October 2024 - Linux-stable-mirror

[PATCH v3 12/14] scsi: ufs: exynos: fix hibern8 notify callbacks

by Peter Griffin

v1 of the patch which introduced the ufshcd_vops_hibern8_notify() callback used a bool instead of an enum. In v2 this was updated to an enum based on the review feedback in [1]. ufs-exynos hibernate calls have always been broken upstream as it follows the v1 bool implementation. Link: https://patchwork.kernel.org/project/linux-scsi/patch/001f01d23994$719997c0… [1] Fixes: 55f4b1f73631 ("scsi: ufs: ufs-exynos: Add UFS host support for Exynos SoCs") Signed-off-by: Peter Griffin <peter.griffin(a)linaro.org> Reviewed-by: Tudor Ambarus <tudor.ambarus(a)linaro.org> Cc: stable(a)vger.kernel.org --- v3: Added Link tag, and CC stable, and Reviewed-by (Tudor) --- drivers/ufs/host/ufs-exynos.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c index 5078210b2a5c..9b6c4cfd7665 100644 --- a/drivers/ufs/host/ufs-exynos.c +++ b/drivers/ufs/host/ufs-exynos.c @@ -1526,12 +1526,12 @@ static void exynos_ufs_dev_hw_reset(struct ufs_hba *hba) hci_writel(ufs, 1 << 0, HCI_GPIO_OUT); } -static void exynos_ufs_pre_hibern8(struct ufs_hba *hba, u8 enter) +static void exynos_ufs_pre_hibern8(struct ufs_hba *hba, enum uic_cmd_dme cmd) { struct exynos_ufs *ufs = ufshcd_get_variant(hba); struct exynos_ufs_uic_attr *attr = ufs->drv_data->uic_attr; - if (!enter) { + if (cmd == UIC_CMD_DME_HIBER_EXIT) { if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL) exynos_ufs_disable_auto_ctrl_hcc(ufs); exynos_ufs_ungate_clks(ufs); @@ -1559,11 +1559,11 @@ static void exynos_ufs_pre_hibern8(struct ufs_hba *hba, u8 enter) } } -static void exynos_ufs_post_hibern8(struct ufs_hba *hba, u8 enter) +static void exynos_ufs_post_hibern8(struct ufs_hba *hba, enum uic_cmd_dme cmd) { struct exynos_ufs *ufs = ufshcd_get_variant(hba); - if (!enter) { + if (cmd == UIC_CMD_DME_HIBER_EXIT) { u32 cur_mode = 0; u32 pwrmode; @@ -1582,7 +1582,7 @@ static void exynos_ufs_post_hibern8(struct ufs_hba *hba, u8 enter) if (!(ufs->opts & EXYNOS_UFS_OPT_SKIP_CONNECTION_ESTAB)) exynos_ufs_establish_connt(ufs); - } else { + } else if (cmd == UIC_CMD_DME_HIBER_ENTER) { ufs->entry_hibern8_t = ktime_get(); exynos_ufs_gate_clks(ufs); if (ufs->opts & EXYNOS_UFS_OPT_BROKEN_AUTO_CLK_CTRL) @@ -1669,15 +1669,15 @@ static int exynos_ufs_pwr_change_notify(struct ufs_hba *hba, } static void exynos_ufs_hibern8_notify(struct ufs_hba *hba, - enum uic_cmd_dme enter, + enum uic_cmd_dme cmd, enum ufs_notify_change_status notify) { switch ((u8)notify) { case PRE_CHANGE: - exynos_ufs_pre_hibern8(hba, enter); + exynos_ufs_pre_hibern8(hba, cmd); break; case POST_CHANGE: - exynos_ufs_post_hibern8(hba, enter); + exynos_ufs_post_hibern8(hba, cmd); break; } } -- 2.47.0.163.g1226f6d8fa-goog

1 month, 3 weeks

1
0
0 0

[PATCH v3 04/14] scsi: ufs: exynos: add check inside exynos_ufs_config_smu()

by Peter Griffin

Move the EXYNOS_UFS_OPT_UFSPR_SECURE check inside exynos_ufs_config_smu(). This way all call sites will benefit from the check. This fixes a bug currently in the exynos_ufs_resume() path on gs101 as it calls exynos_ufs_config_smu() and we end up accessing registers that can only be accessed from secure world which results in a serror. Fixes: d11e0a318df8 ("scsi: ufs: exynos: Add support for Tensor gs101 SoC") Signed-off-by: Peter Griffin <peter.griffin(a)linaro.org> Reviewed-by: Tudor Ambarus <tudor.ambarus(a)linaro.org> Cc: stable(a)vger.kernel.org --- v3: CC stable and be more verbose in commit message (Tudor) --- drivers/ufs/host/ufs-exynos.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/ufs/host/ufs-exynos.c b/drivers/ufs/host/ufs-exynos.c index 33de7ff747a2..f4454e89040f 100644 --- a/drivers/ufs/host/ufs-exynos.c +++ b/drivers/ufs/host/ufs-exynos.c @@ -719,6 +719,9 @@ static void exynos_ufs_config_smu(struct exynos_ufs *ufs) { u32 reg, val; + if (ufs->opts & EXYNOS_UFS_OPT_UFSPR_SECURE) + return; + exynos_ufs_disable_auto_ctrl_hcc_save(ufs, &val); /* make encryption disabled by default */ @@ -1454,8 +1457,8 @@ static int exynos_ufs_init(struct ufs_hba *hba) if (ret) goto out; exynos_ufs_specify_phy_time_attr(ufs); - if (!(ufs->opts & EXYNOS_UFS_OPT_UFSPR_SECURE)) - exynos_ufs_config_smu(ufs); + + exynos_ufs_config_smu(ufs); hba->host->dma_alignment = DATA_UNIT_SIZE - 1; return 0; -- 2.47.0.163.g1226f6d8fa-goog

1 month, 3 weeks

1
0
0 0

[PATCH v3] ext4: prevent data-race that occur when read/write ext4_group_desc structure members

by Jeongjun Park

Currently, data-race like [1] occur in fs/ext4/ialloc.c find_group_other() and find_group_orlov() read *_lo, *_hi with ext4_free_inodes_count without additional locking. This can cause data-race, but since the lock is held for most writes and free inodes value is generally not a problem even if it is incorrect, it is more appropriate to use READ_ONCE()/WRITE_ONCE() than to add locking. [1] ================================================================== BUG: KCSAN: data-race in ext4_free_inodes_count / ext4_free_inodes_set write to 0xffff88810404300e of 2 bytes by task 6254 on cpu 1: ext4_free_inodes_set+0x1f/0x80 fs/ext4/super.c:405 __ext4_new_inode+0x15ca/0x2200 fs/ext4/ialloc.c:1216 ext4_symlink+0x242/0x5a0 fs/ext4/namei.c:3391 vfs_symlink+0xca/0x1d0 fs/namei.c:4615 do_symlinkat+0xe3/0x340 fs/namei.c:4641 __do_sys_symlinkat fs/namei.c:4657 [inline] __se_sys_symlinkat fs/namei.c:4654 [inline] __x64_sys_symlinkat+0x5e/0x70 fs/namei.c:4654 x64_sys_call+0x1dda/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:267 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x54/0x120 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x76/0x7e read to 0xffff88810404300e of 2 bytes by task 6257 on cpu 0: ext4_free_inodes_count+0x1c/0x80 fs/ext4/super.c:349 find_group_other fs/ext4/ialloc.c:594 [inline] __ext4_new_inode+0x6ec/0x2200 fs/ext4/ialloc.c:1017 ext4_symlink+0x242/0x5a0 fs/ext4/namei.c:3391 vfs_symlink+0xca/0x1d0 fs/namei.c:4615 do_symlinkat+0xe3/0x340 fs/namei.c:4641 __do_sys_symlinkat fs/namei.c:4657 [inline] __se_sys_symlinkat fs/namei.c:4654 [inline] __x64_sys_symlinkat+0x5e/0x70 fs/namei.c:4654 x64_sys_call+0x1dda/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:267 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x54/0x120 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x76/0x7e value changed: 0x185c -> 0x185b Cc: <stable(a)vger.kernel.org> Fixes: ac27a0ec112a ("[PATCH] ext4: initial copy of files from ext3") Signed-off-by: Jeongjun Park <aha310510(a)gmail.com> --- fs/ext4/super.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 16a4ce704460..8337c4999f90 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -346,9 +346,9 @@ __u32 ext4_free_group_clusters(struct super_block *sb, __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { - return le16_to_cpu(bg->bg_free_inodes_count_lo) | + return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? - (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0); + (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, @@ -402,9 +402,9 @@ void ext4_free_group_clusters_set(struct super_block *sb, void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { - bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count); + WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count)); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) - bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16); + WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16)); } void ext4_used_dirs_set(struct super_block *sb, --

1 month, 3 weeks

3
2
0 0

[PATCH] vp_vdpa: fix id_table array not null terminated error

by Xiaoguang Wang

Allocate one extra virtio_device_id as null terminator, otherwise vdpa_mgmtdev_get_classes() may iterate multiple times and visit undefined memory. Fixes: ffbda8e9df10 ("vdpa/vp_vdpa : add vdpa tool support in vp_vdpa") Cc: stable(a)vger.kernel.org Signed-off-by: Xiaoguang Wang <lege.wang(a)jaguarmicro.com> --- drivers/vdpa/virtio_pci/vp_vdpa.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index ac4ab22f7d8b..74cc4ed77cc4 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -612,7 +612,11 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto mdev_err; } - mdev_id = kzalloc(sizeof(struct virtio_device_id), GFP_KERNEL); + /* + * id_table should be a null terminated array. + * See vdpa_mgmtdev_get_classes(). + */ + mdev_id = kzalloc(sizeof(struct virtio_device_id) * 2, GFP_KERNEL); if (!mdev_id) { err = -ENOMEM; goto mdev_id_err; -- 2.40.1

1 month, 3 weeks

3
2
0 0

[PATCH] efistub/tpm: Use ACPI reclaim memory for event log to avoid corruption

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> The TPM event log table is a Linux specific construct, where the data produced by the GetEventLog() boot service is cached in memory, and passed on to the OS using a EFI configuration table. The use of EFI_LOADER_DATA here results in the region being left unreserved in the E820 memory map constructed by the EFI stub, and this is the memory description that is passed on to the incoming kernel by kexec, which is therefore unaware that the region should be reserved. Even though the utility of the TPM2 event log after a kexec is questionable, any corruption might send the parsing code off into the weeds and crash the kernel. So let's use EFI_ACPI_RECLAIM_MEMORY instead, which is always treated as reserved by the E820 conversion logic. Cc: <stable(a)vger.kernel.org> Reported-by: Breno Leitao <leitao(a)debian.org> Tested-by: Usama Arif <usamaarif642(a)gmail.com> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- drivers/firmware/efi/libstub/tpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index df3182f2e63a..1fd6823248ab 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -96,7 +96,7 @@ static void efi_retrieve_tcg2_eventlog(int version, efi_physical_addr_t log_loca } /* Allocate space for the logs and copy them. */ - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*log_tbl) + log_size, (void **)&log_tbl); if (status != EFI_SUCCESS) { -- 2.46.0.662.g92d0881bb0-goog

1 month, 3 weeks

7
19
0 0

[PATCH 6.6] Revert "selftests/bpf: Implement get_hw_ring_size function to retrieve current and max interface size"

by Pu Lehui

From: Pu Lehui <pulehui(a)huawei.com> This reverts commit c8c590f07ad7ffaa6ef11e90b81202212077497b which is commit 90a695c3d31e1c9f0adb8c4c80028ed4ea7ed5ab upstream. Commit c8c590f07ad7 ("selftests/bpf: Implement get_hw_ring_size function to retrieve current and max interface size") will cause the following bpf selftests compilation error in the 6.6 stable branch, and it is not the Stable-dep-of of commit 103c0431c7fb ("selftests/bpf: Drop unneeded error.h includes"). So let's revert commit c8c590f07ad7 to fix this compilation error. ./network_helpers.h:66:43: error: 'struct ethtool_ringparam' declared inside parameter list will not be visible outside of this definition or declaration [-Werror] 66 | int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param); Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- tools/testing/selftests/bpf/network_helpers.c | 24 ------------------- tools/testing/selftests/bpf/network_helpers.h | 4 ---- .../selftests/bpf/prog_tests/flow_dissector.c | 1 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 14 +++++++++++ 4 files changed, 15 insertions(+), 28 deletions(-) diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index d2acc8875212..0877b60ec81f 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -465,27 +465,3 @@ int get_socket_local_port(int sock_fd) return -1; } - -int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param) -{ - struct ifreq ifr = {0}; - int sockfd, err; - - sockfd = socket(AF_INET, SOCK_DGRAM, 0); - if (sockfd < 0) - return -errno; - - memcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); - - ring_param->cmd = ETHTOOL_GRINGPARAM; - ifr.ifr_data = (char *)ring_param; - - if (ioctl(sockfd, SIOCETHTOOL, &ifr) < 0) { - err = errno; - close(sockfd); - return -err; - } - - close(sockfd); - return 0; -} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 11cbe194769b..5eccc67d1a99 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -9,11 +9,8 @@ typedef __u16 __sum16; #include <linux/if_packet.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/ethtool.h> -#include <linux/sockios.h> #include <netinet/tcp.h> #include <bpf/bpf_endian.h> -#include <net/if.h> #define MAGIC_VAL 0x1234 #define NUM_ITER 100000 @@ -63,7 +60,6 @@ int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); int get_socket_local_port(int sock_fd); -int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param); struct nstoken; /** diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 3171047414a7..b81046806579 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -2,6 +2,7 @@ #define _GNU_SOURCE #include <test_progs.h> #include <network_helpers.h> +#include <linux/if.h> #include <linux/if_tun.h> #include <sys/uio.h> diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 79f2da8f6ead..adb77c1a6a74 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -288,6 +288,20 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t return 0; } +struct ethtool_channels { + __u32 cmd; + __u32 max_rx; + __u32 max_tx; + __u32 max_other; + __u32 max_combined; + __u32 rx_count; + __u32 tx_count; + __u32 other_count; + __u32 combined_count; +}; + +#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */ + static int rxq_num(const char *ifname) { struct ethtool_channels ch = { -- 2.34.1

1 month, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] mm-mmap-limit-thp-aligment-of-anonymous-mappings-to-pmd-aligned-sizes.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm, mmap: limit THP alignment of anonymous mappings to PMD-aligned sizes has been removed from the -mm tree. Its filename was mm-mmap-limit-thp-aligment-of-anonymous-mappings-to-pmd-aligned-sizes.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Vlastimil Babka <vbabka(a)suse.cz> Subject: mm, mmap: limit THP alignment of anonymous mappings to PMD-aligned sizes Date: Thu, 24 Oct 2024 17:12:29 +0200 Since commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") a mmap() of anonymous memory without a specific address hint and of at least PMD_SIZE will be aligned to PMD so that it can benefit from a THP backing page. However this change has been shown to regress some workloads significantly. [1] reports regressions in various spec benchmarks, with up to 600% slowdown of the cactusBSSN benchmark on some platforms. The benchmark seems to create many mappings of 4632kB, which would have merged to a large THP-backed area before commit efa7df3e3bb5 and now they are fragmented to multiple areas each aligned to PMD boundary with gaps between. The regression then seems to be caused mainly due to the benchmark's memory access pattern suffering from TLB or cache aliasing due to the aligned boundaries of the individual areas. Another known regression bisected to commit efa7df3e3bb5 is darktable [2] [3] and early testing suggests this patch fixes the regression there as well. To fix the regression but still try to benefit from THP-friendly anonymous mapping alignment, add a condition that the size of the mapping must be a multiple of PMD size instead of at least PMD size. In case of many odd-sized mapping like the cactusBSSN creates, those will stop being aligned and with gaps between, and instead naturally merge again. Link: https://lkml.kernel.org/r/20241024151228.101841-2-vbabka@suse.cz Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") Signed-off-by: Vlastimil Babka <vbabka(a)suse.cz> Reported-by: Michael Matz <matz(a)suse.de> Debugged-by: Gabriel Krisman Bertazi <gabriel(a)krisman.be> Closes: https://bugzilla.suse.com/show_bug.cgi?id=1229012 [1] Reported-by: Matthias Bodenbinder <matthias(a)bodenbinder.de> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219366 [2] Closes: https://lore.kernel.org/all/2050f0d4-57b0-481d-bab8-05e8d48fed0c@leemhuis.i… [3] Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Jann Horn <jannh(a)google.com> Cc: Liam R. Howlett <Liam.Howlett(a)Oracle.com> Cc: Petr Tesarik <ptesarik(a)suse.com> Cc: Thorsten Leemhuis <regressions(a)leemhuis.info> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/mmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/mm/mmap.c~mm-mmap-limit-thp-aligment-of-anonymous-mappings-to-pmd-aligned-sizes +++ a/mm/mmap.c @@ -900,7 +900,8 @@ __get_unmapped_area(struct file *file, u if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); _ Patches currently in -mm which might be from vbabka(a)suse.cz are

1 month, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] mm-shrinker-avoid-memleak-in-alloc_shrinker_info.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: shrinker: avoid memleak in alloc_shrinker_info has been removed from the -mm tree. Its filename was mm-shrinker-avoid-memleak-in-alloc_shrinker_info.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Chen Ridong <chenridong(a)huawei.com> Subject: mm: shrinker: avoid memleak in alloc_shrinker_info Date: Fri, 25 Oct 2024 06:09:42 +0000 A memleak was found as below: unreferenced object 0xffff8881010d2a80 (size 32): comm "mkdir", pid 1559, jiffies 4294932666 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 @............... backtrace (crc 2e7ef6fa): [<ffffffff81372754>] __kmalloc_node_noprof+0x394/0x470 [<ffffffff813024ab>] alloc_shrinker_info+0x7b/0x1a0 [<ffffffff813b526a>] mem_cgroup_css_online+0x11a/0x3b0 [<ffffffff81198dd9>] online_css+0x29/0xa0 [<ffffffff811a243d>] cgroup_apply_control_enable+0x20d/0x360 [<ffffffff811a5728>] cgroup_mkdir+0x168/0x5f0 [<ffffffff8148543e>] kernfs_iop_mkdir+0x5e/0x90 [<ffffffff813dbb24>] vfs_mkdir+0x144/0x220 [<ffffffff813e1c97>] do_mkdirat+0x87/0x130 [<ffffffff813e1de9>] __x64_sys_mkdir+0x49/0x70 [<ffffffff81f8c928>] do_syscall_64+0x68/0x140 [<ffffffff8200012f>] entry_SYSCALL_64_after_hwframe+0x76/0x7e alloc_shrinker_info(), when shrinker_unit_alloc() returns an errer, the info won't be freed. Just fix it. Link: https://lkml.kernel.org/r/20241025060942.1049263-1-chenridong@huaweicloud.c… Fixes: 307bececcd12 ("mm: shrinker: add a secondary array for shrinker_info::{map, nr_deferred}") Signed-off-by: Chen Ridong <chenridong(a)huawei.com> Acked-by: Qi Zheng <zhengqi.arch(a)bytedance.com> Acked-by: Roman Gushchin <roman.gushchin(a)linux.dev> Acked-by: Vlastimil Babka <vbabka(a)suse.cz> Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Reviewed-by: Dave Chinner <dchinner(a)redhat.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Wang Weiyang <wangweiyang2(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/shrinker.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) --- a/mm/shrinker.c~mm-shrinker-avoid-memleak-in-alloc_shrinker_info +++ a/mm/shrinker.c @@ -76,19 +76,21 @@ void free_shrinker_info(struct mem_cgrou int alloc_shrinker_info(struct mem_cgroup *memcg) { - struct shrinker_info *info; int nid, ret = 0; int array_size = 0; mutex_lock(&shrinker_mutex); array_size = shrinker_unit_size(shrinker_nr_max); for_each_node(nid) { - info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); + struct shrinker_info *info = kvzalloc_node(sizeof(*info) + array_size, + GFP_KERNEL, nid); if (!info) goto err; info->map_nr_max = shrinker_nr_max; - if (shrinker_unit_alloc(info, NULL, nid)) + if (shrinker_unit_alloc(info, NULL, nid)) { + kvfree(info); goto err; + } rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } mutex_unlock(&shrinker_mutex); _ Patches currently in -mm which might be from chenridong(a)huawei.com are

1 month, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] vmscanmigrate-fix-double-decrement-on-node-stats-when-demoting-pages.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: vmscan,migrate: fix page count imbalance on node stats when demoting pages has been removed from the -mm tree. Its filename was vmscanmigrate-fix-double-decrement-on-node-stats-when-demoting-pages.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Gregory Price <gourry(a)gourry.net> Subject: vmscan,migrate: fix page count imbalance on node stats when demoting pages Date: Fri, 25 Oct 2024 10:17:24 -0400 When numa balancing is enabled with demotion, vmscan will call migrate_pages when shrinking LRUs. migrate_pages will decrement the the node's isolated page count, leading to an imbalanced count when invoked from (MG)LRU code. The result is dmesg output like such: $ cat /proc/sys/vm/stat_refresh [77383.088417] vmstat_refresh: nr_isolated_anon -103212 [77383.088417] vmstat_refresh: nr_isolated_file -899642 This negative value may impact compaction and reclaim throttling. The following path produces the decrement: shrink_folio_list demote_folio_list migrate_pages migrate_pages_batch migrate_folio_move migrate_folio_done mod_node_page_state(-ve) <- decrement This path happens for SUCCESSFUL migrations, not failures. Typically callers to migrate_pages are required to handle putback/accounting for failures, but this is already handled in the shrink code. When accounting for migrations, instead do not decrement the count when the migration reason is MR_DEMOTION. As of v6.11, this demotion logic is the only source of MR_DEMOTION. Link: https://lkml.kernel.org/r/20241025141724.17927-1-gourry@gourry.net Fixes: 26aa2d199d6f ("mm/migrate: demote pages during reclaim") Signed-off-by: Gregory Price <gourry(a)gourry.net> Reviewed-by: Yang Shi <shy828301(a)gmail.com> Reviewed-by: Davidlohr Bueso <dave(a)stgolabs.net> Reviewed-by: Shakeel Butt <shakeel.butt(a)linux.dev> Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Wei Xu <weixugc(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/migrate.c~vmscanmigrate-fix-double-decrement-on-node-stats-when-demoting-pages +++ a/mm/migrate.c @@ -1178,7 +1178,7 @@ static void migrate_folio_done(struct fo * not accounted to NR_ISOLATED_*. They can be recognized * as __folio_test_movable */ - if (likely(!__folio_test_movable(src))) + if (likely(!__folio_test_movable(src)) && reason != MR_DEMOTION) mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + folio_is_file_lru(src), -folio_nr_pages(src)); _ Patches currently in -mm which might be from gourry(a)gourry.net are

1 month, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats has been removed from the -mm tree. Its filename was mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats Date: Sat, 19 Oct 2024 01:29:38 +0000 Patch series "mm: multi-gen LRU: Have secondary MMUs participate in MM_WALK". Today, the MM_WALK capability causes MGLRU to clear the young bit from PMDs and PTEs during the page table walk before eviction, but MGLRU does not call the clear_young() MMU notifier in this case. By not calling this notifier, the MM walk takes less time/CPU, but it causes pages that are accessed mostly through KVM / secondary MMUs to appear younger than they should be. We do call the clear_young() notifier today, but only when attempting to evict the page, so we end up clearing young/accessed information less frequently for secondary MMUs than for mm PTEs, and therefore they appear younger and are less likely to be evicted. Therefore, memory that is *not* being accessed mostly by KVM will be evicted *more* frequently, worsening performance. ChromeOS observed a tab-open latency regression when enabling MGLRU with a setup that involved running a VM: Tab-open latency histogram (ms) Version p50 mean p95 p99 max base 1315 1198 2347 3454 10319 mglru 2559 1311 7399 12060 43758 fix 1119 926 2470 4211 6947 This series replaces the final non-selftest patchs from this series[1], which introduced a similar change (and a new MMU notifier) with KVM optimizations. I'll send a separate series (to Sean and Paolo) for the KVM optimizations. This series also makes proactive reclaim with MGLRU possible for KVM memory. I have verified that this functions correctly with the selftest from [1], but given that that test is a KVM selftest, I'll send it with the rest of the KVM optimizations later. Andrew, let me know if you'd like to take the test now anyway. [1]: https://lore.kernel.org/linux-mm/20240926013506.860253-18-jthoughton@google… This patch (of 2): The removed stats, MM_LEAF_OLD and MM_NONLEAF_TOTAL, are not very helpful and become more complicated to properly compute when adding test/clear_young() notifiers in MGLRU's mm walk. Link: https://lkml.kernel.org/r/20241019012940.3656292-1-jthoughton@google.com Link: https://lkml.kernel.org/r/20241019012940.3656292-2-jthoughton@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Signed-off-by: James Houghton <jthoughton(a)google.com> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Cc: David Rientjes <rientjes(a)google.com> Cc: David Stevens <stevensd(a)google.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Wei Xu <weixugc(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 2 -- mm/vmscan.c | 14 +++++--------- 2 files changed, 5 insertions(+), 11 deletions(-) --- a/include/linux/mmzone.h~mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats +++ a/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS --- a/mm/vmscan.c~mm-multi-gen-lru-remove-mm_leaf_old-and-mm_nonleaf_total-stats +++ a/mm/vmscan.c @@ -3399,7 +3399,6 @@ restart: continue; if (!pte_young(ptent)) { - walk->mm_stats[MM_LEAF_OLD]++; continue; } @@ -3552,7 +3551,6 @@ restart: walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { - walk->mm_stats[MM_LEAF_OLD]++; continue; } @@ -3564,8 +3562,6 @@ restart: continue; } - walk->mm_stats[MM_NONLEAF_TOTAL]++; - if (!walk->force_scan && should_clear_pmd_young()) { if (!pmd_young(val)) continue; @@ -5254,11 +5250,11 @@ static void lru_gen_seq_show_full(struct for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { - const char *s = " "; + const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { - s = "RT "; + s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { @@ -5280,14 +5276,14 @@ static void lru_gen_seq_show_full(struct seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { - const char *s = " "; + const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { - s = "LOYNFA"; + s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { - s = "loynfa"; + s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-page_alloc-keep-track-of-free-highatomic.patch

1 month, 3 weeks

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024