August 2018 - Linux-stable-mirror

[PATCH v2 2/3] x86/mm: add .data..decrypted section to hold shared variables

by Brijesh Singh

kvmclock defines few static variables which are shared with hypervisor during the kvmclock initialization. When SEV is active, memory is encrypted with a guest-specific key, and if guest OS wants to share the memory region with hypervisor then it must clear the C-bit before sharing it. Currently, we use kernel_physical_mapping_init() to split large pages before clearing the C-bit on shared pages. But the kernel_physical_mapping_init fails when called from the kvmclock initialization (mainly because memblock allocator was not ready). The '__decrypted' can be used to define a shared variable; the variables will be put in the .data.decryption section. This section is mapped with C=0 early in the boot, we also ensure that the initialized values are updated to match with C=0 (i.e perform an in-place decryption). The .data..decrypted section is PMD aligned and sized so that we avoid the need to split the large pages when mapping this section. The sme_encrypt_kernel() was used to perform the in-place encryption of the Linux kernel and initrd when SME is active. The routine has been enhanced to decrypt the .data..decryption section for both SME and SEV cases. While reusing the sme_populate_pgd() we found that the function does not update the flags if the pte/pmd entry already exists. The patch updates the function to take care of it. Signed-off-by: Brijesh Singh <brijesh.singh(a)amd.com> Cc: stable(a)vger.kernel.org Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: kvm(a)vger.kernel.org Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Borislav Petkov <bp(a)suse.de> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: linux-kernel(a)vger.kernel.org Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <sean.j.christopherson(a)intel.com> Cc: kvm(a)vger.kernel.org Cc: "Radim Krčmář" <rkrcmar(a)redhat.com> --- arch/x86/include/asm/mem_encrypt.h | 6 +++ arch/x86/kernel/head64.c | 9 ++++ arch/x86/kernel/vmlinux.lds.S | 17 +++++++ arch/x86/mm/mem_encrypt_identity.c | 100 +++++++++++++++++++++++++++++-------- 4 files changed, 112 insertions(+), 20 deletions(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c064383..802b2eb 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -52,6 +52,8 @@ void __init mem_encrypt_init(void); bool sme_active(void); bool sev_active(void); +#define __decrypted __attribute__((__section__(".data..decrypted"))) + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -77,6 +79,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +#define __decrypted + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* @@ -88,6 +92,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; #define __sme_pa(x) (__pa(x) | sme_me_mask) #define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) +extern char __start_data_decrypted[], __end_data_decrypted[]; + #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8047379..3e03129 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -112,6 +112,7 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { + unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -234,6 +235,14 @@ unsigned long __head __startup_64(unsigned long physaddr, /* Encrypt the kernel and related (if SME is active) */ sme_encrypt_kernel(bp); + /* Clear the memory encryption mask from the decrypted section */ + vaddr = (unsigned long)__start_data_decrypted; + vaddr_end = (unsigned long)__end_data_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + /* * Return the SME encryption mask (if SME is active) to be used as a * modifier for the initial pgdir entry programmed into CR3. diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8bde0a4..0ef9320 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -89,6 +89,21 @@ PHDRS { note PT_NOTE FLAGS(0); /* ___ */ } +/* + * This section contains data which will be mapped as decrypted. Memory + * encryption operates on a page basis. But we make this section a pmd + * aligned to avoid spliting the pages while mapping the section early. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#define DATA_DECRYPTED_SECTION \ + . = ALIGN(PMD_SIZE); \ + __start_data_decrypted = .; \ + *(.data..decrypted); \ + . = ALIGN(PMD_SIZE); \ + __end_data_decrypted = .; \ + SECTIONS { #ifdef CONFIG_X86_32 @@ -171,6 +186,8 @@ SECTIONS /* rarely changed data like cpu maps */ READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES) + DATA_DECRYPTED_SECTION + /* End of data section */ _edata = .; } :data diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index bf6097e..88c1cce 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -51,6 +51,8 @@ (_PAGE_PAT | _PAGE_PWT)) #define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) +#define PMD_FLAGS_ENC_WP ((PMD_FLAGS_ENC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) #define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) @@ -59,6 +61,8 @@ (_PAGE_PAT | _PAGE_PWT)) #define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) +#define PTE_FLAGS_ENC_WP ((PTE_FLAGS_ENC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) struct sme_populate_pgd_data { void *pgtable_area; @@ -154,9 +158,6 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) return; pmd = pmd_offset(pud, ppd->vaddr); - if (pmd_large(*pmd)) - return; - set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); } @@ -182,8 +183,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) return; pte = pte_offset_map(pmd, ppd->vaddr); - if (pte_none(*pte)) - set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); + set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); } static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) @@ -235,6 +235,11 @@ static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); } +static void __init sme_map_range_encrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC_WP, PTE_FLAGS_ENC_WP); +} + static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); @@ -382,7 +387,10 @@ static void __init build_workarea_map(struct boot_params *bp, ppd->paddr = workarea_start; ppd->vaddr = workarea_start; ppd->vaddr_end = workarea_end; - sme_map_range_decrypted(ppd); + if (sev_active()) + sme_map_range_encrypted(ppd); + else + sme_map_range_decrypted(ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); @@ -439,16 +447,27 @@ static void __init build_workarea_map(struct boot_params *bp, sme_map_range_decrypted_wp(ppd); } - /* Add decrypted workarea mappings to both kernel mappings */ + /* + * When SEV is active, kernel is already encrypted hence mapping + * the initial workarea_start as encrypted. When SME is active, + * the kernel is not encrypted hence add a decrypted workarea + * mappings to both kernel mappings. + */ ppd->paddr = workarea_start; ppd->vaddr = workarea_start; ppd->vaddr_end = workarea_end; - sme_map_range_decrypted(ppd); + if (sev_active()) + sme_map_range_encrypted(ppd); + else + sme_map_range_decrypted(ppd); ppd->paddr = workarea_start; ppd->vaddr = workarea_start + decrypted_base; ppd->vaddr_end = workarea_end + decrypted_base; - sme_map_range_decrypted(ppd); + if (sev_active()) + sme_map_range_encrypted(ppd); + else + sme_map_range_decrypted(ppd); wa->kernel_start = kernel_start; wa->kernel_end = kernel_end; @@ -491,28 +510,69 @@ static void __init remove_workarea_map(struct sme_workarea_data *wa, native_write_cr3(__native_read_cr3()); } +static void __init decrypt_data_decrypted_section(struct sme_workarea_data *wa, + struct sme_populate_pgd_data *ppd) +{ + unsigned long decrypted_start, decrypted_end, decrypted_len; + + /* Physical addresses of decrypted data section */ + decrypted_start = __pa_symbol(__start_data_decrypted); + decrypted_end = ALIGN(__pa_symbol(__end_data_decrypted), PMD_PAGE_SIZE); + decrypted_len = decrypted_end - decrypted_start; + + if (!decrypted_len) + return; + + /* Add decrypted mapping for the section (identity) */ + ppd->paddr = decrypted_start; + ppd->vaddr = decrypted_start; + ppd->vaddr_end = decrypted_end; + sme_map_range_decrypted(ppd); + + /* Add encrypted-wp mapping for the section (non-identity) */ + ppd->paddr = decrypted_start; + ppd->vaddr = decrypted_start + wa->decrypted_base; + ppd->vaddr_end = decrypted_end + wa->decrypted_base; + sme_map_range_encrypted_wp(ppd); + + /* Perform in-place decryption */ + sme_encrypt_execute(decrypted_start, + decrypted_start + wa->decrypted_base, + decrypted_len, wa->workarea_start, + (unsigned long)ppd->pgd); + + ppd->vaddr = decrypted_start + wa->decrypted_base; + ppd->vaddr_end = decrypted_end + wa->decrypted_base; + sme_clear_pgd(ppd); +} + void __init sme_encrypt_kernel(struct boot_params *bp) { struct sme_populate_pgd_data ppd; struct sme_workarea_data wa; - if (!sme_active()) + if (!mem_encrypt_active()) return; build_workarea_map(bp, &wa, &ppd); - /* When SEV is active, encrypt kernel and initrd */ - sme_encrypt_execute(wa.kernel_start, - wa.kernel_start + wa.decrypted_base, - wa.kernel_len, wa.workarea_start, - (unsigned long)ppd.pgd); - - if (wa.initrd_len) - sme_encrypt_execute(wa.initrd_start, - wa.initrd_start + wa.decrypted_base, - wa.initrd_len, wa.workarea_start, + /* When SME is active, encrypt kernel and initrd */ + if (sme_active()) { + sme_encrypt_execute(wa.kernel_start, + wa.kernel_start + wa.decrypted_base, + wa.kernel_len, wa.workarea_start, (unsigned long)ppd.pgd); + if (wa.initrd_len) + sme_encrypt_execute(wa.initrd_start, + wa.initrd_start + wa.decrypted_base, + wa.initrd_len, wa.workarea_start, + (unsigned long)ppd.pgd); + } + + /* Decrypt the contents of .data..decrypted section */ + decrypt_data_decrypted_section(&wa, &ppd); + remove_workarea_map(&wa, &ppd); } -- 2.7.4

6 years, 1 month

3
7
0 0

[PATCH v4] drm/i915: Re-apply "Perform link quality check, unconditionally during long pulse"

by Lyude Paul

From: Jan-Marek Glogowski <glogow(a)fbihome.de> This re-applies the workaround for "some DP sinks, [which] are a little nuts" from commit 1a36147bb939 ("drm/i915: Perform link quality check unconditionally during long pulse"). It makes the secondary AOC E2460P monitor connected via DP to an acer Veriton N4640G usable again. This hunk was dropped in commit c85d200e8321 ("drm/i915: Move SST DP link retraining into the ->post_hotplug() hook") Fixes: c85d200e8321 ("drm/i915: Move SST DP link retraining into the ->post_hotplug() hook") [Cleaned up commit message, added stable cc] Signed-off-by: Lyude Paul <lyude(a)redhat.com> Signed-off-by: Jan-Marek Glogowski <glogow(a)fbihome.de> Cc: stable(a)vger.kernel.org --- Resending this to update patchwork; will push in a little bit drivers/gpu/drm/i915/intel_dp.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index b3f6f04c3c7d..db8515171270 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4333,18 +4333,6 @@ intel_dp_needs_link_retrain(struct intel_dp *intel_dp) return !drm_dp_channel_eq_ok(link_status, intel_dp->lane_count); } -/* - * If display is now connected check links status, - * there has been known issues of link loss triggering - * long pulse. - * - * Some sinks (eg. ASUS PB287Q) seem to perform some - * weird HPD ping pong during modesets. So we can apparently - * end up with HPD going low during a modeset, and then - * going back up soon after. And once that happens we must - * retrain the link to get a picture. That's in case no - * userspace component reacted to intermittent HPD dip. - */ int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx) { @@ -5031,7 +5019,8 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) } static int -intel_dp_long_pulse(struct intel_connector *connector) +intel_dp_long_pulse(struct intel_connector *connector, + struct drm_modeset_acquire_ctx *ctx) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_dp *intel_dp = intel_attached_dp(&connector->base); @@ -5090,6 +5079,22 @@ intel_dp_long_pulse(struct intel_connector *connector) */ status = connector_status_disconnected; goto out; + } else { + /* + * If display is now connected check links status, + * there has been known issues of link loss triggering + * long pulse. + * + * Some sinks (eg. ASUS PB287Q) seem to perform some + * weird HPD ping pong during modesets. So we can apparently + * end up with HPD going low during a modeset, and then + * going back up soon after. And once that happens we must + * retrain the link to get a picture. That's in case no + * userspace component reacted to intermittent HPD dip. + */ + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + + intel_dp_retrain_link(encoder, ctx); } /* @@ -5151,7 +5156,7 @@ intel_dp_detect(struct drm_connector *connector, return ret; } - status = intel_dp_long_pulse(intel_dp->attached_connector); + status = intel_dp_long_pulse(intel_dp->attached_connector, ctx); } intel_dp->detect_done = false; -- 2.17.1

6 years, 1 month

5
9
0 0

[PATCH] PM / devfreq: Add new name attribute for sysfs

by Chanwoo Choi

commit 4585fbcb5331 ("PM / devfreq: Modify the device name as devfreq(X) for sysfs") changed the node name to devfreq(x). After this commit, it is not possible to get the device name through /sys/class/devfreq/devfreq(X)/*. Add new name attribute in order to get device name. Cc: stable(a)vger.kernel.org Fixes: 4585fbcb5331 ("PM / devfreq: Modify the device name as devfreq(X) for sysfs") Signed-off-by: Chanwoo Choi <cw00.choi(a)samsung.com> --- drivers/devfreq/devfreq.c | 11 +++++++++++ include/linux/devfreq.h | 3 +++ 2 files changed, 14 insertions(+) diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 4c49bb1330b5..2145563d5ee5 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -620,6 +620,9 @@ struct devfreq *devfreq_add_device(struct device *dev, } devfreq->max_freq = devfreq->scaling_max_freq; + devfreq->name = dev_name(devfreq->dev.parent); + if (IS_ERR_OR_NULL(devfreq->name)) + return -EINVAL; dev_set_name(&devfreq->dev, "devfreq%d", atomic_inc_return(&devfreq_no)); err = device_register(&devfreq->dev); @@ -1261,6 +1264,13 @@ static ssize_t trans_stat_show(struct device *dev, } static DEVICE_ATTR_RO(trans_stat); +static ssize_t name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", to_devfreq(dev)->name); +} +static DEVICE_ATTR_RO(name); + static struct attribute *devfreq_attrs[] = { &dev_attr_governor.attr, &dev_attr_available_governors.attr, @@ -1271,6 +1281,7 @@ static ssize_t trans_stat_show(struct device *dev, &dev_attr_min_freq.attr, &dev_attr_max_freq.attr, &dev_attr_trans_stat.attr, + &dev_attr_name.attr, NULL, }; ATTRIBUTE_GROUPS(devfreq); diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 3aae5b3af87c..f79b5a666102 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -111,6 +111,7 @@ struct devfreq_dev_profile { /** * struct devfreq - Device devfreq structure + * @name: name of the device * @node: list node - contains the devices with devfreq that have been * registered. * @lock: a mutex to protect accessing devfreq. @@ -146,6 +147,8 @@ struct devfreq_dev_profile { * to protect its own private data in void *data as well. */ struct devfreq { + const char *name; + struct list_head node; struct mutex lock; -- 1.9.1

6 years, 1 month

3
4
0 0

[PATCH RESEND v3 1/6] drm/nouveau: Check backlight IDs are >= 0, not > 0

by Lyude Paul

Remember, ida IDs start at 0, not 1! Signed-off-by: Lyude Paul <lyude(a)redhat.com> Reviewed-by: Karol Herbst <kherbst(a)redhat.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/nouveau/nouveau_backlight.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index 408b955e5c39..6dd72bc32897 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -116,7 +116,7 @@ nv40_backlight_init(struct drm_connector *connector) &nv40_bl_ops, &props); if (IS_ERR(bd)) { - if (bl_connector.id > 0) + if (bl_connector.id >= 0) ida_simple_remove(&bl_ida, bl_connector.id); return PTR_ERR(bd); } @@ -249,7 +249,7 @@ nv50_backlight_init(struct drm_connector *connector) nv_encoder, ops, &props); if (IS_ERR(bd)) { - if (bl_connector.id > 0) + if (bl_connector.id >= 0) ida_simple_remove(&bl_ida, bl_connector.id); return PTR_ERR(bd); } -- 2.17.1

6 years, 1 month

1
0
0 0

[PATCH v2 1/5] drm/nouveau: Check backlight IDs are >= 0, not > 0

by Lyude Paul

Remember, ida IDs start at 0, not 1! Signed-off-by: Lyude Paul <lyude(a)redhat.com> Reviewed-by: Karol Herbst <kherbst(a)redhat.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/nouveau/nouveau_backlight.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index 408b955e5c39..6dd72bc32897 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -116,7 +116,7 @@ nv40_backlight_init(struct drm_connector *connector) &nv40_bl_ops, &props); if (IS_ERR(bd)) { - if (bl_connector.id > 0) + if (bl_connector.id >= 0) ida_simple_remove(&bl_ida, bl_connector.id); return PTR_ERR(bd); } @@ -249,7 +249,7 @@ nv50_backlight_init(struct drm_connector *connector) nv_encoder, ops, &props); if (IS_ERR(bd)) { - if (bl_connector.id > 0) + if (bl_connector.id >= 0) ida_simple_remove(&bl_ida, bl_connector.id); return PTR_ERR(bd); } -- 2.17.1

6 years, 1 month

1
0
0 0

[PATCH v2 2/2] ARM: dts: exynos: Mark 1GHz CPU OPP as suspend OPP

by Marek Szyprowski

1GHz CPU OPP is the default boot value for the Exynos5250 SOC, so mark it as suspend OPP. This fixes suspend/resume on Samsung Exynos5250 Snow Chomebook, which was broken since switching to generic cpufreq-dt driver in v4.3. CC: <stable(a)vger.kernel.org> # 4.3.x: cd6f55457eb4 ARM: dts: exynos: Remove "cooling-{min|max}-level" for CPU nodes CC: <stable(a)vger.kernel.org> # 4.3.x: 672f33198bee arm: dts: exynos: Add missing cooling device properties for CPUs CC: <stable(a)vger.kernel.org> # 4.3.x Signed-off-by: Marek Szyprowski <m.szyprowski(a)samsung.com> Reviewed-by: Chanwoo Choi <cw00.choi(a)samsung.com> Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie(a)samsung.com> --- arch/arm/boot/dts/exynos5250.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index 8746189990eb..b85527faa6ea 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -118,6 +118,7 @@ opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <1075000>; clock-latency-ns = <140000>; + opp-suspend; }; opp-1100000000 { opp-hz = /bits/ 64 <1100000000>; -- 2.17.1

6 years, 1 month

2
1
0 0

[PATCH v2 1/2] ARM: dts: exynos: Convert exynos5250.dtsi to opp-v2 bindings

by Marek Szyprowski

Convert Exynos5250 to OPP-v2 bindings. This is a preparation to add proper support for suspend operation point, which cannot be marked in opp-v1. CC: <stable(a)vger.kernel.org> # 4.3.x: cd6f55457eb4 ARM: dts: exynos: Remove "cooling-{min|max}-level" for CPU nodes CC: <stable(a)vger.kernel.org> # 4.3.x: 672f33198bee arm: dts: exynos: Add missing cooling device properties for CPUs CC: <stable(a)vger.kernel.org> # 4.3.x Signed-off-by: Marek Szyprowski <m.szyprowski(a)samsung.com> Reviewed-by: Chanwoo Choi <cw00.choi(a)samsung.com> Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie(a)samsung.com> --- arch/arm/boot/dts/exynos5250.dtsi | 130 ++++++++++++++++++++---------- 1 file changed, 88 insertions(+), 42 deletions(-) diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index da163a40af15..8746189990eb 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -54,62 +54,108 @@ device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <0>; - clock-frequency = <1700000000>; clocks = <&clock CLK_ARM_CLK>; clock-names = "cpu"; - clock-latency = <140000>; - - operating-points = < - 1700000 1300000 - 1600000 1250000 - 1500000 1225000 - 1400000 1200000 - 1300000 1150000 - 1200000 1125000 - 1100000 1100000 - 1000000 1075000 - 900000 1050000 - 800000 1025000 - 700000 1012500 - 600000 1000000 - 500000 975000 - 400000 950000 - 300000 937500 - 200000 925000 - >; + operating-points-v2 = <&cpu0_opp_table>; #cooling-cells = <2>; /* min followed by max */ }; cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a15"; reg = <1>; - clock-frequency = <1700000000>; clocks = <&clock CLK_ARM_CLK>; clock-names = "cpu"; - clock-latency = <140000>; - - operating-points = < - 1700000 1300000 - 1600000 1250000 - 1500000 1225000 - 1400000 1200000 - 1300000 1150000 - 1200000 1125000 - 1100000 1100000 - 1000000 1075000 - 900000 1050000 - 800000 1025000 - 700000 1012500 - 600000 1000000 - 500000 975000 - 400000 950000 - 300000 937500 - 200000 925000 - >; + operating-points-v2 = <&cpu0_opp_table>; #cooling-cells = <2>; /* min followed by max */ }; }; + cpu0_opp_table: opp_table0 { + compatible = "operating-points-v2"; + opp-shared; + + opp-200000000 { + opp-hz = /bits/ 64 <200000000>; + opp-microvolt = <925000>; + clock-latency-ns = <140000>; + }; + opp-300000000 { + opp-hz = /bits/ 64 <300000000>; + opp-microvolt = <937500>; + clock-latency-ns = <140000>; + }; + opp-400000000 { + opp-hz = /bits/ 64 <400000000>; + opp-microvolt = <950000>; + clock-latency-ns = <140000>; + }; + opp-500000000 { + opp-hz = /bits/ 64 <500000000>; + opp-microvolt = <975000>; + clock-latency-ns = <140000>; + }; + opp-600000000 { + opp-hz = /bits/ 64 <600000000>; + opp-microvolt = <1000000>; + clock-latency-ns = <140000>; + }; + opp-700000000 { + opp-hz = /bits/ 64 <700000000>; + opp-microvolt = <1012500>; + clock-latency-ns = <140000>; + }; + opp-800000000 { + opp-hz = /bits/ 64 <800000000>; + opp-microvolt = <1025000>; + clock-latency-ns = <140000>; + }; + opp-900000000 { + opp-hz = /bits/ 64 <900000000>; + opp-microvolt = <1050000>; + clock-latency-ns = <140000>; + }; + opp-1000000000 { + opp-hz = /bits/ 64 <1000000000>; + opp-microvolt = <1075000>; + clock-latency-ns = <140000>; + }; + opp-1100000000 { + opp-hz = /bits/ 64 <1100000000>; + opp-microvolt = <1100000>; + clock-latency-ns = <140000>; + }; + opp-1200000000 { + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = <1125000>; + clock-latency-ns = <140000>; + }; + opp-1300000000 { + opp-hz = /bits/ 64 <1300000000>; + opp-microvolt = <1150000>; + clock-latency-ns = <140000>; + }; + opp-1400000000 { + opp-hz = /bits/ 64 <1400000000>; + opp-microvolt = <1200000>; + clock-latency-ns = <140000>; + }; + opp-1500000000 { + opp-hz = /bits/ 64 <1500000000>; + opp-microvolt = <1225000>; + clock-latency-ns = <140000>; + }; + opp-1600000000 { + opp-hz = /bits/ 64 <1600000000>; + opp-microvolt = <1250000>; + clock-latency-ns = <140000>; + }; + opp-1700000000 { + opp-hz = /bits/ 64 <1700000000>; + opp-microvolt = <1300000>; + clock-latency-ns = <140000>; + }; + }; + soc: soc { sysram@2020000 { compatible = "mmio-sram"; -- 2.17.1

6 years, 1 month

2
1
0 0

FAILED: patch "[PATCH] Btrfs: fix mount failure after fsync due to hard link" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 0d836392cadd5535f4184d46d901a82eb276ed62 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Fri, 20 Jul 2018 10:59:06 +0100 Subject: [PATCH] Btrfs: fix mount failure after fsync due to hard link recreation If we end up with logging an inode reference item which has the same name but different index from the one we have persisted, we end up failing when replaying the log with an errno value of -EEXIST. The error comes from btrfs_add_link(), which is called from add_inode_ref(), when we are replaying an inode reference item. Example scenario where this happens: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ touch /mnt/foo $ ln /mnt/foo /mnt/bar $ sync # Rename the first hard link (foo) to a new name and rename the second # hard link (bar) to the old name of the first hard link (foo). $ mv /mnt/foo /mnt/qwerty $ mv /mnt/bar /mnt/foo # Create a new file, in the same parent directory, with the old name of # the second hard link (bar) and fsync this new file. # We do this instead of calling fsync on foo/qwerty because if we did # that the fsync resulted in a full transaction commit, not triggering # the problem. $ touch /mnt/bar $ xfs_io -c "fsync" /mnt/bar <power fail> $ mount /dev/sdb /mnt mount: mount /dev/sdb on /mnt failed: File exists So fix this by checking if a conflicting inode reference exists (same name, same parent but different index), removing it (and the associated dir index entries from the parent inode) if it exists, before attempting to add the new reference. A test case for fstests follows soon. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 10f6a4223897..033aeebbe9de 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1290,6 +1290,46 @@ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, return ret; } +static int btrfs_inode_ref_exists(struct inode *inode, struct inode *dir, + const u8 ref_type, const char *name, + const int namelen) +{ + struct btrfs_key key; + struct btrfs_path *path; + const u64 parent_id = btrfs_ino(BTRFS_I(dir)); + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = ref_type; + if (key.type == BTRFS_INODE_REF_KEY) + key.offset = parent_id; + else + key.offset = btrfs_extref_hash(parent_id, name, namelen); + + ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &key, path, 0, 0); + if (ret < 0) + goto out; + if (ret > 0) { + ret = 0; + goto out; + } + if (key.type == BTRFS_INODE_EXTREF_KEY) + ret = btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], parent_id, + name, namelen, NULL); + else + ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, namelen, NULL); + +out: + btrfs_free_path(path); + return ret; +} + /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. @@ -1399,6 +1439,32 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } } + /* + * If a reference item already exists for this inode + * with the same parent and name, but different index, + * drop it and the corresponding directory index entries + * from the parent before adding the new reference item + * and dir index entries, otherwise we would fail with + * -EEXIST returned from btrfs_add_link() below. + */ + ret = btrfs_inode_ref_exists(inode, dir, key->type, + name, namelen); + if (ret > 0) { + ret = btrfs_unlink_inode(trans, root, + BTRFS_I(dir), + BTRFS_I(inode), + name, namelen); + /* + * If we dropped the link count to 0, bump it so + * that later the iput() on the inode will not + * free it. We will fixup the link count later. + */ + if (!ret && inode->i_nlink == 0) + inc_nlink(inode); + } + if (ret < 0) + goto out; + /* insert our name */ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),

6 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix mount failure after fsync due to hard link" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 0d836392cadd5535f4184d46d901a82eb276ed62 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Fri, 20 Jul 2018 10:59:06 +0100 Subject: [PATCH] Btrfs: fix mount failure after fsync due to hard link recreation If we end up with logging an inode reference item which has the same name but different index from the one we have persisted, we end up failing when replaying the log with an errno value of -EEXIST. The error comes from btrfs_add_link(), which is called from add_inode_ref(), when we are replaying an inode reference item. Example scenario where this happens: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ touch /mnt/foo $ ln /mnt/foo /mnt/bar $ sync # Rename the first hard link (foo) to a new name and rename the second # hard link (bar) to the old name of the first hard link (foo). $ mv /mnt/foo /mnt/qwerty $ mv /mnt/bar /mnt/foo # Create a new file, in the same parent directory, with the old name of # the second hard link (bar) and fsync this new file. # We do this instead of calling fsync on foo/qwerty because if we did # that the fsync resulted in a full transaction commit, not triggering # the problem. $ touch /mnt/bar $ xfs_io -c "fsync" /mnt/bar <power fail> $ mount /dev/sdb /mnt mount: mount /dev/sdb on /mnt failed: File exists So fix this by checking if a conflicting inode reference exists (same name, same parent but different index), removing it (and the associated dir index entries from the parent inode) if it exists, before attempting to add the new reference. A test case for fstests follows soon. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 10f6a4223897..033aeebbe9de 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1290,6 +1290,46 @@ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, return ret; } +static int btrfs_inode_ref_exists(struct inode *inode, struct inode *dir, + const u8 ref_type, const char *name, + const int namelen) +{ + struct btrfs_key key; + struct btrfs_path *path; + const u64 parent_id = btrfs_ino(BTRFS_I(dir)); + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = ref_type; + if (key.type == BTRFS_INODE_REF_KEY) + key.offset = parent_id; + else + key.offset = btrfs_extref_hash(parent_id, name, namelen); + + ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &key, path, 0, 0); + if (ret < 0) + goto out; + if (ret > 0) { + ret = 0; + goto out; + } + if (key.type == BTRFS_INODE_EXTREF_KEY) + ret = btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], parent_id, + name, namelen, NULL); + else + ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, namelen, NULL); + +out: + btrfs_free_path(path); + return ret; +} + /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. @@ -1399,6 +1439,32 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } } + /* + * If a reference item already exists for this inode + * with the same parent and name, but different index, + * drop it and the corresponding directory index entries + * from the parent before adding the new reference item + * and dir index entries, otherwise we would fail with + * -EEXIST returned from btrfs_add_link() below. + */ + ret = btrfs_inode_ref_exists(inode, dir, key->type, + name, namelen); + if (ret > 0) { + ret = btrfs_unlink_inode(trans, root, + BTRFS_I(dir), + BTRFS_I(inode), + name, namelen); + /* + * If we dropped the link count to 0, bump it so + * that later the iput() on the inode will not + * free it. We will fixup the link count later. + */ + if (!ret && inode->i_nlink == 0) + inc_nlink(inode); + } + if (ret < 0) + goto out; + /* insert our name */ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),

6 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix mount failure after fsync due to hard link" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 0d836392cadd5535f4184d46d901a82eb276ed62 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Fri, 20 Jul 2018 10:59:06 +0100 Subject: [PATCH] Btrfs: fix mount failure after fsync due to hard link recreation If we end up with logging an inode reference item which has the same name but different index from the one we have persisted, we end up failing when replaying the log with an errno value of -EEXIST. The error comes from btrfs_add_link(), which is called from add_inode_ref(), when we are replaying an inode reference item. Example scenario where this happens: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ touch /mnt/foo $ ln /mnt/foo /mnt/bar $ sync # Rename the first hard link (foo) to a new name and rename the second # hard link (bar) to the old name of the first hard link (foo). $ mv /mnt/foo /mnt/qwerty $ mv /mnt/bar /mnt/foo # Create a new file, in the same parent directory, with the old name of # the second hard link (bar) and fsync this new file. # We do this instead of calling fsync on foo/qwerty because if we did # that the fsync resulted in a full transaction commit, not triggering # the problem. $ touch /mnt/bar $ xfs_io -c "fsync" /mnt/bar <power fail> $ mount /dev/sdb /mnt mount: mount /dev/sdb on /mnt failed: File exists So fix this by checking if a conflicting inode reference exists (same name, same parent but different index), removing it (and the associated dir index entries from the parent inode) if it exists, before attempting to add the new reference. A test case for fstests follows soon. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 10f6a4223897..033aeebbe9de 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1290,6 +1290,46 @@ again: return ret; } +static int btrfs_inode_ref_exists(struct inode *inode, struct inode *dir, + const u8 ref_type, const char *name, + const int namelen) +{ + struct btrfs_key key; + struct btrfs_path *path; + const u64 parent_id = btrfs_ino(BTRFS_I(dir)); + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = ref_type; + if (key.type == BTRFS_INODE_REF_KEY) + key.offset = parent_id; + else + key.offset = btrfs_extref_hash(parent_id, name, namelen); + + ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &key, path, 0, 0); + if (ret < 0) + goto out; + if (ret > 0) { + ret = 0; + goto out; + } + if (key.type == BTRFS_INODE_EXTREF_KEY) + ret = btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], parent_id, + name, namelen, NULL); + else + ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, namelen, NULL); + +out: + btrfs_free_path(path); + return ret; +} + /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. @@ -1399,6 +1439,32 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } } + /* + * If a reference item already exists for this inode + * with the same parent and name, but different index, + * drop it and the corresponding directory index entries + * from the parent before adding the new reference item + * and dir index entries, otherwise we would fail with + * -EEXIST returned from btrfs_add_link() below. + */ + ret = btrfs_inode_ref_exists(inode, dir, key->type, + name, namelen); + if (ret > 0) { + ret = btrfs_unlink_inode(trans, root, + BTRFS_I(dir), + BTRFS_I(inode), + name, namelen); + /* + * If we dropped the link count to 0, bump it so + * that later the iput() on the inode will not + * free it. We will fixup the link count later. + */ + if (!ret && inode->i_nlink == 0) + inc_nlink(inode); + } + if (ret < 0) + goto out; + /* insert our name */ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),

6 years, 1 month

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2018