ports learning attribute because we want the standalone ports to have learning disabled by default and port 7 cannot be bridged, so its learning attribute will not change past its initial configuration.

Signed-off-by: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Vladimir Oltean olteanv@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/dsa/b53/b53_common.c | 20 ++++++++++++++++++++ drivers/net/dsa/b53/b53_regs.h | 1 + drivers/net/dsa/bcm_sf2.c | 5 +++++ drivers/net/dsa/bcm_sf2_regs.h | 2 ++ 4 files changed, 28 insertions(+)

--- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -501,6 +501,19 @@ static void b53_imp_vlan_setup(struct ds } }

+static void b53_port_set_learning(struct b53_device *dev, int port, + bool learning) +{ + u16 reg; + + b53_read16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, &reg); + if (learning) + reg &= ~BIT(port); + else + reg |= BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, reg); +} + static int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) { @@ -508,6 +521,8 @@ static int b53_enable_port(struct dsa_sw unsigned int cpu_port = dev->cpu_port; u16 pvlan;

+ b53_port_set_learning(dev, port, false); + /* Clear the Rx and Tx disable bits and set to no spanning tree */ b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), 0);

@@ -551,6 +566,8 @@ static void b53_enable_cpu_port(struct b PORT_CTRL_RX_MCST_EN | PORT_CTRL_RX_UCST_EN; b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(cpu_port), port_ctrl); + + b53_port_set_learning(dev, cpu_port, false); }

static void b53_enable_mib(struct b53_device *dev) @@ -1342,6 +1359,8 @@ int b53_br_join(struct dsa_switch *ds, i b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan); dev->ports[port].vlan_ctl_mask = pvlan;

+ b53_port_set_learning(dev, port, true); + return 0; } EXPORT_SYMBOL(b53_br_join); @@ -1392,6 +1411,7 @@ void b53_br_leave(struct dsa_switch *ds, vl->untag |= BIT(port) | BIT(dev->cpu_port); b53_set_vlan_entry(dev, pvid, vl); } + b53_port_set_learning(dev, port, false); } EXPORT_SYMBOL(b53_br_leave);

--- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -112,6 +112,7 @@ #define B53_UC_FLOOD_MASK 0x32 #define B53_MC_FLOOD_MASK 0x34 #define B53_IPMC_FLOOD_MASK 0x36 +#define B53_DIS_LEARNING 0x3c

/* * Override Ports 0-7 State on devices with xMII interfaces (8 bit) --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -252,6 +252,11 @@ static int bcm_sf2_port_setup(struct dsa reg &= ~P_TXQ_PSM_VDD(port); core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);

+ /* Disable learning */ + reg = core_readl(priv, CORE_DIS_LEARN); + reg |= BIT(port); + core_writel(priv, reg, CORE_DIS_LEARN); + /* Enable Broadcom tags for that port if requested */ if (priv->brcm_tag_mask & BIT(port)) bcm_sf2_brcm_hdr_setup(priv, port); --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -150,6 +150,8 @@ enum bcm_sf2_reg_offs { #define CORE_SWITCH_CTRL 0x00088 #define MII_DUMB_FWDG_EN (1 << 6)

+#define CORE_DIS_LEARN 0x000f0 + #define CORE_SFT_LRN_CTRL 0x000f8 #define SW_LEARN_CNTL(x) (1 << (x))

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 0cab893f409c53634d0d818fa414641cbcdb0dab upstream.

Revert commit 44cc89f76464 ("PM: runtime: Update device status before letting suppliers suspend") that introduced a race condition into __rpm_callback() which allowed a concurrent rpm_resume() to run and resume the device prematurely after its status had been changed to RPM_SUSPENDED by __rpm_callback().

Fixes: 44cc89f76464 ("PM: runtime: Update device status before letting suppliers suspend") Link: https://lore.kernel.org/linux-pm/24dfb6fc-5d54-6ee2-9195-26428b7ecf8a@intel.... Reported-by: Adrian Hunter adrian.hunter@intel.com Cc: 4.10+ stable@vger.kernel.org # 4.10+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/power/runtime.c | 62 +++++++++++++++++-------------------------- 1 file changed, 25 insertions(+), 37 deletions(-)

--- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -306,22 +306,22 @@ static void rpm_put_suppliers(struct dev static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { - bool use_links = dev->power.links_count > 0; - bool get = false; int retval, idx; - bool put; + bool use_links = dev->power.links_count > 0;

if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); - } else if (!use_links) { - spin_unlock_irq(&dev->power.lock); } else { - get = dev->power.runtime_status == RPM_RESUMING; - spin_unlock_irq(&dev->power.lock);

- /* Resume suppliers if necessary. */ - if (get) { + /* + * Resume suppliers if necessary. + * + * The device's runtime PM status cannot change until this + * routine returns, so it is safe to read the status outside of + * the lock. + */ + if (use_links && dev->power.runtime_status == RPM_RESUMING) { idx = device_links_read_lock();

retval = rpm_get_suppliers(dev); @@ -336,36 +336,24 @@ static int __rpm_callback(int (*cb)(stru

if (dev->power.irq_safe) { spin_lock(&dev->power.lock); - return retval; - } - - spin_lock_irq(&dev->power.lock); - - if (!use_links) - return retval; - - /* - * If the device is suspending and the callback has returned success, - * drop the usage counters of the suppliers that have been reference - * counted on its resume. - * - * Do that if the resume fails too. - */ - put = dev->power.runtime_status == RPM_SUSPENDING && !retval; - if (put) - __update_runtime_status(dev, RPM_SUSPENDED); - else - put = get && retval; - - if (put) { - spin_unlock_irq(&dev->power.lock); - - idx = device_links_read_lock(); + } else { + /* + * If the device is suspending and the callback has returned + * success, drop the usage counters of the suppliers that have + * been reference counted on its resume. + * + * Do that if resume fails too. + */ + if (use_links + && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) + || (dev->power.runtime_status == RPM_RESUMING && retval))) { + idx = device_links_read_lock();

-fail: - rpm_put_suppliers(dev); + fail: + rpm_put_suppliers(dev);

- device_links_read_unlock(idx); + device_links_read_unlock(idx); + }

spin_lock_irq(&dev->power.lock); }

From: Arnaldo Carvalho de Melo acme@redhat.com

commit 8feb8efef97a134933620071e0b6384cb3238b4e upstream.

As the namespace support code will use this, which is not available in some non _GNU_SOURCE libraries such as Android's bionic used in my container build tests (r12b and r15c at the moment).

Cc: Adrian Hunter adrian.hunter@intel.com Cc: David Ahern dsahern@gmail.com Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Cc: Wang Nan wangnan0@huawei.com Link: https://lkml.kernel.org/n/tip-x56ypm940pwclwu45d7jfj47@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-all.c | 5 +++++ tools/build/feature/test-get_current_dir_name.c | 10 ++++++++++ tools/perf/Makefile.config | 5 +++++ tools/perf/util/Build | 1 + tools/perf/util/get_current_dir_name.c | 18 ++++++++++++++++++ tools/perf/util/util.h | 4 ++++ 8 files changed, 48 insertions(+) create mode 100644 tools/build/feature/test-get_current_dir_name.c create mode 100644 tools/perf/util/get_current_dir_name.c

--- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC := dwarf_getlocations \ fortify-source \ sync-compare-and-swap \ + get_current_dir_name \ glibc \ gtk2 \ gtk2-infobar \ --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -7,6 +7,7 @@ FILES= test-dwarf_getlocations.bin \ test-fortify-source.bin \ test-sync-compare-and-swap.bin \ + test-get_current_dir_name.bin \ test-glibc.bin \ test-gtk2.bin \ test-gtk2-infobar.bin \ @@ -89,6 +90,9 @@ $(OUTPUT)test-bionic.bin: $(OUTPUT)test-libelf.bin: $(BUILD) -lelf

+$(OUTPUT)test-get_current_dir_name.bin: + $(BUILD) + $(OUTPUT)test-glibc.bin: $(BUILD)

--- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -34,6 +34,10 @@ # include "test-libelf-mmap.c" #undef main

+#define main main_test_get_current_dir_name +# include "test-get_current_dir_name.c" +#undef main + #define main main_test_glibc # include "test-glibc.c" #undef main @@ -166,6 +170,7 @@ int main(int argc, char *argv[]) main_test_hello(); main_test_libelf(); main_test_libelf_mmap(); + main_test_get_current_dir_name(); main_test_glibc(); main_test_dwarf(); main_test_dwarf_getlocations(); --- /dev/null +++ b/tools/build/feature/test-get_current_dir_name.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <unistd.h> +#include <stdlib.h> + +int main(void) +{ + free(get_current_dir_name()); + return 0; +} --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -281,6 +281,11 @@ ifndef NO_BIONIC endif endif

+ifeq ($(feature-get_current_dir_name), 1) + CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME +endif + + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -10,6 +10,7 @@ libperf-y += evlist.o libperf-y += evsel.o libperf-y += evsel_fprintf.o libperf-y += find_bit.o +libperf-y += get_current_dir_name.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o --- /dev/null +++ b/tools/perf/util/get_current_dir_name.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo acme@redhat.com +// +#ifndef HAVE_GET_CURRENT_DIR_NAME +#include "util.h" +#include <unistd.h> +#include <stdlib.h> +#include <stdlib.h> + +/* Android's 'bionic' library, for one, doesn't have this */ + +char *get_current_dir_name(void) +{ + char pwd[PATH_MAX]; + + return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd); +} +#endif // HAVE_GET_CURRENT_DIR_NAME --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -57,6 +57,10 @@ int fetch_kernel_version(unsigned int *p

const char *perf_tip(const char *dirpath);

+#ifndef HAVE_GET_CURRENT_DIR_NAME +char *get_current_dir_name(void); +#endif + #ifndef HAVE_SCHED_GETCPU_SUPPORT int sched_getcpu(void); #endif

From: Arnaldo Carvalho de Melo acme@redhat.com

commit 4541a8bb13a86e504416a13360c8dc64d2fd612a upstream.

Laura reported that the perf build failed in fedora when we got a glibc that provides gettid(), which I reproduced using fedora rawhide with the glibc-devel-2.29.9000-26.fc31.x86_64 package.

Add a feature check to avoid providing a gettid() helper in such systems.

On a fedora rawhide system with this patch applied we now get:

[root@7a5f55352234 perf]# grep gettid /tmp/build/perf/FEATURE-DUMP feature-gettid=1 [root@7a5f55352234 perf]# cat /tmp/build/perf/feature/test-gettid.make.output [root@7a5f55352234 perf]# ldd /tmp/build/perf/feature/test-gettid.bin linux-vdso.so.1 (0x00007ffc6b1f6000) libc.so.6 => /lib64/libc.so.6 (0x00007f04e0a74000) /lib64/ld-linux-x86-64.so.2 (0x00007f04e0c47000) [root@7a5f55352234 perf]# nm /tmp/build/perf/feature/test-gettid.bin | grep -w gettid U gettid@@GLIBC_2.30 [root@7a5f55352234 perf]#

While on a fedora:29 system:

[acme@quaco perf]$ grep gettid /tmp/build/perf/FEATURE-DUMP feature-gettid=0 [acme@quaco perf]$ cat /tmp/build/perf/feature/test-gettid.make.output test-gettid.c: In function ‘main’: test-gettid.c:8:9: error: implicit declaration of function ‘gettid’; did you mean ‘getgid’? [-Werror=implicit-function-declaration] return gettid(); ^~~~~~ getgid cc1: all warnings being treated as errors [acme@quaco perf]$

Reported-by: Laura Abbott labbott@redhat.com Tested-by: Laura Abbott labbott@redhat.com Acked-by: Jiri Olsa jolsa@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Florian Weimer fweimer@redhat.com Cc: Namhyung Kim namhyung@kernel.org Cc: Stephane Eranian eranian@google.com Link: https://lkml.kernel.org/n/tip-yfy3ch53agmklwu9o7rlgf9c@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-all.c | 5 +++++ tools/build/feature/test-gettid.c | 11 +++++++++++ tools/perf/Makefile.config | 4 ++++ tools/perf/jvmti/jvmti_agent.c | 2 ++ 6 files changed, 27 insertions(+) create mode 100644 tools/build/feature/test-gettid.c

--- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -35,6 +35,7 @@ FEATURE_TESTS_BASIC := fortify-source \ sync-compare-and-swap \ get_current_dir_name \ + gettid \ glibc \ gtk2 \ gtk2-infobar \ --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -51,6 +51,7 @@ FILES= test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ + test-gettid.bin \ test-jvmti.bin \ test-sched_getcpu.bin \ test-setns.bin @@ -242,6 +243,9 @@ $(OUTPUT)test-sdt.bin: $(OUTPUT)test-cxx.bin: $(BUILDXX) -std=gnu++11

+$(OUTPUT)test-gettid.bin: + $(BUILD) + $(OUTPUT)test-jvmti.bin: $(BUILD)

--- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -38,6 +38,10 @@ # include "test-get_current_dir_name.c" #undef main

+#define main main_test_gettid +# include "test-gettid.c" +#undef main + #define main main_test_glibc # include "test-glibc.c" #undef main @@ -175,6 +179,7 @@ int main(int argc, char *argv[]) main_test_libelf(); main_test_libelf_mmap(); main_test_get_current_dir_name(); + main_test_gettid(); main_test_glibc(); main_test_dwarf(); main_test_dwarf_getlocations(); --- /dev/null +++ b/tools/build/feature/test-gettid.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo acme@redhat.com +#define _GNU_SOURCE +#include <unistd.h> + +int main(void) +{ + return gettid(); +} + +#undef _GNU_SOURCE --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -289,6 +289,10 @@ ifeq ($(feature-get_current_dir_name), 1 CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME endif

+ifeq ($(feature-gettid), 1) + CFLAGS += -DHAVE_GETTID +endif + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -45,10 +45,12 @@ static char jit_path[PATH_MAX]; static void *marker_addr;

+#ifndef HAVE_GETTID static inline pid_t gettid(void) { return (pid_t)syscall(__NR_gettid); } +#endif

static int get_e_machine(struct jitheader *hdr) {

From: Arnaldo Carvalho de Melo acme@redhat.com

commit 25ab5abf5b141d7fd13eed506c7458aa04749c29 upstream.

As 'perf bench futex wake-parallel" will use this, which is not available in older systems such as versions of the android NDK used in my container build tests (r12b and r15c at the moment).

Cc: Adrian Hunter adrian.hunter@intel.com Cc: David Ahern dsahern@gmail.com Cc: Davidlohr Bueso dave@stgolabs.net Cc: James Yang <james.yang@arm.com Cc: Jiri Olsa jolsa@kernel.org Cc: Kim Phillips kim.phillips@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Wang Nan wangnan0@huawei.com Link: https://lkml.kernel.org/n/tip-1i7iv54in4wj08lwo55b0pzv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-all.c | 5 +++++ tools/build/feature/test-pthread-barrier.c | 12 ++++++++++++ tools/perf/Makefile.config | 4 ++++ 5 files changed, 26 insertions(+) create mode 100644 tools/build/feature/test-pthread-barrier.c

--- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -59,6 +59,7 @@ FEATURE_TESTS_BASIC := libunwind-arm \ libunwind-aarch64 \ pthread-attr-setaffinity-np \ + pthread-barrier \ stackprotector-all \ timerfd \ libdw-dwarf-unwind \ --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -39,6 +39,7 @@ FILES= test-libunwind-debug-frame-arm.bin \ test-libunwind-debug-frame-aarch64.bin \ test-pthread-attr-setaffinity-np.bin \ + test-pthread-barrier.bin \ test-stackprotector-all.bin \ test-timerfd.bin \ test-libdw-dwarf-unwind.bin \ @@ -80,6 +81,9 @@ $(OUTPUT)test-hello.bin: $(OUTPUT)test-pthread-attr-setaffinity-np.bin: $(BUILD) -D_GNU_SOURCE -lpthread

+$(OUTPUT)test-pthread-barrier.bin: + $(BUILD) -lpthread + $(OUTPUT)test-stackprotector-all.bin: $(BUILD) -fstack-protector-all

--- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -130,6 +130,10 @@ # include "test-pthread-attr-setaffinity-np.c" #undef main

+#define main main_test_pthread_barrier +# include "test-pthread-barrier.c" +#undef main + #define main main_test_sched_getcpu # include "test-sched_getcpu.c" #undef main @@ -202,6 +206,7 @@ int main(int argc, char *argv[]) main_test_sync_compare_and_swap(argc, argv); main_test_zlib(); main_test_pthread_attr_setaffinity_np(); + main_test_pthread_barrier(); main_test_lzma(); main_test_get_cpuid(); main_test_bpf(); --- /dev/null +++ b/tools/build/feature/test-pthread-barrier.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdint.h> +#include <pthread.h> + +int main(void) +{ + pthread_barrier_t barrier; + + pthread_barrier_init(&barrier, NULL, 1); + pthread_barrier_wait(&barrier); + return pthread_barrier_destroy(&barrier); +} --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,10 @@ ifeq ($(feature-pthread-attr-setaffinity CFLAGS += -DHAVE_PTHREAD_ATTR_SETAFFINITY_NP endif

+ifeq ($(feature-pthread-barrier), 1) + CFLAGS += -DHAVE_PTHREAD_BARRIER +endif + ifndef NO_BIONIC $(call feature_check,bionic) ifeq ($(feature-bionic), 1)

From: Sagi Grimberg sagi@grimberg.me

commit d218a8a3003e84ab136e69a4e30dd4ec7dab2d22 upstream.

From the base spec, Figure 78:

"Controller Configuration, these fields are defined as parameters to configure an "I/O Controller (IOC)" and not to configure a "Discovery Controller (DC).

... If the controller does not support I/O queues, then this field shall be read-only with a value of 0h

Just perform this check for I/O controllers.

Fixes: a07b4970f464 ("nvmet: add a generic NVMe target") Reported-by: Belanger, Martin Martin.Belanger@dell.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Chaitanya Kulkarni chaitanya.kulkarni@wdc.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/target/core.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-)

--- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -594,9 +594,20 @@ static void nvmet_start_ctrl(struct nvme { lockdep_assert_held(&ctrl->lock);

- if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES || - nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES || - nvmet_cc_mps(ctrl->cc) != 0 || + /* + * Only I/O controllers should verify iosqes,iocqes. + * Strictly speaking, the spec says a discovery controller + * should verify iosqes,iocqes are zeroed, however that + * would break backwards compatibility, so don't enforce it. + */ + if (ctrl->subsys->type != NVME_NQN_DISC && + (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES || + nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) { + ctrl->csts = NVME_CSTS_CFS; + return; + } + + if (nvmet_cc_mps(ctrl->cc) != 0 || nvmet_cc_ams(ctrl->cc) != 0 || nvmet_cc_css(ctrl->cc) != 0) { ctrl->csts = NVME_CSTS_CFS;

From: Timo Rothenpieler timo@rothenpieler.org

commit 6820bf77864d5894ff67b5c00d7dba8f92011e3d upstream.

This brings it in line with the regular tcp backchannel, which also has all those timeouts disabled.

Prevents the backchannel from timing out, getting some async operations like server side copying getting stuck indefinitely on the client side.

Signed-off-by: Timo Rothenpieler timo@rothenpieler.org Fixes: 5d252f90a800 ("svcrdma: Add class for RDMA backwards direction transport") Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -321,9 +321,9 @@ xprt_setup_rdma_bc(struct xprt_create *a xprt->timeout = &xprt_rdma_bc_timeout; xprt_set_bound(xprt); xprt_set_connected(xprt); - xprt->bind_timeout = RPCRDMA_BIND_TO; - xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO; - xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO; + xprt->bind_timeout = 0; + xprt->reestablish_timeout = 0; + xprt->idle_timeout = 0;

xprt->prot = XPRT_TRANSPORT_BC_RDMA; xprt->tsh_size = RPCRDMA_HDRLEN_MIN / sizeof(__be32);

From: Pavel Skripkin paskripkin@gmail.com

commit 093b036aa94e01a0bea31a38d7f0ee28a2749023 upstream.

syzbot found WARNING in __alloc_pages_nodemask()[1] when order >= MAX_ORDER. It was caused by a huge length value passed from userspace to qrtr_tun_write_iter(), which tries to allocate skb. Since the value comes from the untrusted source there is no need to raise a warning in __alloc_pages_nodemask().

[1] WARNING in __alloc_pages_nodemask+0x5f8/0x730 mm/page_alloc.c:5014 Call Trace: __alloc_pages include/linux/gfp.h:511 [inline] __alloc_pages_node include/linux/gfp.h:524 [inline] alloc_pages_node include/linux/gfp.h:538 [inline] kmalloc_large_node+0x60/0x110 mm/slub.c:3999 __kmalloc_node_track_caller+0x319/0x3f0 mm/slub.c:4496 __kmalloc_reserve net/core/skbuff.c:150 [inline] __alloc_skb+0x4e4/0x5a0 net/core/skbuff.c:210 __netdev_alloc_skb+0x70/0x400 net/core/skbuff.c:446 netdev_alloc_skb include/linux/skbuff.h:2832 [inline] qrtr_endpoint_post+0x84/0x11b0 net/qrtr/qrtr.c:442 qrtr_tun_write_iter+0x11f/0x1a0 net/qrtr/tun.c:98 call_write_iter include/linux/fs.h:1901 [inline] new_sync_write+0x426/0x650 fs/read_write.c:518 vfs_write+0x791/0xa30 fs/read_write.c:605 ksys_write+0x12d/0x250 fs/read_write.c:658 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported-by: syzbot+80dccaee7c6630fa9dcf@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin paskripkin@gmail.com Acked-by: Alexander Lobakin alobakin@pm.me Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/qrtr/qrtr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -235,7 +235,7 @@ int qrtr_endpoint_post(struct qrtr_endpo if (dst != QRTR_PORT_CTRL && type != QRTR_TYPE_DATA) return -EINVAL;

- skb = netdev_alloc_skb(NULL, len); + skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN); if (!skb) return -ENOMEM;

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit c4c6df5fc84659690d4391d1fba155cd94185295 ]

We only setup io queues for nvme controllers, and it makes absolutely no sense to allow a controller (re)connect without any I/O queues. If we happen to fail setting the queue count for any reason, we should not allow this to be a successful reconnect as I/O has no chance in going through. Instead just fail and schedule another reconnect.

Reported-by: Chao Leng lengchao@huawei.com Fixes: 711023071960 ("nvme-rdma: add a NVMe over Fabrics RDMA host driver") Signed-off-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Chao Leng lengchao@huawei.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/rdma.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 564e457f1345..57e1c0dd63c4 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -655,8 +655,11 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) return ret;

ctrl->ctrl.queue_count = nr_io_queues + 1; - if (ctrl->ctrl.queue_count < 2) - return 0; + if (ctrl->ctrl.queue_count < 2) { + dev_err(ctrl->ctrl.device, + "unable to set any I/O queues\n"); + return -ENOMEM; + }

dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues);

From: Macpaul Lin macpaul.lin@mediatek.com

commit 81c7462883b0cc0a4eeef0687f80ad5b5baee5f6 upstream.

Replace hardcoded maximum USB string length (126 bytes) by definition "USB_MAX_STRING_LEN".

Signed-off-by: Macpaul Lin macpaul.lin@mediatek.com Acked-by: Alan Stern stern@rowland.harvard.edu Link: https://lore.kernel.org/r/1592471618-29428-1-git-send-email-macpaul.lin@medi... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/gadget/composite.c | 4 ++-- drivers/usb/gadget/configfs.c | 2 +- drivers/usb/gadget/usbstring.c | 4 ++-- include/uapi/linux/usb/ch9.h | 3 +++ 4 files changed, 8 insertions(+), 5 deletions(-)

--- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1080,7 +1080,7 @@ static void collect_langs(struct usb_gad while (*sp) { s = *sp; language = cpu_to_le16(s->language); - for (tmp = buf; *tmp && tmp < &buf[126]; tmp++) { + for (tmp = buf; *tmp && tmp < &buf[USB_MAX_STRING_LEN]; tmp++) { if (*tmp == language) goto repeat; } @@ -1155,7 +1155,7 @@ static int get_string(struct usb_composi collect_langs(sp, s->wData); }

- for (len = 0; len <= 126 && s->wData[len]; len++) + for (len = 0; len <= USB_MAX_STRING_LEN && s->wData[len]; len++) continue; if (!len) return -EINVAL; --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -114,7 +114,7 @@ static int usb_string_copy(const char *s char *str; char *copy = *s_copy; ret = strlen(s); - if (ret > 126) + if (ret > USB_MAX_STRING_LEN) return -EOVERFLOW;

str = kstrdup(s, GFP_KERNEL); --- a/drivers/usb/gadget/usbstring.c +++ b/drivers/usb/gadget/usbstring.c @@ -59,9 +59,9 @@ usb_gadget_get_string (struct usb_gadget return -EINVAL;

/* string descriptors have length, tag, then UTF16-LE text */ - len = min ((size_t) 126, strlen (s->s)); + len = min((size_t)USB_MAX_STRING_LEN, strlen(s->s)); len = utf8s_to_utf16s(s->s, len, UTF16_LITTLE_ENDIAN, - (wchar_t *) &buf[2], 126); + (wchar_t *) &buf[2], USB_MAX_STRING_LEN); if (len < 0) return -EINVAL; buf [0] = (len + 1) * 2; --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -360,6 +360,9 @@ struct usb_config_descriptor {

/*-------------------------------------------------------------------------*/

+/* USB String descriptors can contain at most 126 characters. */ +#define USB_MAX_STRING_LEN 126 + /* USB_DT_STRING: String descriptor */ struct usb_string_descriptor { __u8 bLength;

From: Jonathan Cameron Jonathan.Cameron@huawei.com

commit 121875b28e3bd7519a675bf8ea2c2e793452c2bd upstream.

Seems that there are config combinations in which this driver gets enabled and hence selects the MFD, but with out HAS_IOMEM getting pulled in via some other route. MFD is entirely contained in an if HAS_IOMEM block, leading to the build issue in this bugzilla.

https://bugzilla.kernel.org/show_bug.cgi?id=209889

Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Link: https://lore.kernel.org/r/20210124195034.22576-1-jic23@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/adc/Kconfig | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -635,6 +635,7 @@ config STM32_ADC_CORE depends on HAS_DMA depends on OF depends on REGULATOR + depends on HAS_IOMEM select IIO_BUFFER select MFD_STM32_TIMERS select IIO_STM32_TIMER_TRIGGER

From: Dan Carpenter dan.carpenter@oracle.com

commit a71266e454b5df10d019b06f5ebacd579f76be28 upstream.

This is to silence a new Smatch warning:

drivers/iio/imu/adis16400.c:492 adis16400_initial_setup() warn: sscanf doesn't return error codes

If the condition "if (st->variant->flags & ADIS16400_HAS_SLOW_MODE) {" is false then we return 1 instead of returning 0 and probe will fail.

Fixes: 72a868b38bdd ("iio: imu: check sscanf return value") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Cc: Stable@vger.kernel.org Link: https://lore.kernel.org/r/YCwgFb3JVG6qrlQ+@mwanda Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/iio/imu/adis16400_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/iio/imu/adis16400_core.c +++ b/drivers/iio/imu/adis16400_core.c @@ -288,8 +288,7 @@ static int adis16400_initial_setup(struc if (ret) goto err_ret;

- ret = sscanf(indio_dev->name, "adis%u\n", &device_id); - if (ret != 1) { + if (sscanf(indio_dev->name, "adis%u\n", &device_id) != 1) { ret = -EINVAL; goto err_ret; }

From: Ye Xiang xiang.ye@intel.com

commit 37e89e574dc238a4ebe439543c5ab4fbb2f0311b upstream.

This patch ensures that, there is sufficient space and correct alignment for the timestamp.

Fixes: d7ed89d5aadf ("iio: hid: Add humidity sensor support") Signed-off-by: Ye Xiang xiang.ye@intel.com Cc: Stable@vger.kernel.org Link: https://lore.kernel.org/r/20210303063615.12130-2-xiang.ye@intel.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/humidity/hid-sensor-humidity.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/drivers/iio/humidity/hid-sensor-humidity.c +++ b/drivers/iio/humidity/hid-sensor-humidity.c @@ -28,7 +28,10 @@ struct hid_humidity_state { struct hid_sensor_common common_attributes; struct hid_sensor_hub_attribute_info humidity_attr; - s32 humidity_data; + struct { + s32 humidity_data; + u64 timestamp __aligned(8); + } scan; int scale_pre_decml; int scale_post_decml; int scale_precision; @@ -139,9 +142,8 @@ static int humidity_proc_event(struct hi struct hid_humidity_state *humid_st = iio_priv(indio_dev);

if (atomic_read(&humid_st->common_attributes.data_ready)) - iio_push_to_buffers_with_timestamp(indio_dev, - &humid_st->humidity_data, - iio_get_time_ns(indio_dev)); + iio_push_to_buffers_with_timestamp(indio_dev, &humid_st->scan, + iio_get_time_ns(indio_dev));

return 0; } @@ -156,7 +158,7 @@ static int humidity_capture_sample(struc

switch (usage_id) { case HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY: - humid_st->humidity_data = *(s32 *)raw_data; + humid_st->scan.humidity_data = *(s32 *)raw_data;

return 0; default:

From: Ye Xiang xiang.ye@intel.com

commit 141e7633aa4d2838d1f6ad5c74cccc53547c16ac upstream.

This patch fixes 2 issues of timestamp channel: 1. This patch ensures that there is sufficient space and correct alignment for the timestamp. 2. Correct the timestamp channel scan index.

Fixes: 59d0f2da3569 ("iio: hid: Add temperature sensor support") Signed-off-by: Ye Xiang xiang.ye@intel.com Cc: Stable@vger.kernel.org Link: https://lore.kernel.org/r/20210303063615.12130-4-xiang.ye@intel.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/temperature/hid-sensor-temperature.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

--- a/drivers/iio/temperature/hid-sensor-temperature.c +++ b/drivers/iio/temperature/hid-sensor-temperature.c @@ -28,7 +28,10 @@ struct temperature_state { struct hid_sensor_common common_attributes; struct hid_sensor_hub_attribute_info temperature_attr; - s32 temperature_data; + struct { + s32 temperature_data; + u64 timestamp __aligned(8); + } scan; int scale_pre_decml; int scale_post_decml; int scale_precision; @@ -45,7 +48,7 @@ static const struct iio_chan_spec temper BIT(IIO_CHAN_INFO_SAMP_FREQ) | BIT(IIO_CHAN_INFO_HYSTERESIS), }, - IIO_CHAN_SOFT_TIMESTAMP(3), + IIO_CHAN_SOFT_TIMESTAMP(1), };

/* Adjust channel real bits based on report descriptor */ @@ -137,9 +140,8 @@ static int temperature_proc_event(struct struct temperature_state *temp_st = iio_priv(indio_dev);

if (atomic_read(&temp_st->common_attributes.data_ready)) - iio_push_to_buffers_with_timestamp(indio_dev, - &temp_st->temperature_data, - iio_get_time_ns(indio_dev)); + iio_push_to_buffers_with_timestamp(indio_dev, &temp_st->scan, + iio_get_time_ns(indio_dev));

return 0; } @@ -154,7 +156,7 @@ static int temperature_capture_sample(st

switch (usage_id) { case HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE: - temp_st->temperature_data = *(s32 *)raw_data; + temp_st->scan.temperature_data = *(s32 *)raw_data; return 0; default: return -EINVAL;

From: Kan Liang kan.liang@linux.intel.com

commit d88d05a9e0b6d9356e97129d4ff9942d765f46ea upstream.

A repeatable crash can be triggered by the perf_fuzzer on some Haswell system. https://lore.kernel.org/lkml/7170d3b-c17f-1ded-52aa-cc6d9ae999f4@maine.edu/

For some old CPUs (HSW and earlier), the PEBS status in a PEBS record may be mistakenly set to 0. To minimize the impact of the defect, the commit was introduced to try to avoid dropping the PEBS record for some cases. It adds a check in the intel_pmu_drain_pebs_nhm(), and updates the local pebs_status accordingly. However, it doesn't correct the PEBS status in the PEBS record, which may trigger the crash, especially for the large PEBS.

It's possible that all the PEBS records in a large PEBS have the PEBS status 0. If so, the first get_next_pebs_record_by_bit() in the __intel_pmu_pebs_event() returns NULL. The at = NULL. Since it's a large PEBS, the 'count' parameter must > 1. The second get_next_pebs_record_by_bit() will crash.

Besides the local pebs_status, correct the PEBS status in the PEBS record as well.

Fixes: 01330d7288e0 ("perf/x86: Allow zero PEBS status with only single active event") Reported-by: Vince Weaver vincent.weaver@maine.edu Suggested-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1615555298-140216-1-git-send-email-kan.liang@linux... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/events/intel/ds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1515,7 +1515,7 @@ static void intel_pmu_drain_pebs_nhm(str */ if (!pebs_status && cpuc->pebs_enabled && !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) - pebs_status = cpuc->pebs_enabled; + pebs_status = p->status = cpuc->pebs_enabled;

bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events);

From: Oleg Nesterov oleg@redhat.com

commit 5abbe51a526253b9f003e9a0a195638dc882d660 upstream.

Preparation for fixing get_nr_restart_syscall() on X86 for COMPAT.

Add a new helper which sets restart_block->fn and calls a dummy arch_set_restart_data() helper.

Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code") Signed-off-by: Oleg Nesterov oleg@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210201174641.GA17871@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/select.c | 10 ++++------ include/linux/thread_info.h | 13 +++++++++++++ kernel/futex.c | 3 +-- kernel/time/alarmtimer.c | 2 +- kernel/time/hrtimer.c | 2 +- kernel/time/posix-cpu-timers.c | 2 +- 6 files changed, 21 insertions(+), 11 deletions(-)

--- a/fs/select.c +++ b/fs/select.c @@ -1006,10 +1006,9 @@ static long do_restart_poll(struct resta

ret = do_sys_poll(ufds, nfds, to);

- if (ret == -EINTR) { - restart_block->fn = do_restart_poll; - ret = -ERESTART_RESTARTBLOCK; - } + if (ret == -EINTR) + ret = set_restart_fn(restart_block, do_restart_poll); + return ret; }

@@ -1031,7 +1030,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __us struct restart_block *restart_block;

restart_block = &current->restart_block; - restart_block->fn = do_restart_poll; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds;

@@ -1042,7 +1040,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __us } else restart_block->poll.has_timeout = 0;

- ret = -ERESTART_RESTARTBLOCK; + ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -11,6 +11,7 @@ #include <linux/types.h> #include <linux/bug.h> #include <linux/restart_block.h> +#include <linux/errno.h>

#ifdef CONFIG_THREAD_INFO_IN_TASK /* @@ -39,6 +40,18 @@ enum {

#ifdef __KERNEL__

+#ifndef arch_set_restart_data +#define arch_set_restart_data(restart) do { } while (0) +#endif + +static inline long set_restart_fn(struct restart_block *restart, + long (*fn)(struct restart_block *)) +{ + restart->fn = fn; + arch_set_restart_data(restart); + return -ERESTART_RESTARTBLOCK; +} + #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2875,14 +2875,13 @@ retry: goto out;

restart = &current->restart_block; - restart->fn = futex_wait_restart; restart->futex.uaddr = uaddr; restart->futex.val = val; restart->futex.time = *abs_time; restart->futex.bitset = bitset; restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;

- ret = -ERESTART_RESTARTBLOCK; + ret = set_restart_fn(restart, futex_wait_restart);

out: if (to) { --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -822,9 +822,9 @@ static int alarm_timer_nsleep(const cloc if (flags == TIMER_ABSTIME) return -ERESTARTNOHAND;

- restart->fn = alarm_timer_nsleep_restart; restart->nanosleep.clockid = type; restart->nanosleep.expires = exp; + set_restart_fn(restart, alarm_timer_nsleep_restart); return ret; }

--- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1545,9 +1545,9 @@ long hrtimer_nanosleep(const struct time }

restart = &current->restart_block; - restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); + set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1348,8 +1348,8 @@ static int posix_cpu_nsleep(const clocki if (flags & TIMER_ABSTIME) return -ERESTARTNOHAND;

- restart_block->fn = posix_cpu_nsleep_restart; restart_block->nanosleep.clockid = which_clock; + set_restart_fn(restart_block, posix_cpu_nsleep_restart); } return error; }

From: Oleg Nesterov oleg@redhat.com

commit 8c150ba2fb5995c84a7a43848250d444a3329a7d upstream.

The comment in get_nr_restart_syscall() says:

* The problem is that we can get here when ptrace pokes * syscall-like values into regs even if we're not in a syscall * at all.

Yes, but if not in a syscall then the

status & (TS_COMPAT|TS_I386_REGS_POKED)

check below can't really help:

- TS_COMPAT can't be set

- TS_I386_REGS_POKED is only set if regs->orig_ax was changed by 32bit debugger; and even in this case get_nr_restart_syscall() is only correct if the tracee is 32bit too.

Suppose that a 64bit debugger plays with a 32bit tracee and

* Tracee calls sleep(2) // TS_COMPAT is set * User interrupts the tracee by CTRL-C after 1 sec and does "(gdb) call func()" * gdb saves the regs by PTRACE_GETREGS * does PTRACE_SETREGS to set %rip='func' and %orig_rax=-1 * PTRACE_CONT // TS_COMPAT is cleared * func() hits int3. * Debugger catches SIGTRAP. * Restore original regs by PTRACE_SETREGS. * PTRACE_CONT

get_nr_restart_syscall() wrongly returns __NR_restart_syscall==219, the tracee calls ia32_sys_call_table[219] == sys_madvise.

Add the sticky TS_COMPAT_RESTART flag which survives after return to user mode. It's going to be removed in the next step again by storing the information in the restart block. As a further cleanup it might be possible to remove also TS_I386_REGS_POKED with that.

Test-case:

$ cvs -d :pserver:anoncvs:anoncvs@sourceware.org:/cvs/systemtap co ptrace-tests $ gcc -o erestartsys-trap-debuggee ptrace-tests/tests/erestartsys-trap-debuggee.c --m32 $ gcc -o erestartsys-trap-debugger ptrace-tests/tests/erestartsys-trap-debugger.c -lutil $ ./erestartsys-trap-debugger Unexpected: retval 1, errno 22 erestartsys-trap-debugger: ptrace-tests/tests/erestartsys-trap-debugger.c:421

Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code") Reported-by: Jan Kratochvil jan.kratochvil@redhat.com Signed-off-by: Oleg Nesterov oleg@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210201174709.GA17895@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/thread_info.h | 14 +++++++++++++- arch/x86/kernel/signal.c | 24 +----------------------- 2 files changed, 14 insertions(+), 24 deletions(-)

--- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -238,10 +238,22 @@ static inline int arch_within_stack_fram */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/

+#ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ +#define TS_COMPAT_RESTART 0x0008 + +#define arch_set_restart_data arch_set_restart_data + +static inline void arch_set_restart_data(struct restart_block *restart) +{ + struct thread_info *ti = current_thread_info(); + if (ti->status & TS_COMPAT) + ti->status |= TS_COMPAT_RESTART; + else + ti->status &= ~TS_COMPAT_RESTART; +} #endif -#ifndef __ASSEMBLY__

#ifdef CONFIG_X86_32 #define in_ia32_syscall() true --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -769,30 +769,8 @@ handle_signal(struct ksignal *ksig, stru

static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { - /* - * This function is fundamentally broken as currently - * implemented. - * - * The idea is that we want to trigger a call to the - * restart_block() syscall and that we want in_ia32_syscall(), - * in_x32_syscall(), etc. to match whatever they were in the - * syscall being restarted. We assume that the syscall - * instruction at (regs->ip - 2) matches whatever syscall - * instruction we used to enter in the first place. - * - * The problem is that we can get here when ptrace pokes - * syscall-like values into regs even if we're not in a syscall - * at all. - * - * For now, we maintain historical behavior and guess based on - * stored state. We could do better by saving the actual - * syscall arch in restart_block or (with caveats on x32) by - * checking if regs->ip points to 'int $0x80'. The current - * behavior is incorrect if a tracer has a different bitness - * than the tracee. - */ #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & TS_COMPAT_RESTART) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI

From: zhangyi (F) yi.zhang@huawei.com

commit 6b22489911b726eebbf169caee52fea52013fbdd upstream.

Syzbot report a warning that ext4 may create an empty ea_inode if set an empty extent attribute to a file on the file system which is no free blocks left.

WARNING: CPU: 6 PID: 10667 at fs/ext4/xattr.c:1640 ext4_xattr_set_entry+0x10f8/0x1114 fs/ext4/xattr.c:1640 ... Call trace: ext4_xattr_set_entry+0x10f8/0x1114 fs/ext4/xattr.c:1640 ext4_xattr_block_set+0x1d0/0x1b1c fs/ext4/xattr.c:1942 ext4_xattr_set_handle+0x8a0/0xf1c fs/ext4/xattr.c:2390 ext4_xattr_set+0x120/0x1f0 fs/ext4/xattr.c:2491 ext4_xattr_trusted_set+0x48/0x5c fs/ext4/xattr_trusted.c:37 __vfs_setxattr+0x208/0x23c fs/xattr.c:177 ...

Now, ext4 try to store extent attribute into an external inode if ext4_xattr_block_set() return -ENOSPC, but for the case of store an empty extent attribute, store the extent entry into the extent attribute block is enough. A simple reproduce below.

fallocate test.img -l 1M mkfs.ext4 -F -b 2048 -O ea_inode test.img mount test.img /mnt dd if=/dev/zero of=/mnt/foo bs=2048 count=500 setfattr -n "user.test" /mnt/foo

Reported-by: syzbot+98b881fdd8ebf45ab4ae@syzkaller.appspotmail.com Fixes: 9c6e7853c531 ("ext4: reserve space for xattr entries/names") Cc: stable@kernel.org Signed-off-by: zhangyi (F) yi.zhang@huawei.com Link: https://lore.kernel.org/r/20210305120508.298465-1-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2418,7 +2418,7 @@ retry_inode: * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && - !i.in_inode) { + i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; }

From: Thomas Gleixner tglx@linutronix.de

commit 81e2073c175b887398e5bca6c004efa89983f58d upstream.

With interrupt force threading all device interrupt handlers are invoked from kernel threads. Contrary to hard interrupt context the invocation only disables bottom halfs, but not interrupts. This was an oversight back then because any code like this will have an issue:

thread(irq_A) irq_handler(A) spin_lock(&foo->lock);

interrupt(irq_B) irq_handler(B) spin_lock(&foo->lock);

This has been triggered with networking (NAPI vs. hrtimers) and console drivers where printk() happens from an interrupt which interrupted the force threaded handler.

Now people noticed and started to change the spin_lock() in the handler to spin_lock_irqsave() which affects performance or add IRQF_NOTHREAD to the interrupt request which in turn breaks RT.

Fix the root cause and not the symptom and disable interrupts before invoking the force threaded handler which preserves the regular semantics and the usefulness of the interrupt force threading as a general debugging tool.

For not RT this is not changing much, except that during the execution of the threaded handler interrupts are delayed until the handler returns. Vs. scheduling and softirq processing there is no difference.

For RT kernels there is no issue.

Fixes: 8d32a307e4fa ("genirq: Provide forced interrupt threading") Reported-by: Johan Hovold johan@kernel.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Johan Hovold johan@kernel.org Acked-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Link: https://lore.kernel.org/r/20210317143859.513307808@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/irq/manage.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -916,11 +916,15 @@ irq_forced_thread_fn(struct irq_desc *de irqreturn_t ret;

local_bh_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) + local_irq_disable(); ret = action->thread_fn(action->irq, action->dev_id); if (ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled);

irq_finalize_oneshot(desc, action); + if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) + local_irq_enable(); local_bh_enable(); return ret; }