diff options
29 files changed, 294 insertions, 143 deletions
diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt index d3d0a4f..079b42a 100644 --- a/Documentation/devicetree/bindings/dma/ti-edma.txt +++ b/Documentation/devicetree/bindings/dma/ti-edma.txt @@ -22,8 +22,7 @@ Required properties: Optional properties: - ti,hwmods: Name of the hwmods associated to the eDMA CC - ti,edma-memcpy-channels: List of channels allocated to be used for memcpy, iow - these channels will be SW triggered channels. The list must - contain 16 bits numbers, see example. + these channels will be SW triggered channels. See example. - ti,edma-reserved-slot-ranges: PaRAM slot ranges which should not be used by the driver, they are allocated to be used by for example the DSP. See example. @@ -56,10 +55,9 @@ edma: edma@49000000 { ti,tptcs = <&edma_tptc0 7>, <&edma_tptc1 7>, <&edma_tptc2 0>; /* Channel 20 and 21 is allocated for memcpy */ - ti,edma-memcpy-channels = /bits/ 16 <20 21>; - /* The following PaRAM slots are reserved: 35-45 and 100-110 */ - ti,edma-reserved-slot-ranges = /bits/ 16 <35 10>, - /bits/ 16 <100 10>; + ti,edma-memcpy-channels = <20 21>; + /* The following PaRAM slots are reserved: 35-44 and 100-109 */ + ti,edma-reserved-slot-ranges = <35 10>, <100 10>; }; edma_tptc0: tptc@49800000 { diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 8cc85a4..35c9db8 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -510,10 +510,14 @@ __copy_to_user_std(void __user *to, const void *from, unsigned long n); static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { +#ifndef CONFIG_UACCESS_WITH_MEMCPY unsigned int __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; +#else + return arm_copy_to_user(to, from, n); +#endif } extern unsigned long __must_check diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 7a7c4ce..4adfb46 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -95,6 +95,22 @@ void __show_regs(struct pt_regs *regs) { unsigned long flags; char buf[64]; +#ifndef CONFIG_CPU_V7M + unsigned int domain; +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Get the domain register for the parent context. In user + * mode, we don't save the DACR, so lets use what it should + * be. For other modes, we place it after the pt_regs struct. + */ + if (user_mode(regs)) + domain = DACR_UACCESS_ENABLE; + else + domain = *(unsigned int *)(regs + 1); +#else + domain = get_domain(); +#endif +#endif show_regs_print_info(KERN_DEFAULT); @@ -123,21 +139,8 @@ void __show_regs(struct pt_regs *regs) #ifndef CONFIG_CPU_V7M { - unsigned int domain = get_domain(); const char *segment; -#ifdef CONFIG_CPU_SW_DOMAIN_PAN - /* - * Get the domain register for the parent context. In user - * mode, we don't save the DACR, so lets use what it should - * be. For other modes, we place it after the pt_regs struct. - */ - if (user_mode(regs)) - domain = DACR_UACCESS_ENABLE; - else - domain = *(unsigned int *)(regs + 1); -#endif - if ((domain & domain_mask(DOMAIN_USER)) == domain_val(DOMAIN_USER, DOMAIN_NOACCESS)) segment = "none"; @@ -163,11 +166,11 @@ void __show_regs(struct pt_regs *regs) buf[0] = '\0'; #ifdef CONFIG_CPU_CP15_MMU { - unsigned int transbase, dac = get_domain(); + unsigned int transbase; asm("mrc p15, 0, %0, c2, c0\n\t" : "=r" (transbase)); snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x", - transbase, dac); + transbase, domain); } #endif asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl)); diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c index 5b26e7e..c3fe769d 100644 --- a/arch/arm/kernel/swp_emulate.c +++ b/arch/arm/kernel/swp_emulate.c @@ -36,10 +36,10 @@ */ #define __user_swpX_asm(data, addr, res, temp, B) \ __asm__ __volatile__( \ - " mov %2, %1\n" \ - "0: ldrex"B" %1, [%3]\n" \ - "1: strex"B" %0, %2, [%3]\n" \ + "0: ldrex"B" %2, [%3]\n" \ + "1: strex"B" %0, %1, [%3]\n" \ " cmp %0, #0\n" \ + " moveq %1, %2\n" \ " movne %0, %4\n" \ "2:\n" \ " .section .text.fixup,\"ax\"\n" \ diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index d72b909..588bbc2 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -88,6 +88,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) static unsigned long noinline __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) { + unsigned long ua_flags; int atomic; if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { @@ -118,7 +119,9 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memcpy((void *)to, from, tocopy); + uaccess_restore(ua_flags); to += tocopy; from += tocopy; n -= tocopy; @@ -145,14 +148,21 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n) * With frame pointer disabled, tail call optimization kicks in * as well making this test almost invisible. */ - if (n < 64) - return __copy_to_user_std(to, from, n); - return __copy_to_user_memcpy(to, from, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __copy_to_user_std(to, from, n); + uaccess_restore(ua_flags); + } else { + n = __copy_to_user_memcpy(to, from, n); + } + return n; } static unsigned long noinline __clear_user_memset(void __user *addr, unsigned long n) { + unsigned long ua_flags; + if (unlikely(segment_eq(get_fs(), KERNEL_DS))) { memset((void *)addr, 0, n); return 0; @@ -175,7 +185,9 @@ __clear_user_memset(void __user *addr, unsigned long n) if (tocopy > n) tocopy = n; + ua_flags = uaccess_save_and_enable(); memset((void *)addr, 0, tocopy); + uaccess_restore(ua_flags); addr += tocopy; n -= tocopy; @@ -193,9 +205,14 @@ out: unsigned long arm_clear_user(void __user *addr, unsigned long n) { /* See rational for this in __copy_to_user() above. */ - if (n < 64) - return __clear_user_std(addr, n); - return __clear_user_memset(addr, n); + if (n < 64) { + unsigned long ua_flags = uaccess_save_and_enable(); + n = __clear_user_std(addr, n); + uaccess_restore(ua_flags); + } else { + n = __clear_user_memset(addr, n); + } + return n; } #if 0 diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 845769e..c8c8b9e 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -165,13 +165,28 @@ static void flush_context(unsigned int cpu) __flush_icache_all(); } -static int is_reserved_asid(u64 asid) +static bool check_update_reserved_asid(u64 asid, u64 newasid) { int cpu; - for_each_possible_cpu(cpu) - if (per_cpu(reserved_asids, cpu) == asid) - return 1; - return 0; + bool hit = false; + + /* + * Iterate over the set of reserved ASIDs looking for a match. + * If we find one, then we can update our mm to use newasid + * (i.e. the same ASID in the current generation) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old ASID are updated to reflect the mm. Failure to do + * so could result in us missing the reserved ASID in a future + * generation. + */ + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_asids, cpu) == asid) { + hit = true; + per_cpu(reserved_asids, cpu) = newasid; + } + } + + return hit; } static u64 new_context(struct mm_struct *mm, unsigned int cpu) @@ -181,12 +196,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) u64 generation = atomic64_read(&asid_generation); if (asid != 0) { + u64 newasid = generation | (asid & ~ASID_MASK); + /* * If our current ASID was active during a rollover, we * can continue to use it and this was just a false alarm. */ - if (is_reserved_asid(asid)) - return generation | (asid & ~ASID_MASK); + if (check_update_reserved_asid(asid, newasid)) + return newasid; /* * We had a valid ASID in a previous life, so try to re-use @@ -194,7 +211,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) */ asid &= ~ASID_MASK; if (!__test_and_set_bit(asid, asid_map)) - goto bump_gen; + return newasid; } /* @@ -216,11 +233,8 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) __set_bit(asid, asid_map); cur_idx = asid; - -bump_gen: - asid |= generation; cpumask_clear(mm_cpumask(mm)); - return asid; + return asid | generation; } void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e62400e..534a60a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1521,7 +1521,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, return -ENOMEM; for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) { - phys_addr_t phys = sg_phys(s) & PAGE_MASK; + phys_addr_t phys = page_to_phys(sg_page(s)); unsigned int len = PAGE_ALIGN(s->offset + s->length); if (!is_coherent && diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 8a63b4c..7f8cd1b 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -22,6 +22,7 @@ #include <linux/memblock.h> #include <linux/dma-contiguous.h> #include <linux/sizes.h> +#include <linux/stop_machine.h> #include <asm/cp15.h> #include <asm/mach-types.h> @@ -627,12 +628,10 @@ static struct section_perm ro_perms[] = { * safe to be called with preemption disabled, as under stop_machine(). */ static inline void section_update(unsigned long addr, pmdval_t mask, - pmdval_t prot) + pmdval_t prot, struct mm_struct *mm) { - struct mm_struct *mm; pmd_t *pmd; - mm = current->active_mm; pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr); #ifdef CONFIG_ARM_LPAE @@ -656,49 +655,82 @@ static inline bool arch_has_strict_perms(void) return !!(get_cr() & CR_XP); } -#define set_section_perms(perms, field) { \ - size_t i; \ - unsigned long addr; \ - \ - if (!arch_has_strict_perms()) \ - return; \ - \ - for (i = 0; i < ARRAY_SIZE(perms); i++) { \ - if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || \ - !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { \ - pr_err("BUG: section %lx-%lx not aligned to %lx\n", \ - perms[i].start, perms[i].end, \ - SECTION_SIZE); \ - continue; \ - } \ - \ - for (addr = perms[i].start; \ - addr < perms[i].end; \ - addr += SECTION_SIZE) \ - section_update(addr, perms[i].mask, \ - perms[i].field); \ - } \ +void set_section_perms(struct section_perm *perms, int n, bool set, + struct mm_struct *mm) +{ + size_t i; + unsigned long addr; + + if (!arch_has_strict_perms()) + return; + + for (i = 0; i < n; i++) { + if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) || + !IS_ALIGNED(perms[i].end, SECTION_SIZE)) { + pr_err("BUG: section %lx-%lx not aligned to %lx\n", + perms[i].start, perms[i].end, + SECTION_SIZE); + continue; + } + + for (addr = perms[i].start; + addr < perms[i].end; + addr += SECTION_SIZE) + section_update(addr, perms[i].mask, + set ? perms[i].prot : perms[i].clear, mm); + } + } -static inline void fix_kernmem_perms(void) +static void update_sections_early(struct section_perm perms[], int n) { - set_section_perms(nx_perms, prot); + struct task_struct *t, *s; + + read_lock(&tasklist_lock); + for_each_process(t) { + if (t->flags & PF_KTHREAD) + continue; + for_each_thread(t, s) + set_section_perms(perms, n, true, s->mm); + } + read_unlock(&tasklist_lock); + set_section_perms(perms, n, true, current->active_mm); + set_section_perms(perms, n, true, &init_mm); +} + +int __fix_kernmem_perms(void *unused) +{ + update_sections_early(nx_perms, ARRAY_SIZE(nx_perms)); + return 0; +} + +void fix_kernmem_perms(void) +{ + stop_machine(__fix_kernmem_perms, NULL, NULL); } #ifdef CONFIG_DEBUG_RODATA +int __mark_rodata_ro(void *unused) +{ + update_sections_early(ro_perms, ARRAY_SIZE(ro_perms)); + return 0; +} + void mark_rodata_ro(void) { - set_section_perms(ro_perms, prot); + stop_machine(__mark_rodata_ro, NULL, NULL); } void set_kernel_text_rw(void) { - set_section_perms(ro_perms, clear); + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false, + current->active_mm); } void set_kernel_text_ro(void) { - set_section_perms(ro_perms, prot); + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true, + current->active_mm); } #endif /* CONFIG_DEBUG_RODATA */ diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index de2b246..8e1ea43 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area) .equ cpu_v7_suspend_size, 4 * 9 #ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID mrc p15, 0, r5, c13, c0, 3 @ User r/o thread ID stmia r0!, {r4 - r5} @@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend) mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control stmia r0, {r5 - r11} - ldmfd sp!, {r4 - r10, pc} + ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_v7_do_suspend) ENTRY(cpu_v7_do_resume) diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index db73390..74c132d 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -11,7 +11,7 @@ -#define NR_syscalls 322 /* length of syscall table */ +#define NR_syscalls 323 /* length of syscall table */ /* * The following defines stop scripts/checksyscalls.sh from complaining about diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index 9038726..762edce 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -335,5 +335,6 @@ #define __NR_userfaultfd 1343 #define __NR_membarrier 1344 #define __NR_kcmp 1345 +#define __NR_mlock2 1346 #endif /* _UAPI_ASM_IA64_UNISTD_H */ diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index dcd97f8..534a74a 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1771,5 +1771,6 @@ sys_call_table: data8 sys_userfaultfd data8 sys_membarrier data8 sys_kcmp // 1345 + data8 sys_mlock2 .org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index c89da63..bf4dec2 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -61,7 +61,8 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, /* FIXME this part of code is untested */ for_each_sg(sgl, sg, nents, i) { sg->dma_address = sg_phys(sg); - __dma_sync(sg_phys(sg), sg->length, direction); + __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, + sg->length, direction); } return nents; diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a035c2a..0f1c6fc 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -89,7 +89,7 @@ static struct addr_marker address_markers[] = { { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/*VMALLOC_END*/, "vmalloc() End" }, # ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, + { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, # endif { 0/*FIXADDR_START*/, "Fixmap Area" }, #endif diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c index b4ffc5b..e5b5721 100644 --- a/crypto/ablkcipher.c +++ b/crypto/ablkcipher.c @@ -277,12 +277,12 @@ static int ablkcipher_walk_first(struct ablkcipher_request *req, if (WARN_ON_ONCE(in_irq())) return -EDEADLK; + walk->iv = req->info; walk->nbytes = walk->total; if (unlikely(!walk->total)) return 0; walk->iv_buffer = NULL; - walk->iv = req->info; if (unlikely(((unsigned long)walk->iv & alignmask))) { int err = ablkcipher_copy_iv(walk, tfm, alignmask); diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c index 11b9814..8cc1622 100644 --- a/crypto/blkcipher.c +++ b/crypto/blkcipher.c @@ -326,12 +326,12 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc, if (WARN_ON_ONCE(in_irq())) return -EDEADLK; + walk->iv = desc->info; walk->nbytes = walk->total; if (unlikely(!walk->total)) return 0; walk->buffer = NULL; - walk->iv = desc->info; if (unlikely(((unsigned long)walk->iv & walk->alignmask))) { int err = blkcipher_copy_iv(walk); if (err) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index e7ed39b..aa45d48 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1810,7 +1810,7 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event) if (!dev->driver) { /* dev->driver may be null if we're being removed */ dev_dbg(dev, "%s: no driver found for dev\n", __func__); - return; + goto out_unlock; } if (!acpi_desc) { diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7f039de..370c661 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -156,7 +156,7 @@ #define AT_XDMAC_CC_WRIP (0x1 << 23) /* Write in Progress (read only) */ #define AT_XDMAC_CC_WRIP_DONE (0x0 << 23) #define AT_XDMAC_CC_WRIP_IN_PROGRESS (0x1 << 23) -#define AT_XDMAC_CC_PERID(i) (0x7f & (h) << 24) /* Channel Peripheral Identifier */ +#define AT_XDMAC_CC_PERID(i) (0x7f & (i) << 24) /* Channel Peripheral Identifier */ #define AT_XDMAC_CDS_MSP 0x2C /* Channel Data Stride Memory Set Pattern */ #define AT_XDMAC_CSUS 0x30 /* Channel Source Microblock Stride */ #define AT_XDMAC_CDUS 0x34 /* Channel Destination Microblock Stride */ @@ -965,7 +965,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); - for (i = 0; i < xt->numf; i++) + + /* Length of the block is (BLEN+1) microblocks. */ + for (i = 0; i < xt->numf - 1; i++) at_xdmac_increment_block_count(chan, first); dev_dbg(chan2dev(chan), "%s: add desc 0x%p to descs_list 0x%p\n", @@ -1086,6 +1088,7 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, /* Check remaining length and change data width if needed. */ dwidth = at_xdmac_align_width(chan, src_addr | dst_addr | xfer_size); + chan_cc &= ~AT_XDMAC_CC_DWIDTH_MASK; chan_cc |= AT_XDMAC_CC_DWIDTH(dwidth); ublen = xfer_size >> dwidth; @@ -1333,7 +1336,7 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl, * since we don't care about the stride anymore. */ if ((i == (sg_len - 1)) && - sg_dma_len(ppsg) == sg_dma_len(psg)) { + sg_dma_len(psg) == sg_dma_len(sg)) { dev_dbg(chan2dev(chan), "%s: desc 0x%p can be merged with desc 0x%p\n", __func__, desc, pdesc); diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index c92d6a7..996c4b0 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -31,6 +31,7 @@ */ #include <linux/dmaengine.h> #include <linux/dma-mapping.h> +#include <linux/dmapool.h> #include <linux/err.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -62,6 +63,11 @@ struct bcm2835_dma_cb { uint32_t pad[2]; }; +struct bcm2835_cb_entry { + struct bcm2835_dma_cb *cb; + dma_addr_t paddr; +}; + struct bcm2835_chan { struct virt_dma_chan vc; struct list_head node; @@ -72,18 +78,18 @@ struct bcm2835_chan { int ch; struct bcm2835_desc *desc; + struct dma_pool *cb_pool; void __iomem *chan_base; int irq_number; }; struct bcm2835_desc { + struct bcm2835_chan *c; struct virt_dma_desc vd; enum dma_transfer_direction dir; - unsigned int control_block_size; - struct bcm2835_dma_cb *control_block_base; - dma_addr_t control_block_base_phys; + struct bcm2835_cb_entry *cb_list; unsigned int frames; size_t size; @@ -143,10 +149,13 @@ static inline struct bcm2835_desc *to_bcm2835_dma_desc( static void bcm2835_dma_desc_free(struct virt_dma_desc *vd) { struct bcm2835_desc *desc = container_of(vd, struct bcm2835_desc, vd); - dma_free_coherent(desc->vd.tx.chan->device->dev, - desc->control_block_size, - desc->control_block_base, - desc->control_block_base_phys); + int i; + + for (i = 0; i < desc->frames; i++) + dma_pool_free(desc->c->cb_pool, desc->cb_list[i].cb, + desc->cb_list[i].paddr); + + kfree(desc->cb_list); kfree(desc); } @@ -199,7 +208,7 @@ static void bcm2835_dma_start_desc(struct bcm2835_chan *c) c->desc = d = to_bcm2835_dma_desc(&vd->tx); - writel(d->control_block_base_phys, c->chan_base + BCM2835_DMA_ADDR); + writel(d->cb_list[0].paddr, c->chan_base + BCM2835_DMA_ADDR); writel(BCM2835_DMA_ACTIVE, c->chan_base + BCM2835_DMA_CS); } @@ -232,9 +241,16 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan) { struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); + struct device *dev = c->vc.chan.device->dev; + + dev_dbg(dev, "Allocating DMA channel %d\n", c->ch); - dev_dbg(c->vc.chan.device->dev, - "Allocating DMA channel %d\n", c->ch); + c->cb_pool = dma_pool_create(dev_name(dev), dev, + sizeof(struct bcm2835_dma_cb), 0, 0); + if (!c->cb_pool) { + dev_err(dev, "unable to allocate descriptor pool\n"); + return -ENOMEM; + } return request_irq(c->irq_number, bcm2835_dma_callback, 0, "DMA IRQ", c); @@ -246,6 +262,7 @@ static void bcm2835_dma_free_chan_resources(struct dma_chan *chan) vchan_free_chan_resources(&c->vc); free_irq(c->irq_number, c); + dma_pool_destroy(c->cb_pool); dev_dbg(c->vc.chan.device->dev, "Freeing DMA channel %u\n", c->ch); } @@ -261,8 +278,7 @@ static size_t bcm2835_dma_desc_size_pos(struct bcm2835_desc *d, dma_addr_t addr) size_t size; for (size = i = 0; i < d->frames; i++) { - struct bcm2835_dma_cb *control_block = - &d->control_block_base[i]; + struct bcm2835_dma_cb *control_block = d->cb_list[i].cb; size_t this_size = control_block->length; dma_addr_t dma; @@ -343,6 +359,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( dma_addr_t dev_addr; unsigned int es, sync_type; unsigned int frame; + int i; /* Grab configuration */ if (!is_slave_direction(direction)) { @@ -374,27 +391,31 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( if (!d) return NULL; + d->c = c; d->dir = direction; d->frames = buf_len / period_len; - /* Allocate memory for control blocks */ - d->control_block_size = d->frames * sizeof(struct bcm2835_dma_cb); - d->control_block_base = dma_zalloc_coherent(chan->device->dev, - d->control_block_size, &d->control_block_base_phys, - GFP_NOWAIT); - - if (!d->control_block_base) { + d->cb_list = kcalloc(d->frames, sizeof(*d->cb_list), GFP_KERNEL); + if (!d->cb_list) { kfree(d); return NULL; } + /* Allocate memory for control blocks */ + for (i = 0; i < d->frames; i++) { + struct bcm2835_cb_entry *cb_entry = &d->cb_list[i]; + + cb_entry->cb = dma_pool_zalloc(c->cb_pool, GFP_ATOMIC, + &cb_entry->paddr); + if (!cb_entry->cb) + goto error_cb; + } /* * Iterate over all frames, create a control block * for each frame and link them together. */ for (frame = 0; frame < d->frames; frame++) { - struct bcm2835_dma_cb *control_block = - &d->control_block_base[frame]; + struct bcm2835_dma_cb *control_block = d->cb_list[frame].cb; /* Setup adresses */ if (d->dir == DMA_DEV_TO_MEM) { @@ -428,12 +449,21 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic( * This DMA engine driver currently only supports cyclic DMA. * Therefore, wrap around at number of frames. */ - control_block->next = d->control_block_base_phys + - sizeof(struct bcm2835_dma_cb) - * ((frame + 1) % d->frames); + control_block->next = d->cb_list[((frame + 1) % d->frames)].paddr; } return vchan_tx_prep(&c->vc, &d->vd, flags); +error_cb: + i--; + for (; i >= 0; i--) { + struct bcm2835_cb_entry *cb_entry = &d->cb_list[i]; + + dma_pool_free(c->cb_pool, cb_entry->cb, cb_entry->paddr); + } + + kfree(d->cb_list); + kfree(d); + return NULL; } static int bcm2835_dma_slave_config(struct dma_chan *chan, diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 0675e26..16fe773 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -1752,16 +1752,14 @@ static enum dma_status edma_tx_status(struct dma_chan *chan, return ret; } -static bool edma_is_memcpy_channel(int ch_num, u16 *memcpy_channels) +static bool edma_is_memcpy_channel(int ch_num, s32 *memcpy_channels) { - s16 *memcpy_ch = memcpy_channels; - if (!memcpy_channels) return false; - while (*memcpy_ch != -1) { - if (*memcpy_ch == ch_num) + while (*memcpy_channels != -1) { + if (*memcpy_channels == ch_num) return true; - memcpy_ch++; + memcpy_channels++; } return false; } @@ -1775,7 +1773,7 @@ static void edma_dma_init(struct edma_cc *ecc, bool legacy_mode) { struct dma_device *s_ddev = &ecc->dma_slave; struct dma_device *m_ddev = NULL; - s16 *memcpy_channels = ecc->info->memcpy_channels; + s32 *memcpy_channels = ecc->info->memcpy_channels; int i, j; dma_cap_zero(s_ddev->cap_mask); @@ -1996,16 +1994,16 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev, prop = of_find_property(dev->of_node, "ti,edma-memcpy-channels", &sz); if (prop) { const char pname[] = "ti,edma-memcpy-channels"; - size_t nelm = sz / sizeof(s16); - s16 *memcpy_ch; + size_t nelm = sz / sizeof(s32); + s32 *memcpy_ch; - memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s16), + memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s32), GFP_KERNEL); if (!memcpy_ch) return ERR_PTR(-ENOMEM); - ret = of_property_read_u16_array(dev->of_node, pname, - (u16 *)memcpy_ch, nelm); + ret = of_property_read_u32_array(dev->of_node, pname, + (u32 *)memcpy_ch, nelm); if (ret) return ERR_PTR(ret); @@ -2017,31 +2015,50 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev, &sz); if (prop) { const char pname[] = "ti,edma-reserved-slot-ranges"; + u32 (*tmp)[2]; s16 (*rsv_slots)[2]; - size_t nelm = sz / sizeof(*rsv_slots); + size_t nelm = sz / sizeof(*tmp); struct edma_rsv_info *rsv_info; + int i; if (!nelm) return info; + tmp = kcalloc(nelm, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ERR_PTR(-ENOMEM); + rsv_info = devm_kzalloc(dev, sizeof(*rsv_info), GFP_KERNEL); - if (!rsv_info) + if (!rsv_info) { + kfree(tmp); return ERR_PTR(-ENOMEM); + } rsv_slots = devm_kcalloc(dev, nelm + 1, sizeof(*rsv_slots), GFP_KERNEL); - if (!rsv_slots) + if (!rsv_slots) { + kfree(tmp); return ERR_PTR(-ENOMEM); + } - ret = of_property_read_u16_array(dev->of_node, pname, - (u16 *)rsv_slots, nelm * 2); - if (ret) + ret = of_property_read_u32_array(dev->of_node, pname, + (u32 *)tmp, nelm * 2); + if (ret) { + kfree(tmp); return ERR_PTR(ret); + } + for (i = 0; i < nelm; i++) { + rsv_slots[i][0] = tmp[i][0]; + rsv_slots[i][1] = tmp[i][1]; + } rsv_slots[nelm][0] = -1; rsv_slots[nelm][1] = -1; + info->rsv = rsv_info; info->rsv->rsv_slots = (const s16 (*)[2])rsv_slots; + + kfree(tmp); } return info; diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index 068e920..cddfa8d 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -317,6 +317,7 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); struct device *dev = mic_dma_ch_to_device(mic_ch); int result; + struct dma_async_tx_descriptor *tx = NULL; if (!len && !flags) return NULL; @@ -324,10 +325,13 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, spin_lock(&mic_ch->prep_lock); result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len); if (result >= 0) - return allocate_tx(mic_ch); - dev_err(dev, "Error enqueueing dma, error=%d\n", result); + tx = allocate_tx(mic_ch); + + if (!tx) + dev_err(dev, "Error enqueueing dma, error=%d\n", result); + spin_unlock(&mic_ch->prep_lock); - return NULL; + return tx; } static struct dma_async_tx_descriptor * @@ -335,13 +339,14 @@ mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags) { struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); int ret; + struct dma_async_tx_descriptor *tx = NULL; spin_lock(&mic_ch->prep_lock); ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0); if (!ret) - return allocate_tx(mic_ch); + tx = allocate_tx(mic_ch); spin_unlock(&mic_ch->prep_lock); - return NULL; + return tx; } /* Return the status of the transaction */ diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index f1042da..ac73876 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2159,7 +2159,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, sg_res = aligned_nrpages(sg->offset, sg->length); sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset; sg->dma_length = sg->length; - pteval = (sg_phys(sg) & PAGE_MASK) | prot; + pteval = page_to_phys(sg_page(sg)) | prot; phys_pfn = pteval >> VTD_PAGE_SHIFT; } @@ -3704,7 +3704,7 @@ static int intel_nontranslate_map_sg(struct device *hddev, for_each_sg(sglist, sg, nelems, i) { BUG_ON(!sg_page(sg)); - sg->dma_address = sg_phys(sg); + sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset; sg->dma_length = sg->length; } return nelems; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index abae363..0e3b009 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1430,7 +1430,7 @@ size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, min_pagesz = 1 << __ffs(domain->ops->pgsize_bitmap); for_each_sg(sg, s, nents, i) { - phys_addr_t phys = sg_phys(s); + phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset; /* * We are mapping on IOMMU page boundaries, so offset within diff --git a/drivers/staging/android/ion/ion_chunk_heap.c b/drivers/staging/android/ion/ion_chunk_heap.c index 195c41d..0813163 100644 --- a/drivers/staging/android/ion/ion_chunk_heap.c +++ b/drivers/staging/android/ion/ion_chunk_heap.c @@ -81,7 +81,7 @@ static int ion_chunk_heap_allocate(struct ion_heap *heap, err: sg = table->sgl; for (i -= 1; i >= 0; i--) { - gen_pool_free(chunk_heap->pool, sg_phys(sg) & PAGE_MASK, + gen_pool_free(chunk_heap->pool, page_to_phys(sg_page(sg)), sg->length); sg = sg_next(sg); } @@ -109,7 +109,7 @@ static void ion_chunk_heap_free(struct ion_buffer *buffer) DMA_BIDIRECTIONAL); for_each_sg(table->sgl, sg, table->nents, i) { - gen_pool_free(chunk_heap->pool, sg_phys(sg) & PAGE_MASK, + gen_pool_free(chunk_heap->pool, page_to_phys(sg_page(sg)), sg->length); } chunk_heap->allocated -= allocated_size; diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index b335c1a..fe00a07 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -479,7 +479,10 @@ static enum fsl_diu_monitor_port fsl_diu_name_to_port(const char *s) port = FSL_DIU_PORT_DLVDS; } - return diu_ops.valid_monitor_port(port); + if (diu_ops.valid_monitor_port) + port = diu_ops.valid_monitor_port(port); + + return port; } /* @@ -1915,6 +1918,14 @@ static int __init fsl_diu_init(void) #else monitor_port = fsl_diu_name_to_port(monitor_string); #endif + + /* + * Must to verify set_pixel_clock. If not implement on platform, + * then that means that there is no platform support for the DIU. + */ + if (!diu_ops.set_pixel_clock) + return -ENODEV; + pr_info("Freescale Display Interface Unit (DIU) framebuffer driver\n"); #ifdef CONFIG_NOT_COHERENT_CACHE diff --git a/drivers/video/fbdev/omap2/dss/venc.c b/drivers/video/fbdev/omap2/dss/venc.c index 99ca268..d05a549 100644 --- a/drivers/video/fbdev/omap2/dss/venc.c +++ b/drivers/video/fbdev/omap2/dss/venc.c @@ -275,6 +275,12 @@ const struct omap_video_timings omap_dss_pal_timings = { .vbp = 41, .interlace = true, + + .hsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .vsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .data_pclk_edge = OMAPDSS_DRIVE_SIG_RISING_EDGE, + .de_level = OMAPDSS_SIG_ACTIVE_HIGH, + .sync_pclk_edge = OMAPDSS_DRIVE_SIG_FALLING_EDGE, }; EXPORT_SYMBOL(omap_dss_pal_timings); @@ -290,6 +296,12 @@ const struct omap_video_timings omap_dss_ntsc_timings = { .vbp = 31, .interlace = true, + + .hsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .vsync_level = OMAPDSS_SIG_ACTIVE_LOW, + .data_pclk_edge = OMAPDSS_DRIVE_SIG_RISING_EDGE, + .de_level = OMAPDSS_SIG_ACTIVE_HIGH, + .sync_pclk_edge = OMAPDSS_DRIVE_SIG_FALLING_EDGE, }; EXPORT_SYMBOL(omap_dss_ntsc_timings); diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h index e2878ba..4299f4b 100644 --- a/include/linux/platform_data/edma.h +++ b/include/linux/platform_data/edma.h @@ -72,7 +72,7 @@ struct edma_soc_info { struct edma_rsv_info *rsv; /* List of channels allocated for memcpy, terminated with -1 */ - s16 *memcpy_channels; + s32 *memcpy_channels; s8 (*queue_priority_mapping)[2]; const s16 (*xbar_chans)[2]; diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index d092a0c..05a3785 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -93,10 +93,12 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->cpu = curr; /* - * ACQUIRE semantics, pairs with corresponding RELEASE - * in unlock() uncontended, or fastpath. + * We need both ACQUIRE (pairs with corresponding RELEASE in + * unlock() uncontended, or fastpath) and RELEASE (to publish + * the node fields we just initialised) semantics when updating + * the lock tail. */ - old = atomic_xchg_acquire(&lock->tail, curr); + old = atomic_xchg(&lock->tail, curr); if (old == OSQ_UNLOCKED_VAL) return true; diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 8855f01..d34bd24 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1464,7 +1464,7 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, entry->type = dma_debug_coherent; entry->dev = dev; entry->pfn = page_to_pfn(virt_to_page(virt)); - entry->offset = (size_t) virt & PAGE_MASK; + entry->offset = (size_t) virt & ~PAGE_MASK; entry->size = size; entry->dev_addr = dma_addr; entry->direction = DMA_BIDIRECTIONAL; @@ -1480,7 +1480,7 @@ void debug_dma_free_coherent(struct device *dev, size_t size, .type = dma_debug_coherent, .dev = dev, .pfn = page_to_pfn(virt_to_page(virt)), - .offset = (size_t) virt & PAGE_MASK, + .offset = (size_t) virt & ~PAGE_MASK, .dev_addr = addr, .size = size, .direction = DMA_BIDIRECTIONAL, |
