January 2025 - Linux-stable-mirror

[PATCH] arm64: Filter out SVE hwcaps when FEAT_SVE isn't implemented

by Marc Zyngier

The hwcaps code that exposes SVE features to userspace only considers ID_AA64ZFR0_EL1, while this is only valid when ID_AA64PFR0_EL1.SVE advertises that SVE is actually supported. The expectations are that when ID_AA64PFR0_EL1.SVE is 0, the ID_AA64ZFR0_EL1 register is also 0. So far, so good. Things become a bit more interesting if the HW implements SME. In this case, a few ID_AA64ZFR0_EL1 fields indicate *SME* features. And these fields overlap with their SVE interpretations. But the architecture says that the SME and SVE feature sets must match, so we're still hunky-dory. This goes wrong if the HW implements SME, but not SVE. In this case, we end-up advertising some SVE features to userspace, even if the HW has none. That's because we never consider whether SVE is actually implemented. Oh well. Fix it by restricting all SVE capabilities to ID_AA64PFR0_EL1.SVE being non-zero. Reported-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Cc: Will Deacon <will(a)kernel.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- arch/arm64/kernel/cpufeature.c | 58 ++++++++++++++++++++++++---------- 1 file changed, 41 insertions(+), 17 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6ce71f444ed84..d793ca08549cd 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1593,14 +1593,19 @@ feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) return val >= min && val <= max; } -static u64 -read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope) +static u64 __read_scoped_sysreg(u64 reg, int scope) { WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); if (scope == SCOPE_SYSTEM) - return read_sanitised_ftr_reg(entry->sys_reg); + return read_sanitised_ftr_reg(reg); else - return __read_sysreg_by_encoding(entry->sys_reg); + return __read_sysreg_by_encoding(reg); +} + +static u64 +read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope) +{ + return __read_scoped_sysreg(entry->sys_reg, scope); } static bool @@ -3022,6 +3027,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = match, \ } +#define HWCAP_CAP_MATCH_ID(match, reg, field, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, min_value) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -3050,6 +3062,18 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { }; #endif +#ifdef CONFIG_ARM64_SVE +static bool has_sve(const struct arm64_cpu_capabilities *cap, int scope) +{ + u64 aa64pfr0 = __read_scoped_sysreg(SYS_ID_AA64PFR0_EL1, scope); + + if (FIELD_GET(ID_AA64PFR0_EL1_SVE, aa64pfr0) < ID_AA64PFR0_EL1_SVE_IMP) + return false; + + return has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3092,19 +3116,19 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), - HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), - HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), - HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), - HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP_MATCH_ID(has_sve, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif #ifdef CONFIG_ARM64_GCS HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), -- 2.39.2

2 days, 2 hours

2
4
0 0

[PATCH AUTOSEL 5.10] ASoC: mediatek: disable buffer pre-allocation

by Sasha Levin

From: Chen-Yu Tsai <wenst(a)chromium.org> [ Upstream commit 32c9c06adb5b157ef259233775a063a43746d699 ] On Chromebooks based on Mediatek MT8195 or MT8188, the audio frontend (AFE) is limited to accessing a very small window (1 MiB) of memory, which is described as a reserved memory region in the device tree. On these two platforms, the maximum buffer size is given as 512 KiB. The MediaTek common code uses the same value for preallocations. This means that only the first two PCM substreams get preallocations, and then the whole space is exhausted, barring any other substreams from working. Since the substreams used are not always the first two, this means audio won't work correctly. This is observed on the MT8188 Geralt Chromebooks, on which the "mediatek,dai-link" property was dropped when it was upstreamed. That property causes the driver to only register the PCM substreams listed in the property, and in the order given. Instead of trying to compute an optimal value and figuring out which streams are used, simply disable preallocation. The PCM buffers are managed by the core and are allocated and released on the fly. There should be no impact to any of the other MediaTek platforms. Signed-off-by: Chen-Yu Tsai <wenst(a)chromium.org> Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno(a)collabora.com> Link: https://patch.msgid.link/20241219105303.548437-1-wenst@chromium.org Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- sound/soc/mediatek/common/mtk-afe-platform-driver.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c index 01501d5747a7..52495c930ca3 100644 --- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c +++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c @@ -120,8 +120,8 @@ int mtk_afe_pcm_new(struct snd_soc_component *component, struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component); size = afe->mtk_afe_hardware->buffer_bytes_max; - snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, - afe->dev, size, size); + snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, afe->dev, 0, size); + return 0; } EXPORT_SYMBOL_GPL(mtk_afe_pcm_new); -- 2.39.5

2 days, 3 hours

1
0
0 0

[PATCH AUTOSEL 5.15] ASoC: mediatek: disable buffer pre-allocation

by Sasha Levin

From: Chen-Yu Tsai <wenst(a)chromium.org> [ Upstream commit 32c9c06adb5b157ef259233775a063a43746d699 ] On Chromebooks based on Mediatek MT8195 or MT8188, the audio frontend (AFE) is limited to accessing a very small window (1 MiB) of memory, which is described as a reserved memory region in the device tree. On these two platforms, the maximum buffer size is given as 512 KiB. The MediaTek common code uses the same value for preallocations. This means that only the first two PCM substreams get preallocations, and then the whole space is exhausted, barring any other substreams from working. Since the substreams used are not always the first two, this means audio won't work correctly. This is observed on the MT8188 Geralt Chromebooks, on which the "mediatek,dai-link" property was dropped when it was upstreamed. That property causes the driver to only register the PCM substreams listed in the property, and in the order given. Instead of trying to compute an optimal value and figuring out which streams are used, simply disable preallocation. The PCM buffers are managed by the core and are allocated and released on the fly. There should be no impact to any of the other MediaTek platforms. Signed-off-by: Chen-Yu Tsai <wenst(a)chromium.org> Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno(a)collabora.com> Link: https://patch.msgid.link/20241219105303.548437-1-wenst@chromium.org Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- sound/soc/mediatek/common/mtk-afe-platform-driver.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c index 01501d5747a7..52495c930ca3 100644 --- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c +++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c @@ -120,8 +120,8 @@ int mtk_afe_pcm_new(struct snd_soc_component *component, struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component); size = afe->mtk_afe_hardware->buffer_bytes_max; - snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, - afe->dev, size, size); + snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, afe->dev, 0, size); + return 0; } EXPORT_SYMBOL_GPL(mtk_afe_pcm_new); -- 2.39.5

2 days, 3 hours

1
0
0 0

[PATCH AUTOSEL 6.1] ASoC: mediatek: disable buffer pre-allocation

by Sasha Levin

From: Chen-Yu Tsai <wenst(a)chromium.org> [ Upstream commit 32c9c06adb5b157ef259233775a063a43746d699 ] On Chromebooks based on Mediatek MT8195 or MT8188, the audio frontend (AFE) is limited to accessing a very small window (1 MiB) of memory, which is described as a reserved memory region in the device tree. On these two platforms, the maximum buffer size is given as 512 KiB. The MediaTek common code uses the same value for preallocations. This means that only the first two PCM substreams get preallocations, and then the whole space is exhausted, barring any other substreams from working. Since the substreams used are not always the first two, this means audio won't work correctly. This is observed on the MT8188 Geralt Chromebooks, on which the "mediatek,dai-link" property was dropped when it was upstreamed. That property causes the driver to only register the PCM substreams listed in the property, and in the order given. Instead of trying to compute an optimal value and figuring out which streams are used, simply disable preallocation. The PCM buffers are managed by the core and are allocated and released on the fly. There should be no impact to any of the other MediaTek platforms. Signed-off-by: Chen-Yu Tsai <wenst(a)chromium.org> Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno(a)collabora.com> Link: https://patch.msgid.link/20241219105303.548437-1-wenst@chromium.org Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- sound/soc/mediatek/common/mtk-afe-platform-driver.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c index 01501d5747a7..52495c930ca3 100644 --- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c +++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c @@ -120,8 +120,8 @@ int mtk_afe_pcm_new(struct snd_soc_component *component, struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component); size = afe->mtk_afe_hardware->buffer_bytes_max; - snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, - afe->dev, size, size); + snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, afe->dev, 0, size); + return 0; } EXPORT_SYMBOL_GPL(mtk_afe_pcm_new); -- 2.39.5

2 days, 3 hours

1
0
0 0

[PATCH AUTOSEL 6.6 1/3] ASoC: rt722: add delay time to wait for the calibration procedure

by Sasha Levin

From: Shuming Fan <shumingf(a)realtek.com> [ Upstream commit c9e3ebdc52ebe028f238c9df5162ae92483bedd5 ] The calibration procedure needs some time to finish. This patch adds the delay time to ensure the calibration procedure is completed correctly. Signed-off-by: Shuming Fan <shumingf(a)realtek.com> Link: https://patch.msgid.link/20241218091307.96656-1-shumingf@realtek.com Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- sound/soc/codecs/rt722-sdca.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index b9b330375add..0f9f592744ad 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1466,13 +1466,18 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) 0x008d); /* check HP calibration FSM status */ for (loop_check = 0; loop_check < chk_cnt; loop_check++) { + usleep_range(10000, 11000); ret = rt722_sdca_index_read(rt722, RT722_VENDOR_CALI, RT722_DAC_DC_CALI_CTL3, &calib_status); - if (ret < 0 || loop_check == chk_cnt) + if (ret < 0) dev_dbg(&rt722->slave->dev, "calibration failed!, ret=%d\n", ret); if ((calib_status & 0x0040) == 0x0) break; } + + if (loop_check == chk_cnt) + dev_dbg(&rt722->slave->dev, "%s, calibration time-out!\n", __func__); + /* Set ADC09 power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL, 0x2a12); -- 2.39.5

2 days, 3 hours

1
2
0 0

[PATCH AUTOSEL 6.12 1/4] perf/x86/intel/uncore: Add Clearwater Forest support

by Sasha Levin

From: Kan Liang <kan.liang(a)linux.intel.com> [ Upstream commit b6ccddd6fe1fd49c7a82b6fbed01cccad21a29c7 ] From the perspective of the uncore PMU, the Clearwater Forest is the same as the previous Sierra Forest. The only difference is the event list, which will be supported in the perf tool later. Signed-off-by: Kan Liang <kan.liang(a)linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lkml.kernel.org/r/20241211161146.235253-1-kan.liang@linux.intel.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- arch/x86/events/intel/uncore.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d98fac567684..e7aba7349231 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1910,6 +1910,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); -- 2.39.5

2 days, 3 hours

1
3
0 0

[PATCH 1/7] mm/hugetlb: Fix avoid_reserve to allow taking folio from subpool

by Peter Xu

Since commit 04f2cbe35699 ("hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed"), avoid_reserve was introduced for a special case of CoW on hugetlb private mappings, and only if the owner VMA is trying to allocate yet another hugetlb folio that is not reserved within the private vma reserved map. Later on, in commit d85f69b0b533 ("mm/hugetlb: alloc_huge_page handle areas hole punched by fallocate"), alloc_huge_page() enforced to not consume any global reservation as long as avoid_reserve=true. This operation doesn't look correct, because even if it will enforce the allocation to not use global reservation at all, it will still try to take one reservation from the spool (if the subpool existed). Then since the spool reserved pages take from global reservation, it'll also take one reservation globally. Logically it can cause global reservation to go wrong. I wrote a reproducer below, trigger this special path, and every run of such program will cause global reservation count to increment by one, until it hits the number of free pages: #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <fcntl.h> #include <errno.h> #include <unistd.h> #include <stdlib.h> #include <sys/mman.h> #define MSIZE (2UL << 20) int main(int argc, char *argv[]) { const char *path; int *buf; int fd, ret; pid_t child; if (argc < 2) { printf("usage: %s <hugetlb_file>\n", argv[0]); return -1; } path = argv[1]; fd = open(path, O_RDWR | O_CREAT, 0666); if (fd < 0) { perror("open failed"); return -1; } ret = fallocate(fd, 0, 0, MSIZE); if (ret != 0) { perror("fallocate"); return -1; } buf = mmap(NULL, MSIZE, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0); if (buf == MAP_FAILED) { perror("mmap() failed"); return -1; } /* Allocate a page */ *buf = 1; child = fork(); if (child == 0) { /* child doesn't need to do anything */ exit(0); } /* Trigger CoW from owner */ *buf = 2; munmap(buf, MSIZE); close(fd); unlink(path); return 0; } It can only reproduce with a sub-mount when there're reserved pages on the spool, like: # sysctl vm.nr_hugepages=128 # mkdir ./hugetlb-pool # mount -t hugetlbfs -o min_size=8M,pagesize=2M none ./hugetlb-pool Then run the reproducer on the mountpoint: # ./reproducer ./hugetlb-pool/test Fix it by taking the reservation from spool if available. In general, avoid_reserve is IMHO more about "avoid vma resv map", not spool's. I copied stable, however I have no intention for backporting if it's not a clean cherry-pick, because private hugetlb mapping, and then fork() on top is too rare to hit. Cc: linux-stable <stable(a)vger.kernel.org> Fixes: d85f69b0b533 ("mm/hugetlb: alloc_huge_page handle areas hole punched by fallocate") Signed-off-by: Peter Xu <peterx(a)redhat.com> --- mm/hugetlb.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..9ce69fd22a01 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1394,8 +1394,7 @@ static unsigned long available_huge_pages(struct hstate *h) static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve, - long chg) + unsigned long address, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; @@ -1411,10 +1410,6 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; - /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && !available_huge_pages(h)) - goto err; - gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); @@ -1430,7 +1425,7 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); - if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { + if (folio && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } @@ -3007,17 +3002,6 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; - - /* - * Even though there was no reservation in the region/reserve - * map, there could be reservations associated with the - * subpool that can be used. This would be indicated if the - * return value of hugepage_subpool_get_pages() is zero. - * However, if avoid_reserve is specified we still avoid even - * the subpool reservations. - */ - if (avoid_reserve) - gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. @@ -3040,7 +3024,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ - folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); + folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); -- 2.47.0

2 days, 4 hours

2
3
0 0

[PATCH v8] tpm: Map the ACPI provided event log

by Jarkko Sakkinen

The following failure was reported: [ 10.693310][ T1] tpm_tis STM0925:00: 2.0 TPM (device-id 0x3, rev-id 0) [ 10.848132][ T1] ------------[ cut here ]------------ [ 10.853559][ T1] WARNING: CPU: 59 PID: 1 at mm/page_alloc.c:4727 __alloc_pages_noprof+0x2ca/0x330 [ 10.862827][ T1] Modules linked in: [ 10.866671][ T1] CPU: 59 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0-lp155.2.g52785e2-default #1 openSUSE Tumbleweed (unreleased) 588cd98293a7c9eba9013378d807364c088c9375 [ 10.882741][ T1] Hardware name: HPE ProLiant DL320 Gen12/ProLiant DL320 Gen12, BIOS 1.20 10/28/2024 [ 10.892170][ T1] RIP: 0010:__alloc_pages_noprof+0x2ca/0x330 [ 10.898103][ T1] Code: 24 08 e9 4a fe ff ff e8 34 36 fa ff e9 88 fe ff ff 83 fe 0a 0f 86 b3 fd ff ff 80 3d 01 e7 ce 01 00 75 09 c6 05 f8 e6 ce 01 01 <0f> 0b 45 31 ff e9 e5 fe ff ff f7 c2 00 00 08 00 75 42 89 d9 80 e1 [ 10.917750][ T1] RSP: 0000:ffffb7cf40077980 EFLAGS: 00010246 [ 10.923777][ T1] RAX: 0000000000000000 RBX: 0000000000040cc0 RCX: 0000000000000000 [ 10.931727][ T1] RDX: 0000000000000000 RSI: 000000000000000c RDI: 0000000000040cc0 Above shows that ACPI pointed a 16 MiB buffer for the log events because RSI maps to the 'order' parameter of __alloc_pages_noprof(). Address the bug with kvmalloc() and devm_add_action_or_reset(). Suggested-by: Ard Biesheuvel <ardb(a)kernel.org> Cc: stable(a)vger.kernel.org # v2.6.16+ Fixes: 55a82ab3181b ("[PATCH] tpm: add bios measurement log") Reported-by: Andy Liang <andy.liang(a)hpe.com> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219495 Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v8: * Reduced to only to this quick fix. Let HPE reserve 16 MiB if they want to. We have mapping approach backed up in lore. v7: * Use devm_add_action_or_reset(). * Fix tags. v6: * A new patch. --- drivers/char/tpm/eventlog/acpi.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 69533d0bfb51..394c8302cefd 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -63,6 +63,11 @@ static bool tpm_is_tpm2_log(void *bios_event_log, u64 len) return n == 0; } +static void tpm_bios_log_free(void *data) +{ + kvfree(data); +} + /* read binary bios log */ int tpm_read_log_acpi(struct tpm_chip *chip) { @@ -136,10 +141,16 @@ int tpm_read_log_acpi(struct tpm_chip *chip) } /* malloc EventLog space */ - log->bios_event_log = devm_kmalloc(&chip->dev, len, GFP_KERNEL); + log->bios_event_log = kvmalloc(len, GFP_KERNEL); if (!log->bios_event_log) return -ENOMEM; + ret = devm_add_action_or_reset(&chip->dev, tpm_bios_log_free, log->bios_event_log); + if (ret) { + log->bios_event_log = NULL; + return ret; + } + log->bios_event_log_end = log->bios_event_log + len; virt = acpi_os_map_iomem(start, len); -- 2.47.1

2 days, 4 hours

2
1
0 0

[PATCH 1/2] dm-verity FEC: Fix RS FEC repair for roots unaligned to block size (take 2)

by Milan Broz

This patch fixes an issue that was fixed in the commit df7b59ba9245 ("dm verity: fix FEC for RS roots unaligned to block size") but later broken again in the commit 8ca7cab82bda ("dm verity fec: fix misaligned RS roots IO") If the Reed-Solomon roots setting spans multiple blocks, the code does not use proper parity bytes and randomly fails to repair even trivial errors. This bug cannot happen if the sector size is multiple of RS roots setting (Android case with roots 2). The previous solution was to find a dm-bufio block size that is multiple of the device sector size and roots size. Unfortunately, the optimization in commit 8ca7cab82bda ("dm verity fec: fix misaligned RS roots IO") is incorrect and uses data block size for some roots (for example, it uses 4096 block size for roots = 20). This patch uses a different approach: - It always uses a configured data block size for dm-bufio to avoid possible misaligned IOs. - and it caches the processed parity bytes, so it can join it if it spans two blocks. As the RS calculation is called only if an error is detected and the process is computationally intensive, copying a few more bytes should not introduce performance issues. The issue was reported to cryptsetup with trivial reproducer https://gitlab.com/cryptsetup/cryptsetup/-/issues/923 Reproducer (with roots=20): # create verity device with RS FEC dd if=/dev/urandom of=data.img bs=4096 count=8 status=none veritysetup format data.img hash.img --fec-device=fec.img --fec-roots=20 | \ awk '/^Root hash/{ print $3 }' >roothash # create an erasure that should always be repairable with this roots setting dd if=/dev/zero of=data.img conv=notrunc bs=1 count=4 seek=4 status=none # try to read it through dm-verity veritysetup open data.img test hash.img --fec-device=fec.img --fec-roots=20 $(cat roothash) dd if=/dev/mapper/test of=/dev/null bs=4096 status=noxfer Even now the log says it cannot repair it: : verity-fec: 7:1: FEC 0: failed to correct: -74 : device-mapper: verity: 7:1: data block 0 is corrupted ... With this fix, errors are properly repaired. : verity-fec: 7:1: FEC 0: corrected 4 errors Signed-off-by: Milan Broz <gmazyland(a)gmail.com> Fixes: 8ca7cab82bda ("dm verity fec: fix misaligned RS roots IO") Cc: stable(a)vger.kernel.org --- drivers/md/dm-verity-fec.c | 40 +++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 62b1a44b8dd2..6bd9848518d4 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -60,15 +60,19 @@ static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, * to the data block. Caller is responsible for releasing buf. */ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, - unsigned int *offset, struct dm_buffer **buf, - unsigned short ioprio) + unsigned int *offset, unsigned int par_buf_offset, + struct dm_buffer **buf, unsigned short ioprio) { u64 position, block, rem; u8 *res; + /* We have already part of parity bytes read, skip to the next block */ + if (par_buf_offset) + index++; + position = (index + rsb) * v->fec->roots; block = div64_u64_rem(position, v->fec->io_size, &rem); - *offset = (unsigned int)rem; + *offset = par_buf_offset ? 0 : (unsigned int)rem; res = dm_bufio_read_with_ioprio(v->fec->bufio, block, buf, ioprio); if (IS_ERR(res)) { @@ -128,11 +132,12 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, { int r, corrected = 0, res; struct dm_buffer *buf; - unsigned int n, i, offset; - u8 *par, *block; + unsigned int n, i, offset, par_buf_offset = 0; + u8 *par, *block, par_buf[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); @@ -142,7 +147,8 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, */ fec_for_each_buffer_rs_block(fio, n, i) { block = fec_buffer_rs_block(v, fio, n, i); - res = fec_decode_rs8(v, fio, block, &par[offset], neras); + memcpy(&par_buf[par_buf_offset], &par[offset], v->fec->roots - par_buf_offset); + res = fec_decode_rs8(v, fio, block, par_buf, neras); if (res < 0) { r = res; goto error; @@ -155,12 +161,21 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, if (block_offset >= 1 << v->data_dev_block_bits) goto done; - /* read the next block when we run out of parity bytes */ - offset += v->fec->roots; + /* Read the next block when we run out of parity bytes */ + offset += (v->fec->roots - par_buf_offset); + /* Check if parity bytes are split between blocks */ + if (offset < v->fec->io_size && (offset + v->fec->roots) > v->fec->io_size) { + par_buf_offset = v->fec->io_size - offset; + memcpy(par_buf, &par[offset], par_buf_offset); + offset += par_buf_offset; + } else + par_buf_offset = 0; + if (offset >= v->fec->io_size) { dm_bufio_release(buf); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); } @@ -724,10 +739,7 @@ int verity_fec_ctr(struct dm_verity *v) return -E2BIG; } - if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1)) - f->io_size = 1 << v->data_dev_block_bits; - else - f->io_size = v->fec->roots << SECTOR_SHIFT; + f->io_size = 1 << v->data_dev_block_bits; f->bufio = dm_bufio_client_create(f->dev->bdev, f->io_size, -- 2.45.2

2 days, 4 hours

2
1
0 0

FAILED: patch "[PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation" 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 bcc80dec91ee745b3d66f3e48f0ec2efdea97149 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024122324-twitter-clustered-891d@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bcc80dec91ee745b3d66f3e48f0ec2efdea97149 Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Tue, 17 Sep 2024 11:09:17 +0530 Subject: [PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is bigger than the variable hv_sched_clock_offset, which is cached during early boot, but depending on the timing this assumption may be false when a hibernated VM starts again (the clock counter starts from 0 again) and is resuming back (Note: hv_init_tsc_clocksource() is not called during hibernation/resume); consequently, read_hv_sched_clock_tsc() may return a negative integer (which is interpreted as a huge positive integer since the return type is u64) and new kernel messages are prefixed with huge timestamps before read_hv_sched_clock_tsc() grows big enough (which typically takes several seconds). Fix the issue by saving the Hyper-V clock counter just before the suspend, and using it to correct the hv_sched_clock_offset in resume. This makes hv tsc page based sched_clock continuous and ensures that post resume, it starts from where it left off during suspend. Override x86_platform.save_sched_clock_state and x86_platform.restore_sched_clock_state routines to correct this as soon as possible. Note: if Invariant TSC is available, the issue doesn't happen because 1) we don't register read_hv_sched_clock_tsc() for sched clock: See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework clocksource and sched clock setup"); 2) the common x86 code adjusts TSC similarly: see __restore_processor_state() -> tsc_verify_tsc_adjust(true) and x86_platform.restore_sched_clock_state(). Cc: stable(a)vger.kernel.org Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation") Co-developed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu(a)kernel.org> Message-ID: <20240917053917.76787-1-namjain(a)linux.microsoft.com> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)

2 days, 5 hours

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2025