From 71a5849aedaa9ea028fc51ee74576cad61954743 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 29 Sep 2023 21:11:57 +0000 Subject: mm: Change mmap_rnd_bits_max to __ro_after_init Allow mmap_rnd_bits_max to be updated on architectures that determine virtual address space size at runtime instead of relying on Kconfig options by changing it from const to __ro_after_init. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Reviewed-by: Palmer Dabbelt Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230929211155.3910949-5-samitolvanen@google.com Signed-off-by: Palmer Dabbelt --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index f5a97dec5169..2488c0c5a288 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -86,7 +86,7 @@ extern int sysctl_legacy_va_layout; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; -extern const int mmap_rnd_bits_max; +extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS -- cgit v1.2.3 From cb4ede926134a65bc3bf90ed58dace8451d7e759 Mon Sep 17 00:00:00 2001 From: Xiao Wang Date: Sun, 12 Nov 2023 17:44:21 +0800 Subject: riscv: Avoid code duplication with generic bitops implementation There's code duplication between the fallback implementation for bitops __ffs/__fls/ffs/fls API and the generic C implementation in include/asm-generic/bitops/. To avoid this duplication, this patch renames the generic C implementation by adding a "generic_" prefix to them, then we can use these generic APIs as fallback. Suggested-by: Geert Uytterhoeven Signed-off-by: Xiao Wang Reviewed-by: Charlie Jenkins Link: https://lore.kernel.org/r/20231112094421.4014931-1-xiao.w.wang@intel.com Signed-off-by: Palmer Dabbelt --- include/asm-generic/bitops/__ffs.h | 8 ++++++-- include/asm-generic/bitops/__fls.h | 8 ++++++-- include/asm-generic/bitops/ffs.h | 8 ++++++-- include/asm-generic/bitops/fls.h | 8 ++++++-- 4 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h index 39e56e1c7203..446fea6dda78 100644 --- a/include/asm-generic/bitops/__ffs.h +++ b/include/asm-generic/bitops/__ffs.h @@ -5,12 +5,12 @@ #include /** - * __ffs - find first bit in word. + * generic___ffs - find first bit in word. * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __ffs(unsigned long word) +static __always_inline unsigned long generic___ffs(unsigned long word) { int num = 0; @@ -41,4 +41,8 @@ static __always_inline unsigned long __ffs(unsigned long word) return num; } +#ifndef __HAVE_ARCH___FFS +#define __ffs(word) generic___ffs(word) +#endif + #endif /* _ASM_GENERIC_BITOPS___FFS_H_ */ diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h index 03f721a8a2b1..54ccccf96e21 100644 --- a/include/asm-generic/bitops/__fls.h +++ b/include/asm-generic/bitops/__fls.h @@ -5,12 +5,12 @@ #include /** - * __fls - find last (most-significant) set bit in a long word + * generic___fls - find last (most-significant) set bit in a long word * @word: the word to search * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __fls(unsigned long word) +static __always_inline unsigned long generic___fls(unsigned long word) { int num = BITS_PER_LONG - 1; @@ -41,4 +41,8 @@ static __always_inline unsigned long __fls(unsigned long word) return num; } +#ifndef __HAVE_ARCH___FLS +#define __fls(word) generic___fls(word) +#endif + #endif /* _ASM_GENERIC_BITOPS___FLS_H_ */ diff --git a/include/asm-generic/bitops/ffs.h b/include/asm-generic/bitops/ffs.h index 323fd5d6ae26..4c43f242daeb 100644 --- a/include/asm-generic/bitops/ffs.h +++ b/include/asm-generic/bitops/ffs.h @@ -3,14 +3,14 @@ #define _ASM_GENERIC_BITOPS_FFS_H_ /** - * ffs - find first bit set + * generic_ffs - find first bit set * @x: the word to search * * This is defined the same way as * the libc and compiler builtin ffs routines, therefore * differs in spirit from ffz (man ffs). */ -static inline int ffs(int x) +static inline int generic_ffs(int x) { int r = 1; @@ -39,4 +39,8 @@ static inline int ffs(int x) return r; } +#ifndef __HAVE_ARCH_FFS +#define ffs(x) generic_ffs(x) +#endif + #endif /* _ASM_GENERIC_BITOPS_FFS_H_ */ diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h index b168bb10e1be..26f3ce1dd6e4 100644 --- a/include/asm-generic/bitops/fls.h +++ b/include/asm-generic/bitops/fls.h @@ -3,14 +3,14 @@ #define _ASM_GENERIC_BITOPS_FLS_H_ /** - * fls - find last (most-significant) bit set + * generic_fls - find last (most-significant) bit set * @x: the word to search * * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int fls(unsigned int x) +static __always_inline int generic_fls(unsigned int x) { int r = 32; @@ -39,4 +39,8 @@ static __always_inline int fls(unsigned int x) return r; } +#ifndef __HAVE_ARCH_FLS +#define fls(x) generic_fls(x) +#endif + #endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ -- cgit v1.2.3 From 4ff4c745a16c4c151a71863420811e7f406c3ec2 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Wed, 31 Jan 2024 15:49:35 +0100 Subject: locking: Introduce prepare_sync_core_cmd() Introduce an architecture function that architectures can use to set up ("prepare") SYNC_CORE commands. The function will be used by RISC-V to update its "deferred icache- flush" data structures (icache_stale_mask). Architectures defining prepare_sync_core_cmd() static inline need to select ARCH_HAS_PREPARE_SYNC_CORE_CMD. Suggested-by: Mathieu Desnoyers Signed-off-by: Andrea Parri Reviewed-by: Mathieu Desnoyers Link: https://lore.kernel.org/r/20240131144936.29190-4-parri.andrea@gmail.com Signed-off-by: Palmer Dabbelt --- include/linux/sync_core.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sync_core.h b/include/linux/sync_core.h index 013da4b8b327..67bb9794b875 100644 --- a/include/linux/sync_core.h +++ b/include/linux/sync_core.h @@ -17,5 +17,19 @@ static inline void sync_core_before_usermode(void) } #endif -#endif /* _LINUX_SYNC_CORE_H */ +#ifdef CONFIG_ARCH_HAS_PREPARE_SYNC_CORE_CMD +#include +#else +/* + * This is a dummy prepare_sync_core_cmd() implementation that can be used on + * all architectures which provide unconditional core serializing instructions + * in switch_mm(). + * If your architecture doesn't provide such core serializing instructions in + * switch_mm(), you may need to write your own functions. + */ +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ +} +#endif +#endif /* _LINUX_SYNC_CORE_H */ -- cgit v1.2.3 From 7e84c961b2eb062d2f47037dcca52dcd1d3615b5 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Tue, 19 Dec 2023 02:33:24 +0000 Subject: mtd: ubi: introduce pre-removal notification for UBI volumes Introduce a new notification type UBI_VOLUME_SHUTDOWN to inform users that a volume is just about to be removed. This is needed because users (such as the NVMEM subsystem) expect that at the time their removal function is called, the parenting device is still available (for removal of sysfs nodes, for example, in case of NVMEM which otherwise WARNs on volume removal). Signed-off-by: Daniel Golle Signed-off-by: Richard Weinberger --- include/linux/mtd/ubi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index a529347fd75b..562f92504f2b 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -192,6 +192,7 @@ struct ubi_device_info { * or a volume was removed) * @UBI_VOLUME_RESIZED: a volume has been re-sized * @UBI_VOLUME_RENAMED: a volume has been re-named + * @UBI_VOLUME_SHUTDOWN: a volume is going to removed, shutdown users * @UBI_VOLUME_UPDATED: data has been written to a volume * * These constants define which type of event has happened when a volume @@ -202,6 +203,7 @@ enum { UBI_VOLUME_REMOVED, UBI_VOLUME_RESIZED, UBI_VOLUME_RENAMED, + UBI_VOLUME_SHUTDOWN, UBI_VOLUME_UPDATED, }; -- cgit v1.2.3 From 96b171d6dba6a66c63312f35e3ac6465b2c2ca94 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 30 Jan 2024 13:48:35 -0800 Subject: scsi: core: Query the Block Limits Extension VPD page Parse the Reduced Stream Control Supported (RSCS) bit from the block limits extension VPD page. The RSCS bit is defined in SBC-5 r05 (https://www.t10.org/cgi-bin/ac.pl?t=f&f=sbc5r05.pdf). Reviewed-by: Avri Altman Reviewed-by: Daejun Park Cc: Martin K. Petersen Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240130214911.1863909-10-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 5ec1e71a09de..f670b55d803a 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -153,6 +153,7 @@ struct scsi_device { struct scsi_vpd __rcu *vpd_pgb0; struct scsi_vpd __rcu *vpd_pgb1; struct scsi_vpd __rcu *vpd_pgb2; + struct scsi_vpd __rcu *vpd_pgb7; struct scsi_target *sdev_target; -- cgit v1.2.3 From 4977c0f4523e1d6c87df4eedceb33d38f055c5fb Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 30 Jan 2024 13:48:36 -0800 Subject: scsi: scsi_proto: Add structures and constants related to I/O groups and streams Prepare for adding code that will query the I/O advice hints group descriptors and for adding code that will retrieve the stream status. Cc: Martin K. Petersen Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240130214911.1863909-11-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- include/scsi/scsi_proto.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index 07d65c1f59db..843106e1109f 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -10,6 +10,7 @@ #ifndef _SCSI_PROTO_H_ #define _SCSI_PROTO_H_ +#include #include /* @@ -126,6 +127,7 @@ #define SAI_READ_CAPACITY_16 0x10 #define SAI_GET_LBA_STATUS 0x12 #define SAI_REPORT_REFERRALS 0x13 +#define SAI_GET_STREAM_STATUS 0x16 /* values for maintenance in */ #define MI_REPORT_IDENTIFYING_INFORMATION 0x05 #define MI_REPORT_TARGET_PGS 0x0a @@ -275,6 +277,82 @@ struct scsi_lun { __u8 scsi_lun[8]; }; +/* SBC-5 IO advice hints group descriptor */ +struct scsi_io_group_descriptor { +#if defined(__BIG_ENDIAN) + u8 io_advice_hints_mode: 2; + u8 reserved1: 3; + u8 st_enble: 1; + u8 cs_enble: 1; + u8 ic_enable: 1; +#elif defined(__LITTLE_ENDIAN) + u8 ic_enable: 1; + u8 cs_enble: 1; + u8 st_enble: 1; + u8 reserved1: 3; + u8 io_advice_hints_mode: 2; +#else +#error +#endif + u8 reserved2[3]; + /* Logical block markup descriptor */ +#if defined(__BIG_ENDIAN) + u8 acdlu: 1; + u8 reserved3: 1; + u8 rlbsr: 2; + u8 lbm_descriptor_type: 4; +#elif defined(__LITTLE_ENDIAN) + u8 lbm_descriptor_type: 4; + u8 rlbsr: 2; + u8 reserved3: 1; + u8 acdlu: 1; +#else +#error +#endif + u8 params[2]; + u8 reserved4; + u8 reserved5[8]; +}; + +static_assert(sizeof(struct scsi_io_group_descriptor) == 16); + +/* SCSI stream status descriptor */ +struct scsi_stream_status { +#if defined(__BIG_ENDIAN) + u8 perm: 1; + u8 reserved1: 7; +#elif defined(__LITTLE_ENDIAN) + u8 reserved1: 7; + u8 perm: 1; +#else +#error +#endif + u8 reserved2; + __be16 stream_identifier; +#if defined(__BIG_ENDIAN) + u8 reserved3: 2; + u8 rel_lifetime: 6; +#elif defined(__LITTLE_ENDIAN) + u8 rel_lifetime: 6; + u8 reserved3: 2; +#else +#error +#endif + u8 reserved4[3]; +}; + +static_assert(sizeof(struct scsi_stream_status) == 8); + +/* GET STREAM STATUS parameter data */ +struct scsi_stream_status_header { + __be32 len; /* length in bytes of stream_status[] array. */ + u16 reserved; + __be16 number_of_open_streams; + DECLARE_FLEX_ARRAY(struct scsi_stream_status, stream_status); +}; + +static_assert(sizeof(struct scsi_stream_status_header) == 8); + /* SPC asymmetric access states */ #define SCSI_ACCESS_STATE_OPTIMAL 0x00 #define SCSI_ACCESS_STATE_ACTIVE 0x01 -- cgit v1.2.3 From 6b6ca096115e5b7a85e8313f4e68a72d52db91b3 Mon Sep 17 00:00:00 2001 From: "Ricardo B. Marliere" Date: Tue, 5 Mar 2024 15:22:28 -0300 Subject: rtc: class: make rtc_class constant Since commit 43a7206b0963 ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the rtc_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman Suggested-by: Greg Kroah-Hartman Signed-off-by: Ricardo B. Marliere Link: https://lore.kernel.org/r/20240305-class_cleanup-abelloni-v1-1-944c026137c8@marliere.net Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 5f8e438a0312..3f4d315aaec9 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -42,7 +42,7 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) #include #include -extern struct class *rtc_class; +extern const struct class rtc_class; /* * For these RTC methods the device parameter is the physical device -- cgit v1.2.3 From cb8a2ef0848ca80d67d6d56e2df757cfdf6b3355 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Mon, 11 Mar 2024 22:23:47 +0800 Subject: LoongArch: Add ORC stack unwinder support The kernel CONFIG_UNWINDER_ORC option enables the ORC unwinder, which is similar in concept to a DWARF unwinder. The difference is that the format of the ORC data is much simpler than DWARF, which in turn allows the ORC unwinder to be much simpler and faster. The ORC data consists of unwind tables which are generated by objtool. After analyzing all the code paths of a .o file, it determines information about the stack state at each instruction address in the file and outputs that information to the .orc_unwind and .orc_unwind_ip sections. The per-object ORC sections are combined at link time and are sorted and post-processed at boot time. The unwinder uses the resulting data to correlate instruction addresses with their stack states at run time. Most of the logic are similar with x86, in order to get ra info before ra is saved into stack, add ra_reg and ra_offset into orc_entry. At the same time, modify some arch-specific code to silence the objtool warnings. Co-developed-by: Jinyang He Signed-off-by: Jinyang He Co-developed-by: Youling Tang Signed-off-by: Youling Tang Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- include/linux/compiler.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index bb1339c7057b..39f2d4a05208 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -116,6 +116,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define __stringify_label(n) #n +#define __annotate_reachable(c) ({ \ + asm volatile(__stringify_label(c) ":\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long " __stringify_label(c) "b - .\n\t" \ + ".popsection\n\t"); \ +}) +#define annotate_reachable() __annotate_reachable(__COUNTER__) + #define __annotate_unreachable(c) ({ \ asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ @@ -128,6 +136,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __annotate_jump_table __section(".rodata..c_jump_table") #else /* !CONFIG_OBJTOOL */ +#define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ -- cgit v1.2.3 From 7af03e688792293ba33149fb8df619a8dff90e80 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 8 Mar 2024 18:03:39 +0200 Subject: drm/probe-helper: warn about negative .get_modes() The .get_modes() callback is supposed to return the number of modes, never a negative error code. If a negative value is returned, it'll just be interpreted as a negative count, and added to previous calculations. Document the rules, but handle the negative values gracefully with an error message. Cc: stable@vger.kernel.org Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/50208c866facc33226a3c77b82bb96aeef8ef310.1709913674.git.jani.nikula@intel.com Signed-off-by: Jani Nikula --- include/drm/drm_modeset_helper_vtables.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index 881b03e4dc28..9ed42469540e 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -898,7 +898,8 @@ struct drm_connector_helper_funcs { * * RETURNS: * - * The number of modes added by calling drm_mode_probed_add(). + * The number of modes added by calling drm_mode_probed_add(). Return 0 + * on failures (no modes) instead of negative error codes. */ int (*get_modes)(struct drm_connector *connector); -- cgit v1.2.3 From 6d5501d59cf659651e100fc4c5617d444c22ba74 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Sun, 10 Mar 2024 01:38:43 +0200 Subject: drm/bridge: correct DRM_BRIDGE_OP_EDID documentation While the commit d807ad80d811 ("drm/bridge: add ->edid_read hook and drm_bridge_edid_read()") and the commit 27b8f91c08d9 ("drm/bridge: remove ->get_edid callback") replaced ->get_edid() callback with the ->edid_read(), they failed to update documentation. Fix the drm_bridge docs to point to edid_read(). Fixes: 27b8f91c08d9 ("drm/bridge: remove ->get_edid callback") Reviewed-by: Jani Nikula Reviewed-by: Neil Armstrong Signed-off-by: Dmitry Baryshkov Link: https://patchwork.freedesktop.org/patch/msgid/20240310-drm-bridge-fix-docs-v1-1-70d3d741cb7a@linaro.org --- include/drm/drm_bridge.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 3606e1a7f965..4baca0d9107b 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -541,7 +541,7 @@ struct drm_bridge_funcs { * The @get_modes callback is mostly intended to support non-probeable * displays such as many fixed panels. Bridges that support reading * EDID shall leave @get_modes unimplemented and implement the - * &drm_bridge_funcs->get_edid callback instead. + * &drm_bridge_funcs->edid_read callback instead. * * This callback is optional. Bridges that implement it shall set the * DRM_BRIDGE_OP_MODES flag in their &drm_bridge->ops. @@ -687,7 +687,7 @@ enum drm_bridge_ops { /** * @DRM_BRIDGE_OP_EDID: The bridge can retrieve the EDID of the display * connected to its output. Bridges that set this flag shall implement - * the &drm_bridge_funcs->get_edid callback. + * the &drm_bridge_funcs->edid_read callback. */ DRM_BRIDGE_OP_EDID = BIT(1), /** -- cgit v1.2.3 From 152609795dbf02f004c86049b75c23f4e68071d8 Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Sat, 16 Mar 2024 01:10:21 +0100 Subject: fbcon: Increase maximum font width x height to 64 x 128 By using bitmaps we actually support whatever size we would want, but the console currently limits fonts to 64x128 (which gives 60x16 text on 4k screens), so we don't need more for now, and we can easily increase later. Signed-off-by: Samuel Thibault Signed-off-by: Helge Deller --- include/linux/fb.h | 18 ++++++++++++------ include/linux/font.h | 3 ++- 2 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 05dc9624897d..7d7c7791fd26 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -143,9 +143,13 @@ struct fb_event { void *data; }; +/* Enough for the VT console needs, see its max_font_width/height */ +#define FB_MAX_BLIT_WIDTH 64 +#define FB_MAX_BLIT_HEIGHT 128 + struct fb_blit_caps { - u32 x; - u32 y; + DECLARE_BITMAP(x, FB_MAX_BLIT_WIDTH); + DECLARE_BITMAP(y, FB_MAX_BLIT_HEIGHT); u32 len; u32 flags; }; @@ -192,10 +196,12 @@ struct fb_pixmap { u32 scan_align; /* alignment per scanline */ u32 access_align; /* alignment per read/write (bits) */ u32 flags; /* see FB_PIXMAP_* */ - u32 blit_x; /* supported bit block dimensions (1-32)*/ - u32 blit_y; /* Format: blit_x = 1 << (width - 1) */ - /* blit_y = 1 << (height - 1) */ - /* if 0, will be set to 0xffffffff (all)*/ + /* supported bit block dimensions */ + /* Format: test_bit(width - 1, blit_x) */ + /* test_bit(height - 1, blit_y) */ + /* if zero, will be set to full (all) */ + DECLARE_BITMAP(blit_x, FB_MAX_BLIT_WIDTH); + DECLARE_BITMAP(blit_y, FB_MAX_BLIT_HEIGHT); /* access methods */ void (*writeio)(struct fb_info *info, void __iomem *dst, void *src, unsigned int size); void (*readio) (struct fb_info *info, void *dst, void __iomem *src, unsigned int size); diff --git a/include/linux/font.h b/include/linux/font.h index abf1442ce719..81caffd51bb4 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -57,7 +57,8 @@ extern const struct font_desc *find_font(const char *name); /* Get the default font for a specific screen size */ extern const struct font_desc *get_default_font(int xres, int yres, - u32 font_w, u32 font_h); + unsigned long *font_w, + unsigned long *font_h); /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 -- cgit v1.2.3 From 56a34d799bfa53064e7b8bd354aacd176aeaecc8 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Mon, 26 Feb 2024 16:00:08 +0530 Subject: kexec/kdump: make struct crash_mem available without CONFIG_CRASH_DUMP struct crash_mem defined under include/linux/crash_core.h represents a list of memory ranges. While it is used to represent memory ranges for kdump kernel, it can also be used for other kind of memory ranges. In fact, KEXEC_FILE_LOAD syscall in powerpc uses this structure to represent reserved memory ranges and exclude memory ranges needed to find the right memory regions to load kexec kernel. So, make the definition of crash_mem structure available for !CONFIG_CRASH_DUMP case too. Signed-off-by: Hari Bathini Acked-by: Baoquan He Signed-off-by: Michael Ellerman Link: https://msgid.link/20240226103010.589537-2-hbathini@linux.ibm.com --- include/linux/crash_core.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 23270b16e1db..d33352c2e386 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -8,6 +8,12 @@ struct kimage; +struct crash_mem { + unsigned int max_nr_ranges; + unsigned int nr_ranges; + struct range ranges[] __counted_by(max_nr_ranges); +}; + #ifdef CONFIG_CRASH_DUMP int crash_shrink_memory(unsigned long new_size); @@ -51,12 +57,6 @@ static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 -struct crash_mem { - unsigned int max_nr_ranges; - unsigned int nr_ranges; - struct range ranges[] __counted_by(max_nr_ranges); -}; - extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend); -- cgit v1.2.3 From 807f96abdf14c80f534c78f2d854c2590963345c Mon Sep 17 00:00:00 2001 From: Arthur Grillo Date: Sat, 16 Mar 2024 13:25:20 -0300 Subject: drm: Fix drm_fixp2int_round() making it add 0.5 As well noted by Pekka[1], the rounding of drm_fixp2int_round is wrong. To round a number, you need to add 0.5 to the number and floor that, drm_fixp2int_round() is adding 0.0000076. Make it add 0.5. [1]: https://lore.kernel.org/all/20240301135327.22efe0dd.pekka.paalanen@collabora.com/ Fixes: 8b25320887d7 ("drm: Add fixed-point helper to get rounded integer values") Suggested-by: Pekka Paalanen Reviewed-by: Harry Wentland Reviewed-by: Melissa Wen Signed-off-by: Arthur Grillo Signed-off-by: Melissa Wen Link: https://patchwork.freedesktop.org/patch/msgid/20240316-drm_fixed-v2-1-c1bc2665b5ed@riseup.net --- include/drm/drm_fixed.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_fixed.h b/include/drm/drm_fixed.h index 0c9f917a4d4b..81572d32db0c 100644 --- a/include/drm/drm_fixed.h +++ b/include/drm/drm_fixed.h @@ -71,7 +71,6 @@ static inline u32 dfixed_div(fixed20_12 A, fixed20_12 B) } #define DRM_FIXED_POINT 32 -#define DRM_FIXED_POINT_HALF 16 #define DRM_FIXED_ONE (1ULL << DRM_FIXED_POINT) #define DRM_FIXED_DECIMAL_MASK (DRM_FIXED_ONE - 1) #define DRM_FIXED_DIGITS_MASK (~DRM_FIXED_DECIMAL_MASK) @@ -90,7 +89,7 @@ static inline int drm_fixp2int(s64 a) static inline int drm_fixp2int_round(s64 a) { - return drm_fixp2int(a + (1 << (DRM_FIXED_POINT_HALF - 1))); + return drm_fixp2int(a + DRM_FIXED_ONE / 2); } static inline int drm_fixp2int_ceil(s64 a) -- cgit v1.2.3 From f6e922365faf4cd576bd1cf3e64b58c8a32e1856 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 18 Mar 2024 09:54:27 -0700 Subject: xsk: Don't assume metadata is always requested in TX completion `compl->tx_timestam != NULL` means that the user has explicitly requested the metadata via XDP_TX_METADATA+XDP_TX_METADATA_TIMESTAMP. Fixes: 48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support") Reported-by: Daniele Salvatore Albano Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann Tested-by: Daniele Salvatore Albano Link: https://lore.kernel.org/bpf/20240318165427.1403313-1-sdf@google.com --- include/net/xdp_sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 3cb4dc9bd70e..3d54de168a6d 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -188,6 +188,8 @@ static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, { if (!compl) return; + if (!compl->tx_timestamp) + return; *compl->tx_timestamp = ops->tmo_fill_timestamp(priv); } -- cgit v1.2.3 From 203a6763ab699da0568fd2b76303d03bb121abd4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 13 Mar 2024 16:32:27 -0700 Subject: Revert "crypto: pkcs7 - remove sha1 support" This reverts commit 16ab7cb5825fc3425c16ad2c6e53d827f382d7c6 because it broke iwd. iwd uses the KEYCTL_PKEY_* UAPIs via its dependency libell, and apparently it is relying on SHA-1 signature support. These UAPIs are fairly obscure, and their documentation does not mention which algorithms they support. iwd really should be using a properly supported userspace crypto library instead. Regardless, since something broke we have to revert the change. It may be possible that some parts of this commit can be reinstated without breaking iwd (e.g. probably the removal of MODULE_SIG_SHA1), but for now this just does a full revert to get things working again. Reported-by: Karel Balej Closes: https://lore.kernel.org/r/CZSHRUIJ4RKL.34T4EASV5DNJM@matfyz.cz Cc: Dimitri John Ledkov Signed-off-by: Eric Biggers Tested-by: Karel Balej Signed-off-by: Herbert Xu --- include/linux/oid_registry.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 3921fbed0b28..51421fdbb0ba 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -17,10 +17,12 @@ * build_OID_registry.pl to generate the data for look_up_OID(). */ enum OID { + OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */ OID_id_dsa, /* 1.2.840.10040.4.1 */ OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */ OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */ OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */ + OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */ OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */ OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */ @@ -28,6 +30,7 @@ enum OID { /* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */ OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */ + OID_sha1WithRSAEncryption, /* 1.2.840.113549.1.1.5 */ OID_sha256WithRSAEncryption, /* 1.2.840.113549.1.1.11 */ OID_sha384WithRSAEncryption, /* 1.2.840.113549.1.1.12 */ OID_sha512WithRSAEncryption, /* 1.2.840.113549.1.1.13 */ @@ -64,6 +67,7 @@ enum OID { OID_PKU2U, /* 1.3.5.1.5.2.7 */ OID_Scram, /* 1.3.6.1.5.5.14 */ OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ + OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ -- cgit v1.2.3 From d8e45f2929b94099913eb66c3ebb18b5063e9421 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 6 Mar 2024 15:51:36 -0800 Subject: overflow: Change DEFINE_FLEX to take __counted_by member The norm should be flexible array structures with __counted_by annotations, so DEFINE_FLEX() is updated to expect that. Rename the non-annotated version to DEFINE_RAW_FLEX(), and update the few existing users. Additionally add selftests for the macros. Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20240306235128.it.933-kees@kernel.org Reviewed-by: Przemek Kitszel Signed-off-by: Kees Cook --- include/linux/overflow.h | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index aa691f2119b0..0c7e3dcfe867 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -398,7 +398,7 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * @count: Number of elements in the array; must be compile-time const. * @initializer: initializer expression (could be empty for no init). */ -#define _DEFINE_FLEX(type, name, member, count, initializer) \ +#define _DEFINE_FLEX(type, name, member, count, initializer...) \ _Static_assert(__builtin_constant_p(count), \ "onstack flex array members require compile-time const count"); \ union { \ @@ -408,8 +408,8 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) type *name = (type *)&name##_u /** - * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing - * flexible array member. + * DEFINE_RAW_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member, when it does not have a __counted_by annotation. * * @type: structure type name, including "struct" keyword. * @name: Name for a variable to define. @@ -420,7 +420,24 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * flexible array member. * Use __struct_size(@name) to get compile-time size of it afterwards. */ -#define DEFINE_FLEX(type, name, member, count) \ +#define DEFINE_RAW_FLEX(type, name, member, count) \ _DEFINE_FLEX(type, name, member, count, = {}) +/** + * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member. + * + * @TYPE: structure type name, including "struct" keyword. + * @NAME: Name for a variable to define. + * @MEMBER: Name of the array member. + * @COUNTER: Name of the __counted_by member. + * @COUNT: Number of elements in the array; must be compile-time const. + * + * Define a zeroed, on-stack, instance of @TYPE structure with a trailing + * flexible array member. + * Use __struct_size(@NAME) to get compile-time size of it afterwards. + */ +#define DEFINE_FLEX(TYPE, NAME, MEMBER, COUNTER, COUNT) \ + _DEFINE_FLEX(TYPE, NAME, MEMBER, COUNT, = { .obj.COUNTER = COUNT, }) + #endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From be23b2d7c3b7c8bf57b1cf0bf890bd65df9d0186 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 14 Mar 2024 11:09:51 +0100 Subject: wifi: cfg80211: add a flag to disable wireless extensions Wireless extensions are already disabled if MLO is enabled, given that we cannot support MLO there with all the hard- coded assumptions about BSSID etc. However, the WiFi7 ecosystem is still stabilizing, and some devices may need MLO disabled while that happens. In that case, we might end up with a device that supports wext (but not MLO) in one kernel, and then breaks wext in the future (by enabling MLO), which is not desirable. Add a flag to let such drivers/devices disable wext even if MLO isn't yet enabled. Cc: stable@vger.kernel.org Link: https://msgid.link/20240314110951.b50f1dc4ec21.I656ddd8178eedb49dc5c6c0e70f8ce5807afb54f@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2e2be4fd2bb6..1e09329acc42 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4991,6 +4991,7 @@ struct cfg80211_ops { * set this flag to update channels on beacon hints. * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link * of an NSTR mobile AP MLD. + * @WIPHY_FLAG_DISABLE_WEXT: disable wireless extensions for this device */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), @@ -5002,6 +5003,7 @@ enum wiphy_flags { WIPHY_FLAG_4ADDR_STATION = BIT(6), WIPHY_FLAG_CONTROL_PORT_PROTOCOL = BIT(7), WIPHY_FLAG_IBSS_RSN = BIT(8), + WIPHY_FLAG_DISABLE_WEXT = BIT(9), WIPHY_FLAG_MESH_AUTH = BIT(10), WIPHY_FLAG_SUPPORTS_EXT_KCK_32 = BIT(11), WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY = BIT(12), -- cgit v1.2.3 From 151c9c724d05d5b0dd8acd3e11cb69ef1f2dbada Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Mar 2024 13:57:32 +0000 Subject: tcp: properly terminate timers for kernel sockets We had various syzbot reports about tcp timers firing after the corresponding netns has been dismantled. Fortunately Josef Bacik could trigger the issue more often, and could test a patch I wrote two years ago. When TCP sockets are closed, we call inet_csk_clear_xmit_timers() to 'stop' the timers. inet_csk_clear_xmit_timers() can be called from any context, including when socket lock is held. This is the reason it uses sk_stop_timer(), aka del_timer(). This means that ongoing timers might finish much later. For user sockets, this is fine because each running timer holds a reference on the socket, and the user socket holds a reference on the netns. For kernel sockets, we risk that the netns is freed before timer can complete, because kernel sockets do not hold reference on the netns. This patch adds inet_csk_clear_xmit_timers_sync() function that using sk_stop_timer_sync() to make sure all timers are terminated before the kernel socket is released. Modules using kernel sockets close them in their netns exit() handler. Also add sock_not_owned_by_me() helper to get LOCKDEP support : inet_csk_clear_xmit_timers_sync() must not be called while socket lock is held. It is very possible we can revert in the future commit 3a58f13a881e ("net: rds: acquire refcount on TCP sockets") which attempted to solve the issue in rds only. (net/smc/af_smc.c and net/mptcp/subflow.c have similar code) We probably can remove the check_net() tests from tcp_out_of_resources() and __tcp_close() in the future. Reported-by: Josef Bacik Closes: https://lore.kernel.org/netdev/20240314210740.GA2823176@perftesting/ Fixes: 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.") Fixes: 8a68173691f0 ("net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket") Link: https://lore.kernel.org/bpf/CANn89i+484ffqb93aQm1N-tjxxvb3WDKX0EbD7318RwRgsatjw@mail.gmail.com/ Signed-off-by: Eric Dumazet Tested-by: Josef Bacik Cc: Tetsuo Handa Link: https://lore.kernel.org/r/20240322135732.1535772-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 1 + include/net/sock.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 9ab4bf704e86..ccf171f7eb60 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -175,6 +175,7 @@ void inet_csk_init_xmit_timers(struct sock *sk, void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); +void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { diff --git a/include/net/sock.h b/include/net/sock.h index b5e00702acc1..f57bfd8a2ad2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1759,6 +1759,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); -- cgit v1.2.3 From 9cecde80aae0fb0aa44425575d5aca71bc646d89 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 15 Mar 2024 14:08:21 +0000 Subject: mm: increase folio batch size On a 104 thread, 2 socket Skylake system, Intel report a 4.7% performance reduction with will-it-scale page_fault2. This was due to reducing the size of the batch from 32 to 15. Increasing the folio batch size from 15 to 31 gives a performance increase of 12.5% relative to the original, or 17.2% relative to the reduced performance commit. The penalty of this commit is an additional 128 bytes of stack usage. Six folio_batches are also allocated from percpu memory in cpu_fbatches so that will be an additional 768 bytes of percpu memory (per CPU). Tim Chen originally submitted a patch like this in 2020: https://lore.kernel.org/linux-mm/d1cc9f12a8ad6c2a52cb600d93b06b064f2bbc57.1593205965.git.tim.c.chen@linux.intel.com/ Link: https://lkml.kernel.org/r/20240315140823.2478146-1-willy@infradead.org Fixes: 99fbb6bfc16f ("mm: make folios_put() the basis of release_pages()") Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Yujie Liu Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202403151058.7048f6a8-oliver.sang@intel.com Signed-off-by: Andrew Morton --- include/linux/pagevec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index fcc06c300a72..5d3a0cccc6bf 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -11,8 +11,8 @@ #include -/* 15 pointers + header align the folio_batch structure to a power of two */ -#define PAGEVEC_SIZE 15 +/* 31 pointers + header align the folio_batch structure to a power of two */ +#define PAGEVEC_SIZE 31 struct folio; -- cgit v1.2.3 From d5aad4c2ca057e760a92a9a7d65bd38d72963f27 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Mon, 26 Feb 2024 17:35:41 -0800 Subject: prctl: generalize PR_SET_MDWE support check to be per-arch Patch series "ARM: prctl: Reject PR_SET_MDWE where not supported". I noticed after a recent kernel update that my ARM926 system started segfaulting on any execve() after calling prctl(PR_SET_MDWE). After some investigation it appears that ARMv5 is incapable of providing the appropriate protections for MDWE, since any readable memory is also implicitly executable. The prctl_set_mdwe() function already had some special-case logic added disabling it on PARISC (commit 793838138c15, "prctl: Disable prctl(PR_SET_MDWE) on parisc"); this patch series (1) generalizes that check to use an arch_*() function, and (2) adds a corresponding override for ARM to disable MDWE on pre-ARMv6 CPUs. With the series applied, prctl(PR_SET_MDWE) is rejected on ARMv5 and subsequent execve() calls (as well as mmap(PROT_READ|PROT_WRITE)) can succeed instead of unconditionally failing; on ARMv6 the prctl works as it did previously. [0] https://lore.kernel.org/all/2023112456-linked-nape-bf19@gregkh/ This patch (of 2): There exist systems other than PARISC where MDWE may not be feasible to support; rather than cluttering up the generic code with additional arch-specific logic let's add a generic function for checking MDWE support and allow each arch to override it as needed. Link: https://lkml.kernel.org/r/20240227013546.15769-4-zev@bewilderbeest.net Link: https://lkml.kernel.org/r/20240227013546.15769-5-zev@bewilderbeest.net Signed-off-by: Zev Weiss Acked-by: Helge Deller [parisc] Cc: Borislav Petkov Cc: David Hildenbrand Cc: Florent Revest Cc: "James E.J. Bottomley" Cc: Josh Triplett Cc: Kees Cook Cc: Miguel Ojeda Cc: Mike Rapoport (IBM) Cc: Oleg Nesterov Cc: Ondrej Mosnacek Cc: Rick Edgecombe Cc: Russell King (Oracle) Cc: Sam James Cc: Stefan Roesch Cc: Yang Shi Cc: Yin Fengwei Cc: [6.3+] Signed-off-by: Andrew Morton --- include/linux/mman.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mman.h b/include/linux/mman.h index dc7048824be8..bcb201ab7a41 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -162,6 +162,14 @@ calc_vm_flag_bits(unsigned long flags) unsigned long vm_commit_limit(void); +#ifndef arch_memory_deny_write_exec_supported +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return true; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported +#endif + /* * Denies creating a writable executable mapping or gaining executable permissions. * -- cgit v1.2.3 From ea2c09283b44d1a3732a195a9b257d56779c8863 Mon Sep 17 00:00:00 2001 From: Herve Codina Date: Mon, 25 Mar 2024 09:25:05 +0100 Subject: net: wan: framer: Add missing static inline qualifiers Compilation with CONFIG_GENERIC_FRAMER disabled lead to the following warnings: framer.h:184:16: warning: no previous prototype for function 'framer_get' [-Wmissing-prototypes] 184 | struct framer *framer_get(struct device *dev, const char *con_id) framer.h:184:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 184 | struct framer *framer_get(struct device *dev, const char *con_id) framer.h:189:6: warning: no previous prototype for function 'framer_put' [-Wmissing-prototypes] 189 | void framer_put(struct device *dev, struct framer *framer) framer.h:189:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 189 | void framer_put(struct device *dev, struct framer *framer) Add missing 'static inline' qualifiers for these functions. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202403241110.hfJqeJRu-lkp@intel.com/ Fixes: 82c944d05b1a ("net: wan: Add framer framework support") Cc: stable@vger.kernel.org Signed-off-by: Herve Codina Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/framer/framer.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h index 9a9b88962c29..2b85fe9e7f9a 100644 --- a/include/linux/framer/framer.h +++ b/include/linux/framer/framer.h @@ -181,12 +181,12 @@ static inline int framer_notifier_unregister(struct framer *framer, return -ENOSYS; } -struct framer *framer_get(struct device *dev, const char *con_id) +static inline struct framer *framer_get(struct device *dev, const char *con_id) { return ERR_PTR(-ENOSYS); } -void framer_put(struct device *dev, struct framer *framer) +static inline void framer_put(struct device *dev, struct framer *framer) { } -- cgit v1.2.3 From 18685451fc4e546fc0e718580d32df3c0e5c8272 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Mar 2024 11:18:41 +0100 Subject: inet: inet_defrag: prevent sk release while still in use ip_local_out() and other functions can pass skb->sk as function argument. If the skb is a fragment and reassembly happens before such function call returns, the sk must not be released. This affects skb fragments reassembled via netfilter or similar modules, e.g. openvswitch or ct_act.c, when run as part of tx pipeline. Eric Dumazet made an initial analysis of this bug. Quoting Eric: Calling ip_defrag() in output path is also implying skb_orphan(), which is buggy because output path relies on sk not disappearing. A relevant old patch about the issue was : 8282f27449bf ("inet: frag: Always orphan skbs inside ip_defrag()") [..] net/ipv4/ip_output.c depends on skb->sk being set, and probably to an inet socket, not an arbitrary one. If we orphan the packet in ipvlan, then downstream things like FQ packet scheduler will not work properly. We need to change ip_defrag() to only use skb_orphan() when really needed, ie whenever frag_list is going to be used. Eric suggested to stash sk in fragment queue and made an initial patch. However there is a problem with this: If skb is refragmented again right after, ip_do_fragment() will copy head->sk to the new fragments, and sets up destructor to sock_wfree. IOW, we have no choice but to fix up sk_wmem accouting to reflect the fully reassembled skb, else wmem will underflow. This change moves the orphan down into the core, to last possible moment. As ip_defrag_offset is aliased with sk_buff->sk member, we must move the offset into the FRAG_CB, else skb->sk gets clobbered. This allows to delay the orphaning long enough to learn if the skb has to be queued or if the skb is completing the reasm queue. In the former case, things work as before, skb is orphaned. This is safe because skb gets queued/stolen and won't continue past reasm engine. In the latter case, we will steal the skb->sk reference, reattach it to the head skb, and fix up wmem accouting when inet_frag inflates truesize. Fixes: 7026b1ddb6b8 ("netfilter: Pass socket pointer down through okfn().") Diagnosed-by: Eric Dumazet Reported-by: xingwei lee Reported-by: yue sun Reported-by: syzbot+e5167d7144a62715044c@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240326101845.30836-1-fw@strlen.de Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0c7c67b3a87b..9d24aec064e8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -753,8 +753,6 @@ typedef unsigned char *sk_buff_data_t; * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by - * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in - * fragmentation management * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -875,10 +873,7 @@ struct sk_buff { struct llist_node ll_node; }; - union { - struct sock *sk; - int ip_defrag_offset; - }; + struct sock *sk; union { ktime_t tstamp; -- cgit v1.2.3