June 2025 - Linux-stable-mirror

[PATCH] LoongArch: vDSO: correctly use asm parameters in syscall wrappers

by Thomas Weißschuh

The syscall wrappers use the "a0" register for two different register variables, both the first argument and the return value. The "ret" variable is used as both input and output while the argument register is only used as input. Clang treats the conflicting input parameters as undefined behaviour and optimizes away the argument assignment. The code seems to work by chance for the most part today but that may change in the future. Specifically clock_gettime_fallback() fails with clockids from 16 to 23, as implemented by the upcoming auxiliary clocks. Switch the "ret" register variable to a pure output, similar to the other architectures' vDSO code. This works in both clang and GCC. Link: https://lore.kernel.org/lkml/20250602102825-42aa84f0-23f1-4d10-89fc-e8bbaff… Link: https://lore.kernel.org/lkml/20250519082042.742926976@linutronix.de/ Fixes: c6b99bed6b8f ("LoongArch: Add VDSO and VSYSCALL support") Fixes: 18efd0b10e0f ("LoongArch: vDSO: Wire up getrandom() vDSO implementation") Cc: stable(a)vger.kernel.org Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- arch/loongarch/include/asm/vdso/getrandom.h | 2 +- arch/loongarch/include/asm/vdso/gettimeofday.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h index 48c43f55b039b42168698614d0479b7a872d20f3..a81724b69f291ee49dd1f46b12d6893fc18442b8 100644 --- a/arch/loongarch/include/asm/vdso/getrandom.h +++ b/arch/loongarch/include/asm/vdso/getrandom.h @@ -20,7 +20,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (buffer), "r" (len), "r" (flags) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index 88cfcf13311630ed5f1a734d23a2bc3f65d79a88..f15503e3336ca1bdc9675ec6e17bbb77abc35ef4 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -25,7 +25,7 @@ static __always_inline long gettimeofday_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (tv), "r" (tz) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -44,7 +44,7 @@ static __always_inline long clock_gettime_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (clkid), "r" (ts) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -63,7 +63,7 @@ static __always_inline int clock_getres_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (clkid), "r" (ts) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); --- base-commit: 546b1c9e93c2bb8cf5ed24e0be1c86bb089b3253 change-id: 20250603-loongarch-vdso-syscall-f585a99bea03 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

2 months, 2 weeks

6
8
0 0

[PATCH 1/1] dm-verity: fix a memory leak if some arguments are specified multiple times

by Brahmajit Das

From: Mikulas Patocka <mpatocka(a)redhat.com> From: Mikulas Patocka <mpatocka(a)redhat.com> [ Upstream commit 66be40a14e496689e1f0add50118408e22c96169 ] If some of the arguments "check_at_most_once", "ignore_zero_blocks", "use_fec_from_device", "root_hash_sig_key_desc" were specified more than once on the target line, a memory leak would happen. This commit fixes the memory leak. It also fixes error handling in verity_verify_sig_parse_opt_args. Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Cc: stable(a)vger.kernel.org Signed-off-by: Brahmajit Das <listout(a)listout.xyz> --- drivers/md/dm-verity-fec.c | 4 ++++ drivers/md/dm-verity-target.c | 8 +++++++- drivers/md/dm-verity-verify-sig.c | 17 +++++++++++++---- 3 files changed, 24 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 0c41949db784..631a887b487c 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -593,6 +593,10 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, (*argc)--; if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { + if (v->fec->dev) { + ti->error = "FEC device already specified"; + return -EINVAL; + } r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev); if (r) { ti->error = "FEC device lookup failed"; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 3c427f18a04b..ed49bcbd224f 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1120,6 +1120,9 @@ static int verity_alloc_most_once(struct dm_verity *v) { struct dm_target *ti = v->ti; + if (v->validated_blocks) + return 0; + /* the bitset can only handle INT_MAX blocks */ if (v->data_blocks > INT_MAX) { ti->error = "device too large to use check_at_most_once"; @@ -1143,6 +1146,9 @@ static int verity_alloc_zero_digest(struct dm_verity *v) struct dm_verity_io *io; u8 *zero_data; + if (v->zero_digest) + return 0; + v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL); if (!v->zero_digest) @@ -1577,7 +1583,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - /* Root hash signature is a optional parameter*/ + /* Root hash signature is an optional parameter */ r = verity_verify_root_hash(root_hash_digest_to_validate, strlen(root_hash_digest_to_validate), verify_args.sig, diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c index a9e2c6c0a33c..d5261a0e4232 100644 --- a/drivers/md/dm-verity-verify-sig.c +++ b/drivers/md/dm-verity-verify-sig.c @@ -71,9 +71,14 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as, const char *arg_name) { struct dm_target *ti = v->ti; - int ret = 0; + int ret; const char *sig_key = NULL; + if (v->signature_key_desc) { + ti->error = DM_VERITY_VERIFY_ERR("root_hash_sig_key_desc already specified"); + return -EINVAL; + } + if (!*argc) { ti->error = DM_VERITY_VERIFY_ERR("Signature key not specified"); return -EINVAL; @@ -83,14 +88,18 @@ int verity_verify_sig_parse_opt_args(struct dm_arg_set *as, (*argc)--; ret = verity_verify_get_sig_from_key(sig_key, sig_opts); - if (ret < 0) + if (ret < 0) { ti->error = DM_VERITY_VERIFY_ERR("Invalid key specified"); + return ret; + } v->signature_key_desc = kstrdup(sig_key, GFP_KERNEL); - if (!v->signature_key_desc) + if (!v->signature_key_desc) { + ti->error = DM_VERITY_VERIFY_ERR("Could not allocate memory for signature key"); return -ENOMEM; + } - return ret; + return 0; } /* -- 2.49.0

2 months, 2 weeks

2
4
0 0

FAILED: patch "[PATCH] arm64: dts: ti: k3-j721e-sk: Add DT nodes for power" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 97b67cc102dc2cc8aa39a569c22a196e21af5a21 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025060241-numbly-remarry-d1a6@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 97b67cc102dc2cc8aa39a569c22a196e21af5a21 Mon Sep 17 00:00:00 2001 From: Yemike Abhilash Chandra <y-abhilashchandra(a)ti.com> Date: Tue, 15 Apr 2025 16:43:22 +0530 Subject: [PATCH] arm64: dts: ti: k3-j721e-sk: Add DT nodes for power regulators Add device tree nodes for two power regulators on the J721E SK board. vsys_5v0: A fixed regulator representing the 5V supply output from the LM61460 and vdd_sd_dv: A GPIO-controlled TLV71033 regulator. J721E-SK schematics: https://www.ti.com/lit/zip/sprr438 Fixes: 1bfda92a3a36 ("arm64: dts: ti: Add support for J721E SK") Cc: stable(a)vger.kernel.org Signed-off-by: Yemike Abhilash Chandra <y-abhilashchandra(a)ti.com> Reviewed-by: Udit Kumar <u-kumar1(a)ti.com> Link: https://lore.kernel.org/r/20250415111328.3847502-2-y-abhilashchandra@ti.com Signed-off-by: Nishanth Menon <nm(a)ti.com> diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts index 440ef57be294..ffef3d1cfd55 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts @@ -184,6 +184,17 @@ vsys_3v3: fixedregulator-vsys3v3 { regulator-boot-on; }; + vsys_5v0: fixedregulator-vsys5v0 { + /* Output of LM61460 */ + compatible = "regulator-fixed"; + regulator-name = "vsys_5v0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vusb_main>; + regulator-always-on; + regulator-boot-on; + }; + vdd_mmc1: fixedregulator-sd { compatible = "regulator-fixed"; pinctrl-names = "default"; @@ -211,6 +222,20 @@ vdd_sd_dv_alt: gpio-regulator-tps659411 { <3300000 0x1>; }; + vdd_sd_dv: gpio-regulator-TLV71033 { + compatible = "regulator-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&vdd_sd_dv_pins_default>; + regulator-name = "tlv71033"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + vin-supply = <&vsys_5v0>; + gpios = <&main_gpio0 118 GPIO_ACTIVE_HIGH>; + states = <1800000 0x0>, + <3300000 0x1>; + }; + transceiver1: can-phy1 { compatible = "ti,tcan1042"; #phy-cells = <0>; @@ -613,6 +638,12 @@ J721E_WKUP_IOPAD(0xd4, PIN_OUTPUT, 7) /* (G26) WKUP_GPIO0_9 */ >; }; + vdd_sd_dv_pins_default: vdd-sd-dv-default-pins { + pinctrl-single,pins = < + J721E_IOPAD(0x1dc, PIN_OUTPUT, 7) /* (Y1) SPI1_CLK.GPIO0_118 */ + >; + }; + wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < J721E_WKUP_IOPAD(0xa0, PIN_INPUT, 0) /* (J29) WKUP_UART0_RXD */

2 months, 2 weeks

2
1
0 0

FAILED: patch "[PATCH] arm64: dts: ti: k3-j721e-sk: Add DT nodes for power" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 97b67cc102dc2cc8aa39a569c22a196e21af5a21 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025060241-precut-candle-50a9@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 97b67cc102dc2cc8aa39a569c22a196e21af5a21 Mon Sep 17 00:00:00 2001 From: Yemike Abhilash Chandra <y-abhilashchandra(a)ti.com> Date: Tue, 15 Apr 2025 16:43:22 +0530 Subject: [PATCH] arm64: dts: ti: k3-j721e-sk: Add DT nodes for power regulators Add device tree nodes for two power regulators on the J721E SK board. vsys_5v0: A fixed regulator representing the 5V supply output from the LM61460 and vdd_sd_dv: A GPIO-controlled TLV71033 regulator. J721E-SK schematics: https://www.ti.com/lit/zip/sprr438 Fixes: 1bfda92a3a36 ("arm64: dts: ti: Add support for J721E SK") Cc: stable(a)vger.kernel.org Signed-off-by: Yemike Abhilash Chandra <y-abhilashchandra(a)ti.com> Reviewed-by: Udit Kumar <u-kumar1(a)ti.com> Link: https://lore.kernel.org/r/20250415111328.3847502-2-y-abhilashchandra@ti.com Signed-off-by: Nishanth Menon <nm(a)ti.com> diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts index 440ef57be294..ffef3d1cfd55 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts @@ -184,6 +184,17 @@ vsys_3v3: fixedregulator-vsys3v3 { regulator-boot-on; }; + vsys_5v0: fixedregulator-vsys5v0 { + /* Output of LM61460 */ + compatible = "regulator-fixed"; + regulator-name = "vsys_5v0"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vusb_main>; + regulator-always-on; + regulator-boot-on; + }; + vdd_mmc1: fixedregulator-sd { compatible = "regulator-fixed"; pinctrl-names = "default"; @@ -211,6 +222,20 @@ vdd_sd_dv_alt: gpio-regulator-tps659411 { <3300000 0x1>; }; + vdd_sd_dv: gpio-regulator-TLV71033 { + compatible = "regulator-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&vdd_sd_dv_pins_default>; + regulator-name = "tlv71033"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + vin-supply = <&vsys_5v0>; + gpios = <&main_gpio0 118 GPIO_ACTIVE_HIGH>; + states = <1800000 0x0>, + <3300000 0x1>; + }; + transceiver1: can-phy1 { compatible = "ti,tcan1042"; #phy-cells = <0>; @@ -613,6 +638,12 @@ J721E_WKUP_IOPAD(0xd4, PIN_OUTPUT, 7) /* (G26) WKUP_GPIO0_9 */ >; }; + vdd_sd_dv_pins_default: vdd-sd-dv-default-pins { + pinctrl-single,pins = < + J721E_IOPAD(0x1dc, PIN_OUTPUT, 7) /* (Y1) SPI1_CLK.GPIO0_118 */ + >; + }; + wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < J721E_WKUP_IOPAD(0xa0, PIN_INPUT, 0) /* (J29) WKUP_UART0_RXD */

2 months, 2 weeks

2
1
0 0

[PATCH] tools/resolve_btfids: Fix build when cross compiling kernel with clang.

by Suleiman Souhlal

When cross compiling the kernel with clang, we need to override CLANG_CROSS_FLAGS when preparing the step libraries for resolve_btfids. Prior to commit d1d096312176 ("tools: fix annoying "mkdir -p ..." logs when building tools in parallel"), MAKEFLAGS would have been set to a value that wouldn't set a value for CLANG_CROSS_FLAGS, hiding the fact that we weren't properly overriding it. Cc: stable(a)vger.kernel.org Fixes: 56a2df7615fa ("tools/resolve_btfids: Compile resolve_btfids as host program") Signed-of-by: Suleiman Souhlal <suleiman(a)google.com> --- tools/bpf/resolve_btfids/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index afbddea3a39c..ce1b556dfa90 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -17,7 +17,7 @@ endif # Overrides for the prepare step libraries. HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ - CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)" + CROSS_COMPILE="" CLANG_CROSS_FLAGS="" EXTRA_CFLAGS="$(HOSTCFLAGS)" RM ?= rm HOSTCC ?= gcc -- 2.50.0.rc0.642.g800a2b2222-goog

2 months, 2 weeks

2
6
0 0

[merged mm-hotfixes-stable] mm-hugetlb-fix-huge_pmd_unshare-vs-gup-fast-race.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race has been removed from the -mm tree. Its filename was mm-hugetlb-fix-huge_pmd_unshare-vs-gup-fast-race.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: Jann Horn <jannh(a)google.com> Subject: mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race Date: Tue, 27 May 2025 23:23:54 +0200 huge_pmd_unshare() drops a reference on a page table that may have previously been shared across processes, potentially turning it into a normal page table used in another process in which unrelated VMAs can afterwards be installed. If this happens in the middle of a concurrent gup_fast(), gup_fast() could end up walking the page tables of another process. While I don't see any way in which that immediately leads to kernel memory corruption, it is really weird and unexpected. Fix it with an explicit broadcast IPI through tlb_remove_table_sync_one(), just like we do in khugepaged when removing page tables for a THP collapse. Link: https://lkml.kernel.org/r/20250528-hugetlb-fixes-splitrace-v2-2-1329349bad1… Link: https://lkml.kernel.org/r/20250527-hugetlb-fixes-splitrace-v1-2-f4136f5ec58… Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Jann Horn <jannh(a)google.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/hugetlb.c | 7 +++++++ 1 file changed, 7 insertions(+) --- a/mm/hugetlb.c~mm-hugetlb-fix-huge_pmd_unshare-vs-gup-fast-race +++ a/mm/hugetlb.c @@ -7629,6 +7629,13 @@ int huge_pmd_unshare(struct mm_struct *m return 0; pud_clear(pud); + /* + * Once our caller drops the rmap lock, some other process might be + * using this page table as a normal, non-hugetlb page table. + * Wait for pending gup_fast() in other threads to finish before letting + * that happen. + */ + tlb_remove_table_sync_one(); ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; _ Patches currently in -mm which might be from jannh(a)google.com are hugetlb-block-hugetlb-file-creation-if-hugetlb-is-not-set-up.patch

2 months, 2 weeks

1
0
0 0

[merged mm-hotfixes-stable] mm-hugetlb-unshare-page-tables-during-vma-split-not-before.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/hugetlb: unshare page tables during VMA split, not before has been removed from the -mm tree. Its filename was mm-hugetlb-unshare-page-tables-during-vma-split-not-before.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: Jann Horn <jannh(a)google.com> Subject: mm/hugetlb: unshare page tables during VMA split, not before Date: Tue, 27 May 2025 23:23:53 +0200 Currently, __split_vma() triggers hugetlb page table unsharing through vm_ops->may_split(). This happens before the VMA lock and rmap locks are taken - which is too early, it allows racing VMA-locked page faults in our process and racing rmap walks from other processes to cause page tables to be shared again before we actually perform the split. Fix it by explicitly calling into the hugetlb unshare logic from __split_vma() in the same place where THP splitting also happens. At that point, both the VMA and the rmap(s) are write-locked. An annoying detail is that we can now call into the helper hugetlb_unshare_pmds() from two different locking contexts: 1. from hugetlb_split(), holding: - mmap lock (exclusively) - VMA lock - file rmap lock (exclusively) 2. hugetlb_unshare_all_pmds(), which I think is designed to be able to call us with only the mmap lock held (in shared mode), but currently only runs while holding mmap lock (exclusively) and VMA lock Backporting note: This commit fixes a racy protection that was introduced in commit b30c14cd6102 ("hugetlb: unshare some PMDs when splitting VMAs"); that commit claimed to fix an issue introduced in 5.13, but it should actually also go all the way back. [jannh(a)google.com: v2] Link: https://lkml.kernel.org/r/20250528-hugetlb-fixes-splitrace-v2-1-1329349bad1… Link: https://lkml.kernel.org/r/20250528-hugetlb-fixes-splitrace-v2-0-1329349bad1… Link: https://lkml.kernel.org/r/20250527-hugetlb-fixes-splitrace-v1-1-f4136f5ec58… Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Jann Horn <jannh(a)google.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> [b30c14cd6102: hugetlb: unshare some PMDs when splitting VMAs] Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/hugetlb.h | 3 + mm/hugetlb.c | 60 +++++++++++++++++++++-------- mm/vma.c | 7 +++ tools/testing/vma/vma_internal.h | 2 4 files changed, 56 insertions(+), 16 deletions(-) --- a/include/linux/hugetlb.h~mm-hugetlb-unshare-page-tables-during-vma-split-not-before +++ a/include/linux/hugetlb.h @@ -279,6 +279,7 @@ bool is_hugetlb_entry_migration(pte_t pt bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); void fixup_hugetlb_reservations(struct vm_area_struct *vma); +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr); #else /* !CONFIG_HUGETLB_PAGE */ @@ -476,6 +477,8 @@ static inline void fixup_hugetlb_reserva { } +static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write --- a/mm/hugetlb.c~mm-hugetlb-unshare-page-tables-during-vma-split-not-before +++ a/mm/hugetlb.c @@ -121,7 +121,7 @@ static void hugetlb_vma_lock_free(struct static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool take_locks); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static void hugetlb_free_folio(struct folio *folio) @@ -5426,26 +5426,40 @@ static int hugetlb_vm_op_split(struct vm { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + return 0; +} +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) +{ /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + * This function is called in the middle of a VMA split operation, with + * MM, VMA and rmap all write-locked to prevent concurrent page table + * walks (except hardware and gup_fast()). */ + vma_assert_write_locked(vma); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + if (addr & ~PUD_MASK) { - /* - * hugetlb_vm_op_split is called right before we attempt to - * split the VMA. We will need to unshare PMDs in the old and - * new VMAs, so let's unshare before we split. - */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; - if (floor >= vma->vm_start && ceil <= vma->vm_end) - hugetlb_unshare_pmds(vma, floor, ceil); + if (floor >= vma->vm_start && ceil <= vma->vm_end) { + /* + * Locking: + * Use take_locks=false here. + * The file rmap lock is already held. + * The hugetlb VMA lock can't be taken when we already + * hold the file rmap lock, and we don't need it because + * its purpose is to synchronize against concurrent page + * table walks, which are not possible thanks to the + * locks held by our caller. + */ + hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); + } } - - return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) @@ -7885,9 +7899,16 @@ void move_hugetlb_state(struct folio *ol spin_unlock_irq(&hugetlb_lock); } +/* + * If @take_locks is false, the caller must ensure that no concurrent page table + * access can happen (except for gup_fast() and hardware page walks). + * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like + * concurrent page fault handling) and the file rmap lock. + */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, + bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -7911,8 +7932,12 @@ static void hugetlb_unshare_pmds(struct mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); - hugetlb_vma_lock_write(vma); - i_mmap_lock_write(vma->vm_file->f_mapping); + if (take_locks) { + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(vma->vm_file->f_mapping); + } else { + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + } for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) @@ -7922,8 +7947,10 @@ static void hugetlb_unshare_pmds(struct spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); - i_mmap_unlock_write(vma->vm_file->f_mapping); - hugetlb_vma_unlock_write(vma); + if (take_locks) { + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + } /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. @@ -7938,7 +7965,8 @@ static void hugetlb_unshare_pmds(struct void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), - ALIGN_DOWN(vma->vm_end, PUD_SIZE)); + ALIGN_DOWN(vma->vm_end, PUD_SIZE), + /* take_locks = */ true); } /* --- a/mm/vma.c~mm-hugetlb-unshare-page-tables-during-vma-split-not-before +++ a/mm/vma.c @@ -539,7 +539,14 @@ __split_vma(struct vma_iterator *vmi, st init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); + + /* + * Get rid of huge pages and shared page tables straddling the split + * boundary. + */ vma_adjust_trans_huge(vma, vma->vm_start, addr, NULL); + if (is_vm_hugetlb_page(vma)) + hugetlb_split(vma, addr); if (new_below) { vma->vm_start = addr; --- a/tools/testing/vma/vma_internal.h~mm-hugetlb-unshare-page-tables-during-vma-split-not-before +++ a/tools/testing/vma/vma_internal.h @@ -932,6 +932,8 @@ static inline void vma_adjust_trans_huge (void)next; } +static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {} + static inline void vma_iter_free(struct vma_iterator *vmi) { mas_destroy(&vmi->mas); _ Patches currently in -mm which might be from jannh(a)google.com are hugetlb-block-hugetlb-file-creation-if-hugetlb-is-not-set-up.patch

2 months, 2 weeks

1
0
0 0

[merged mm-hotfixes-stable] alloc_tag-handle-module-codetag-load-errors-as-module-load-failures.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: alloc_tag: handle module codetag load errors as module load failures has been removed from the -mm tree. Its filename was alloc_tag-handle-module-codetag-load-errors-as-module-load-failures.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: Suren Baghdasaryan <surenb(a)google.com> Subject: alloc_tag: handle module codetag load errors as module load failures Date: Wed, 21 May 2025 09:06:02 -0700 Failures inside codetag_load_module() are currently ignored. As a result an error there would not cause a module load failure and freeing of the associated resources. Correct this behavior by propagating the error code to the caller and handling possible errors. With this change, error to allocate percpu counters, which happens at this stage, will not be ignored and will cause a module load failure and freeing of resources. With this change we also do not need to disable memory allocation profiling when this error happens, instead we fail to load the module. Link: https://lkml.kernel.org/r/20250521160602.1940771-1-surenb@google.com Fixes: 10075262888b ("alloc_tag: allocate percpu counters for module tags dynamically") Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Reported-by: Casey Chen <cachen(a)purestorage.com> Closes: https://lore.kernel.org/all/20250520231620.15259-1-cachen@purestorage.com/ Cc: Daniel Gomez <da.gomez(a)samsung.com> Cc: David Wang <00107082(a)163.com> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Luis Chamberalin <mcgrof(a)kernel.org> Cc: Petr Pavlu <petr.pavlu(a)suse.com> Cc: Sami Tolvanen <samitolvanen(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/codetag.h | 8 ++++---- kernel/module/main.c | 5 +++-- lib/alloc_tag.c | 12 +++++++----- lib/codetag.c | 34 +++++++++++++++++++++++++--------- 4 files changed, 39 insertions(+), 20 deletions(-) --- a/include/linux/codetag.h~alloc_tag-handle-module-codetag-load-errors-as-module-load-failures +++ a/include/linux/codetag.h @@ -36,8 +36,8 @@ union codetag_ref { struct codetag_type_desc { const char *section; size_t tag_size; - void (*module_load)(struct module *mod, - struct codetag *start, struct codetag *end); + int (*module_load)(struct module *mod, + struct codetag *start, struct codetag *end); void (*module_unload)(struct module *mod, struct codetag *start, struct codetag *end); #ifdef CONFIG_MODULES @@ -89,7 +89,7 @@ void *codetag_alloc_module_section(struc unsigned long align); void codetag_free_module_sections(struct module *mod); void codetag_module_replaced(struct module *mod, struct module *new_mod); -void codetag_load_module(struct module *mod); +int codetag_load_module(struct module *mod); void codetag_unload_module(struct module *mod); #else /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ @@ -103,7 +103,7 @@ codetag_alloc_module_section(struct modu unsigned long align) { return NULL; } static inline void codetag_free_module_sections(struct module *mod) {} static inline void codetag_module_replaced(struct module *mod, struct module *new_mod) {} -static inline void codetag_load_module(struct module *mod) {} +static inline int codetag_load_module(struct module *mod) { return 0; } static inline void codetag_unload_module(struct module *mod) {} #endif /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ --- a/kernel/module/main.c~alloc_tag-handle-module-codetag-load-errors-as-module-load-failures +++ a/kernel/module/main.c @@ -3386,11 +3386,12 @@ static int load_module(struct load_info goto sysfs_cleanup; } + if (codetag_load_module(mod)) + goto sysfs_cleanup; + /* Get rid of temporary copy. */ free_copy(info, flags); - codetag_load_module(mod); - /* Done! */ trace_module_load(mod); --- a/lib/alloc_tag.c~alloc_tag-handle-module-codetag-load-errors-as-module-load-failures +++ a/lib/alloc_tag.c @@ -607,15 +607,16 @@ out: mas_unlock(&mas); } -static void load_module(struct module *mod, struct codetag *start, struct codetag *stop) +static int load_module(struct module *mod, struct codetag *start, struct codetag *stop) { /* Allocate module alloc_tag percpu counters */ struct alloc_tag *start_tag; struct alloc_tag *stop_tag; struct alloc_tag *tag; + /* percpu counters for core allocations are already statically allocated */ if (!mod) - return; + return 0; start_tag = ct_to_alloc_tag(start); stop_tag = ct_to_alloc_tag(stop); @@ -627,12 +628,13 @@ static void load_module(struct module *m free_percpu(tag->counters); tag->counters = NULL; } - shutdown_mem_profiling(true); - pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s. Memory allocation profiling is disabled!\n", + pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s\n", mod->name); - break; + return -ENOMEM; } } + + return 0; } static void replace_module(struct module *mod, struct module *new_mod) --- a/lib/codetag.c~alloc_tag-handle-module-codetag-load-errors-as-module-load-failures +++ a/lib/codetag.c @@ -167,6 +167,7 @@ static int codetag_module_init(struct co { struct codetag_range range; struct codetag_module *cmod; + int mod_id; int err; range = get_section_range(mod, cttype->desc.section); @@ -190,11 +191,20 @@ static int codetag_module_init(struct co cmod->range = range; down_write(&cttype->mod_lock); - err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL); - if (err >= 0) { - cttype->count += range_size(cttype, &range); - if (cttype->desc.module_load) - cttype->desc.module_load(mod, range.start, range.stop); + mod_id = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL); + if (mod_id >= 0) { + if (cttype->desc.module_load) { + err = cttype->desc.module_load(mod, range.start, range.stop); + if (!err) + cttype->count += range_size(cttype, &range); + else + idr_remove(&cttype->mod_idr, mod_id); + } else { + cttype->count += range_size(cttype, &range); + err = 0; + } + } else { + err = mod_id; } up_write(&cttype->mod_lock); @@ -295,17 +305,23 @@ void codetag_module_replaced(struct modu mutex_unlock(&codetag_lock); } -void codetag_load_module(struct module *mod) +int codetag_load_module(struct module *mod) { struct codetag_type *cttype; + int ret = 0; if (!mod) - return; + return 0; mutex_lock(&codetag_lock); - list_for_each_entry(cttype, &codetag_types, link) - codetag_module_init(cttype, mod); + list_for_each_entry(cttype, &codetag_types, link) { + ret = codetag_module_init(cttype, mod); + if (ret) + break; + } mutex_unlock(&codetag_lock); + + return ret; } void codetag_unload_module(struct module *mod) _ Patches currently in -mm which might be from surenb(a)google.com are

2 months, 2 weeks

1
0
0 0

[merged mm-hotfixes-stable] mm-madvise-handle-madvise_lock-failure-during-race-unwinding.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/madvise: handle madvise_lock() failure during race unwinding has been removed from the -mm tree. Its filename was mm-madvise-handle-madvise_lock-failure-during-race-unwinding.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: SeongJae Park <sj(a)kernel.org> Subject: mm/madvise: handle madvise_lock() failure during race unwinding Date: Mon, 2 Jun 2025 10:49:26 -0700 When unwinding race on -ERESTARTNOINTR handling of process_madvise(), madvise_lock() failure is ignored. Check the failure and abort remaining works in the case. Link: https://lkml.kernel.org/r/20250602174926.1074-1-sj@kernel.org Fixes: 4000e3d0a367 ("mm/madvise: remove redundant mmap_lock operations from process_madvise()") Signed-off-by: SeongJae Park <sj(a)kernel.org> Reported-by: Barry Song <21cnbao(a)gmail.com> Closes: https://lore.kernel.org/CAGsJ_4xJXXO0G+4BizhohSZ4yDteziPw43_uF8nPXPWxUVChzw… Reviewed-by: Jann Horn <jannh(a)google.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Shakeel Butt <shakeel.butt(a)linux.dev> Reviewed-by: Barry Song <baohua(a)kernel.org> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/madvise.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/mm/madvise.c~mm-madvise-handle-madvise_lock-failure-during-race-unwinding +++ a/mm/madvise.c @@ -1881,7 +1881,9 @@ static ssize_t vector_madvise(struct mm_ /* Drop and reacquire lock to unwind race. */ madvise_finish_tlb(&madv_behavior); madvise_unlock(mm, behavior); - madvise_lock(mm, behavior); + ret = madvise_lock(mm, behavior); + if (ret) + goto out; madvise_init_tlb(&madv_behavior, mm); continue; } @@ -1892,6 +1894,7 @@ static ssize_t vector_madvise(struct mm_ madvise_finish_tlb(&madv_behavior); madvise_unlock(mm, behavior); +out: ret = (total_len - iov_iter_count(iter)) ? : ret; return ret; _ Patches currently in -mm which might be from sj(a)kernel.org are mm-damon-introduce-damon_stat-module.patch mm-damon-introduce-damon_stat-module-fix.patch mm-damon-stat-calculate-and-expose-estimated-memory-bandwidth.patch mm-damon-stat-calculate-and-expose-idle-time-percentiles.patch docs-admin-guide-mm-damon-add-damon_stat-usage-document.patch

2 months, 2 weeks

1
0
0 0

[merged mm-hotfixes-stable] kvm-s390-rename-prot_none-to-prot_type_dummy.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: KVM: s390: rename PROT_NONE to PROT_TYPE_DUMMY has been removed from the -mm tree. Its filename was kvm-s390-rename-prot_none-to-prot_type_dummy.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: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: KVM: s390: rename PROT_NONE to PROT_TYPE_DUMMY Date: Mon, 19 May 2025 15:56:57 +0100 The enum type prot_type declared in arch/s390/kvm/gaccess.c declares an unfortunate identifier within it - PROT_NONE. This clashes with the protection bit define from the uapi for mmap() declared in include/uapi/asm-generic/mman-common.h, which is indeed what those casually reading this code would assume this to refer to. This means that any changes which subsequently alter headers in any way which results in the uapi header being imported here will cause build errors. Resolve the issue by renaming PROT_NONE to PROT_TYPE_DUMMY. Link: https://lkml.kernel.org/r/20250519145657.178365-1-lorenzo.stoakes@oracle.com Fixes: b3cefd6bf16e ("KVM: s390: Pass initialized arg even if unused") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: Ignacio Moreno Gonzalez <Ignacio.MorenoGonzalez(a)kuka.com> Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202505140943.IgHDa9s7-lkp@intel.com/ Acked-by: Christian Borntraeger <borntraeger(a)linux.ibm.com> Acked-by: Ignacio Moreno Gonzalez <Ignacio.MorenoGonzalez(a)kuka.com> Acked-by: Yang Shi <yang(a)os.amperecomputing.com> Reviewed-by: David Hildenbrand <david(a)redhat.com> Acked-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Reviewed-by: Claudio Imbrenda <imbrenda(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: James Houghton <jthoughton(a)google.com> Cc: Janosch Frank <frankja(a)linux.ibm.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sven Schnelle <svens(a)linux.ibm.com> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/s390/kvm/gaccess.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) --- a/arch/s390/kvm/gaccess.c~kvm-s390-rename-prot_none-to-prot_type_dummy +++ a/arch/s390/kvm/gaccess.c @@ -319,7 +319,7 @@ enum prot_type { PROT_TYPE_DAT = 3, PROT_TYPE_IEP = 4, /* Dummy value for passing an initialized value when code != PGM_PROTECTION */ - PROT_NONE, + PROT_TYPE_DUMMY, }; static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar, @@ -335,7 +335,7 @@ static int trans_exc_ending(struct kvm_v switch (code) { case PGM_PROTECTION: switch (prot) { - case PROT_NONE: + case PROT_TYPE_DUMMY: /* We should never get here, acts like termination */ WARN_ON_ONCE(1); break; @@ -805,7 +805,7 @@ static int guest_range_to_gpas(struct kv gpa = kvm_s390_real_to_abs(vcpu, ga); if (!kvm_is_gpa_in_memslot(vcpu->kvm, gpa)) { rc = PGM_ADDRESSING; - prot = PROT_NONE; + prot = PROT_TYPE_DUMMY; } } if (rc) @@ -963,7 +963,7 @@ int access_guest_with_key(struct kvm_vcp if (rc == PGM_PROTECTION) prot = PROT_TYPE_KEYC; else - prot = PROT_NONE; + prot = PROT_TYPE_DUMMY; rc = trans_exc_ending(vcpu, rc, ga, ar, mode, prot, terminate); } out_unlock: _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are docs-mm-expand-vma-doc-to-highlight-pte-freeing-non-vma-traversal.patch mm-ksm-have-ksm-vma-checks-not-require-a-vma-pointer.patch mm-ksm-refer-to-special-vmas-via-vm_special-in-ksm_compatible.patch mm-prevent-ksm-from-breaking-vma-merging-for-new-vmas.patch tools-testing-selftests-add-vma-merge-tests-for-ksm-merge.patch mm-pagewalk-split-walk_page_range_novma-into-kernel-user-parts.patch

2 months, 2 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025