diff options
282 files changed, 3490 insertions, 5233 deletions
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt index 31d1d65..c0d8788 100644 --- a/Documentation/IPMI.txt +++ b/Documentation/IPMI.txt @@ -587,7 +587,7 @@ used to control it: modprobe ipmi_watchdog timeout=<t> pretimeout=<t> action=<action type> preaction=<preaction type> preop=<preop type> start_now=x - nowayout=x ifnum_to_use=n + nowayout=x ifnum_to_use=n panic_wdt_timeout=<t> ifnum_to_use specifies which interface the watchdog timer should use. The default is -1, which means to pick the first one registered. @@ -597,7 +597,9 @@ is the amount of seconds before the reset that the pre-timeout panic will occur (if pretimeout is zero, then pretimeout will not be enabled). Note that the pretimeout is the time before the final timeout. So if the timeout is 50 seconds and the pretimeout is 10 seconds, then the pretimeout -will occur in 40 second (10 seconds before the timeout). +will occur in 40 second (10 seconds before the timeout). The panic_wdt_timeout +is the value of timeout which is set on kernel panic, in order to let actions +such as kdump to occur during panic. The action may be "reset", "power_cycle", or "power_off", and specifies what to do when the timer times out, and defaults to @@ -634,6 +636,7 @@ for configuring the watchdog: ipmi_watchdog.preop=<preop type> ipmi_watchdog.start_now=x ipmi_watchdog.nowayout=x + ipmi_watchdog.panic_wdt_timeout=<t> The options are the same as the module parameter options. diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index 6a4b1af..1bba38d 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -32,6 +32,7 @@ Supported adapters: * Intel Sunrise Point-LP (PCH) * Intel DNV (SOC) * Intel Broxton (SOC) + * Intel Lewisburg (PCH) Datasheets: Publicly available at the Intel website On Intel Patsburg and later chipsets, both the normal host SMBus controller diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index f8aae63..742f69d 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1583,9 +1583,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. hwp_only Only load intel_pstate on systems which support hardware P state control (HWP) if available. - no_acpi - Don't use ACPI processor performance control objects - _PSS and _PPC specified limits. intremap= [X86-64, Intel-IOMMU] on enable Interrupt Remapping (default) diff --git a/MAINTAINERS b/MAINTAINERS index e9caa4b..b4ca955 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2449,7 +2449,9 @@ F: drivers/firmware/broadcom/* BROADCOM STB NAND FLASH DRIVER M: Brian Norris <computersforpeace@gmail.com> +M: Kamal Dasu <kdasu.kdev@gmail.com> L: linux-mtd@lists.infradead.org +L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mtd/nand/brcmnand/ @@ -2546,7 +2548,7 @@ F: arch/c6x/ CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS M: David Howells <dhowells@redhat.com> -L: linux-cachefs@redhat.com +L: linux-cachefs@redhat.com (moderated for non-subscribers) S: Supported F: Documentation/filesystems/caching/cachefiles.txt F: fs/cachefiles/ @@ -4409,6 +4411,7 @@ K: fmc_d.*register FPGA MANAGER FRAMEWORK M: Alan Tull <atull@opensource.altera.com> +R: Moritz Fischer <moritz.fischer@ettus.com> S: Maintained F: drivers/fpga/ F: include/linux/fpga/fpga-mgr.h @@ -4559,7 +4562,7 @@ F: include/linux/frontswap.h FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS M: David Howells <dhowells@redhat.com> -L: linux-cachefs@redhat.com +L: linux-cachefs@redhat.com (moderated for non-subscribers) S: Supported F: Documentation/filesystems/caching/ F: fs/fscache/ @@ -5711,13 +5714,6 @@ M: Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar> S: Maintained F: net/ipv4/netfilter/ipt_MASQUERADE.c -IP1000A 10/100/1000 GIGABIT ETHERNET DRIVER -M: Francois Romieu <romieu@fr.zoreil.com> -M: Sorbica Shieh <sorbica@icplus.com.tw> -L: netdev@vger.kernel.org -S: Maintained -F: drivers/net/ethernet/icplus/ipg.* - IPATH DRIVER M: Mike Marciniszyn <infinipath@intel.com> L: linux-rdma@vger.kernel.org @@ -6923,13 +6919,21 @@ F: drivers/scsi/megaraid.* F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) -M: Amir Vadai <amirv@mellanox.com> +M: Eugenia Emantayev <eugenia@mellanox.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* +MELLANOX ETHERNET DRIVER (mlx5e) +M: Saeed Mahameed <saeedm@mellanox.com> +L: netdev@vger.kernel.org +S: Supported +W: http://www.mellanox.com +Q: http://patchwork.ozlabs.org/project/netdev/list/ +F: drivers/net/ethernet/mellanox/mlx5/core/en_* + MELLANOX ETHERNET SWITCH DRIVERS M: Jiri Pirko <jiri@mellanox.com> M: Ido Schimmel <idosch@mellanox.com> @@ -7901,6 +7905,18 @@ S: Maintained F: net/openvswitch/ F: include/uapi/linux/openvswitch.h +OPERATING PERFORMANCE POINTS (OPP) +M: Viresh Kumar <vireshk@kernel.org> +M: Nishanth Menon <nm@ti.com> +M: Stephen Boyd <sboyd@codeaurora.org> +L: linux-pm@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git +F: drivers/base/power/opp/ +F: include/linux/pm_opp.h +F: Documentation/power/opp.txt +F: Documentation/devicetree/bindings/opp/ + OPL4 DRIVER M: Clemens Ladisch <clemens@ladisch.de> L: alsa-devel@alsa-project.org (moderated for non-subscribers) @@ -9314,7 +9330,6 @@ F: drivers/i2c/busses/i2c-designware-* F: include/linux/platform_data/i2c-designware.h SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER -M: Seungwon Jeon <tgih.jun@samsung.com> M: Jaehoon Chung <jh80.chung@samsung.com> L: linux-mmc@vger.kernel.org S: Maintained diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 2f4b14c..591f9db 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1061,7 +1061,7 @@ void bpf_jit_compile(struct bpf_prog *fp) } build_epilogue(&ctx); - flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); + flush_icache_range((u32)header, (u32)(ctx.target + ctx.idx)); #if __LINUX_ARM_ARCH__ < 7 if (ctx.imm_count) diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c index ce47792..f7bd9bf 100644 --- a/arch/arm64/crypto/aes-ce-cipher.c +++ b/arch/arm64/crypto/aes-ce-cipher.c @@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey); static struct crypto_alg aes_alg = { .cra_name = "aes", .cra_driver_name = "aes-ce", - .cra_priority = 300, + .cra_priority = 250, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx), diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 624f967..9622eb4 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -64,27 +64,31 @@ do { \ #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1; \ + union { typeof(*p) __val; char __c[1]; } __u; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("ldarb %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u8 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 2: \ asm volatile ("ldarh %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u16 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 4: \ asm volatile ("ldar %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u32 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 8: \ asm volatile ("ldar %0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u64 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ } \ - ___p1; \ + __u.__val; \ }) #define read_barrier_depends() do { } while(0) diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 7fbed69..eb8432b 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -23,7 +23,6 @@ */ #include <linux/types.h> #include <linux/sched.h> -#include <linux/ptrace.h> #define COMPAT_USER_HZ 100 #ifdef __AARCH64EB__ @@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs())) +#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) static inline void __user *arch_compat_alloc_user_space(long len) { diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 54d0ead..61e08f3 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -18,7 +18,6 @@ #ifdef __KERNEL__ -#include <linux/acpi.h> #include <linux/types.h> #include <linux/vmalloc.h> @@ -26,22 +25,16 @@ #include <asm/xen/hypervisor.h> #define DMA_ERROR_CODE (~(dma_addr_t)0) -extern struct dma_map_ops *dma_ops; extern struct dma_map_ops dummy_dma_ops; static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { - if (unlikely(!dev)) - return dma_ops; - else if (dev->archdata.dma_ops) + if (dev && dev->archdata.dma_ops) return dev->archdata.dma_ops; - else if (acpi_disabled) - return dma_ops; /* - * When ACPI is enabled, if arch_set_dma_ops is not called, - * we will disable device DMA capability by setting it - * to dummy_dma_ops. + * We expect no ISA devices, and all other DMA masters are expected to + * have someone call arch_setup_dma_ops at device creation time. */ return &dummy_dma_ops; } diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index c0e8789..2416578 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -101,7 +101,7 @@ static inline void cpu_set_default_tcr_t0sz(void) #define destroy_context(mm) do { } while(0) void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); -#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) +#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) /* * This is called when "tsk" is about to enter lazy TLB mode. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 9819a94..7e074f9 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -81,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 706679d..212ae63 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -30,6 +30,7 @@ #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/delay.h> /* * In case the boot CPU is hotpluggable, we record its initial state and @@ -112,6 +113,10 @@ static int c_show(struct seq_file *m, void *v) */ seq_printf(m, "processor\t: %d\n", i); + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000UL/HZ), + loops_per_jiffy / (5000UL/HZ) % 100); + /* * Dump out the common processor features in a single line. * Userspace should read the hwcaps with getauxval(AT_HWCAP) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index de46b50..fc5508e 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -224,6 +224,8 @@ static bool __init efi_virtmap_init(void) { efi_memory_desc_t *md; + init_new_context(NULL, &efi_mm); + for_each_efi_memory_desc(&memmap, md) { u64 paddr, npages, size; pgprot_t prot; @@ -254,7 +256,8 @@ static bool __init efi_virtmap_init(void) else prot = PAGE_KERNEL; - create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot); + create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, + __pgprot(pgprot_val(prot) | PTE_NG)); } return true; } @@ -329,14 +332,7 @@ core_initcall(arm64_dmi_init); static void efi_set_pgd(struct mm_struct *mm) { - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); - - local_flush_tlb_all(); - if (icache_is_aivivt()) - __local_flush_icache_all(); + switch_mm(NULL, mm, NULL); } void efi_virtmap_load(void) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index fce95e1..1095aa4 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -1,3 +1,4 @@ +#include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/slab.h> #include <asm/cacheflush.h> @@ -71,6 +72,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) local_dbg_save(flags); /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + + /* * mm context saved on the stack, it will be restored when * the cpu comes out of reset through the identity mapped * page tables, so that the thread address space is properly @@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) hw_breakpoint_restore(NULL); } + unpause_graph_tracing(); + /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 131a199..7963aa4 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -18,6 +18,7 @@ */ #include <linux/gfp.h> +#include <linux/acpi.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/genalloc.h> @@ -28,9 +29,6 @@ #include <asm/cacheflush.h> -struct dma_map_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, bool coherent) { @@ -515,13 +513,7 @@ EXPORT_SYMBOL(dummy_dma_ops); static int __init arm64_dma_init(void) { - int ret; - - dma_ops = &swiotlb_dma_ops; - - ret = atomic_pool_init(); - - return ret; + return atomic_pool_init(); } arch_initcall(arm64_dma_init); @@ -552,10 +544,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, { bool coherent = is_device_dma_coherent(dev); int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent); + size_t iosize = size; void *addr; if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) return NULL; + + size = PAGE_ALIGN(size); + /* * Some drivers rely on this, and we probably don't want the * possibility of stale kernel data being read by devices anyway. @@ -566,7 +562,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, struct page **pages; pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); - pages = iommu_dma_alloc(dev, size, gfp, ioprot, handle, + pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle, flush_page); if (!pages) return NULL; @@ -574,7 +570,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, __builtin_return_address(0)); if (!addr) - iommu_dma_free(dev, pages, size, handle); + iommu_dma_free(dev, pages, iosize, handle); } else { struct page *page; /* @@ -591,7 +587,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, if (!addr) return NULL; - *handle = iommu_dma_map_page(dev, page, 0, size, ioprot); + *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); if (iommu_dma_mapping_error(dev, *handle)) { if (coherent) __free_pages(page, get_order(size)); @@ -606,6 +602,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs) { + size_t iosize = size; + + size = PAGE_ALIGN(size); /* * @cpu_addr will be one of 3 things depending on how it was allocated: * - A remapped array of pages from iommu_dma_alloc(), for all @@ -617,17 +616,17 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * Hence how dodgy the below logic looks... */ if (__in_atomic_pool(cpu_addr, size)) { - iommu_dma_unmap_page(dev, handle, size, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); __free_from_pool(cpu_addr, size); } else if (is_vmalloc_addr(cpu_addr)){ struct vm_struct *area = find_vm_area(cpu_addr); if (WARN_ON(!area || !area->pages)) return; - iommu_dma_free(dev, area->pages, size, &handle); + iommu_dma_free(dev, area->pages, iosize, &handle); dma_common_free_remap(cpu_addr, size, VM_USERMAP); } else { - iommu_dma_unmap_page(dev, handle, size, 0, NULL); + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); __free_pages(virt_to_page(cpu_addr), get_order(size)); } } @@ -984,8 +983,8 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, struct iommu_ops *iommu, bool coherent) { - if (!acpi_disabled && !dev->archdata.dma_ops) - dev->archdata.dma_ops = dma_ops; + if (!dev->archdata.dma_ops) + dev->archdata.dma_ops = &swiotlb_dma_ops; dev->archdata.dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e3f563c..abb66f8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -362,8 +362,8 @@ static void __init __map_memblock(phys_addr_t start, phys_addr_t end) * for now. This will get more fine grained later once all memory * is mapped */ - unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); - unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); + unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); if (end < kernel_x_start) { create_mapping(start, __phys_to_virt(start), @@ -451,18 +451,18 @@ static void __init fixup_executable(void) { #ifdef CONFIG_DEBUG_RODATA /* now that we are actually fully mapped, make the start/end more fine grained */ - if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_start = round_down(__pa(_stext), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(aligned_start, __phys_to_virt(aligned_start), __pa(_stext) - aligned_start, PAGE_KERNEL); } - if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_end = round_up(__pa(__init_end), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(__pa(__init_end), (unsigned long)__init_end, aligned_end - __pa(__init_end), PAGE_KERNEL); @@ -475,7 +475,7 @@ void mark_rodata_ro(void) { create_mapping_late(__pa(_stext), (unsigned long)_stext, (unsigned long)_etext - (unsigned long)_stext, - PAGE_KERNEL_EXEC | PTE_RDONLY); + PAGE_KERNEL_ROX); } #endif diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index cf3c7d4..d6a53ef 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -50,7 +50,7 @@ static const int bpf2a64[] = { [BPF_REG_8] = A64_R(21), [BPF_REG_9] = A64_R(22), /* read-only frame pointer to access stack */ - [BPF_REG_FP] = A64_FP, + [BPF_REG_FP] = A64_R(25), /* temporary register for internal BPF JIT */ [TMP_REG_1] = A64_R(23), [TMP_REG_2] = A64_R(24), @@ -155,18 +155,49 @@ static void build_prologue(struct jit_ctx *ctx) stack_size += 4; /* extra for skb_copy_bits buffer */ stack_size = STACK_ALIGN(stack_size); + /* + * BPF prog stack layout + * + * high + * original A64_SP => 0:+-----+ BPF prologue + * |FP/LR| + * current A64_FP => -16:+-----+ + * | ... | callee saved registers + * +-----+ + * | | x25/x26 + * BPF fp register => -80:+-----+ + * | | + * | ... | BPF prog stack + * | | + * | | + * current A64_SP => +-----+ + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + * + */ + + /* Save FP and LR registers to stay align with ARM64 AAPCS */ + emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); + emit(A64_MOV(1, A64_FP, A64_SP), ctx); + /* Save callee-saved register */ emit(A64_PUSH(r6, r7, A64_SP), ctx); emit(A64_PUSH(r8, r9, A64_SP), ctx); if (ctx->tmp_used) emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx); - /* Set up BPF stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Save fp (x25) and x26. SP requires 16 bytes alignment */ + emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx); - /* Set up frame pointer */ + /* Set up BPF prog stack base register (x25) */ emit(A64_MOV(1, fp, A64_SP), ctx); + /* Set up function call stack */ + emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Clear registers A and X */ emit_a64_mov_i64(ra, 0, ctx); emit_a64_mov_i64(rx, 0, ctx); @@ -190,14 +221,17 @@ static void build_epilogue(struct jit_ctx *ctx) /* We're done with BPF stack */ emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Restore fs (x25) and x26 */ + emit(A64_POP(fp, A64_R(26), A64_SP), ctx); + /* Restore callee-saved register */ if (ctx->tmp_used) emit(A64_POP(tmp1, tmp2, A64_SP), ctx); emit(A64_POP(r8, r9, A64_SP), ctx); emit(A64_POP(r6, r7, A64_SP), ctx); - /* Restore frame pointer */ - emit(A64_MOV(1, fp, A64_SP), ctx); + /* Restore FP/LR registers */ + emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); /* Set return value */ emit(A64_MOV(1, A64_R(0), r0), ctx); @@ -758,7 +792,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog) if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, image_size, 2, ctx.image); - bpf_flush_icache(ctx.image, ctx.image + ctx.idx); + bpf_flush_icache(header, ctx.image + ctx.idx); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)ctx.image; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index c365469..729f891 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -108,6 +108,9 @@ config PGTABLE_LEVELS default 3 if 64BIT && PARISC_PAGE_SIZE_4KB default 2 +config SYS_SUPPORTS_HUGETLBFS + def_bool y if PA20 + source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h new file mode 100644 index 0000000..7d56a9c --- /dev/null +++ b/arch/parisc/include/asm/hugetlb.h @@ -0,0 +1,85 @@ +#ifndef _ASM_PARISC64_HUGETLB_H +#define _ASM_PARISC64_HUGETLB_H + +#include <asm/page.h> +#include <asm-generic/hugetlb.h> + + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) { + return 0; +} + +/* + * If the arch doesn't supply something else, assume that hugepage + * size aligned regions are ok without further preparation. + */ +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + if (len & ~HPAGE_MASK) + return -EINVAL; + if (addr & ~HPAGE_MASK) + return -EINVAL; + return 0; +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, + unsigned long ceiling) +{ + free_pgd_range(tlb, addr, end, floor, ceiling); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t old_pte = *ptep; + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + int changed = !pte_same(*ptep, pte); + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_page(vma, addr); + } + return changed; +} + +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + return *ptep; +} + +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + +#endif /* _ASM_PARISC64_HUGETLB_H */ diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 60d5d17..80e742a 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -145,11 +145,22 @@ extern int npmem_ranges; #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_HUGETLB_PAGE -#define HPAGE_SHIFT 22 /* 4MB (is this fixed?) */ +#define HPAGE_SHIFT PMD_SHIFT /* fixed for transparent huge pages */ #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB) +# define REAL_HPAGE_SHIFT 20 /* 20 = 1MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_1M +#elif !defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB) +# define REAL_HPAGE_SHIFT 22 /* 22 = 4MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4M +#else +# define REAL_HPAGE_SHIFT 24 /* 24 = 16MB */ +# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16M #endif +#endif /* CONFIG_HUGETLB_PAGE */ #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 3edbb9f..f2fd327 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -35,7 +35,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) PxD_FLAG_VALID | PxD_FLAG_ATTACHED) + (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT)); - /* The first pmd entry also is marked with _PAGE_GATEWAY as + /* The first pmd entry also is marked with PxD_FLAG_ATTACHED as * a signal that this pmd may not be freed */ __pgd_val_set(*pgd, PxD_FLAG_ATTACHED); #endif diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index f93c4a4..d8534f9 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -83,7 +83,11 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e)) /* This is the size of the initially mapped kernel memory */ -#define KERNEL_INITIAL_ORDER 24 /* 0 to 1<<24 = 16MB */ +#ifdef CONFIG_64BIT +#define KERNEL_INITIAL_ORDER 25 /* 1<<25 = 32MB */ +#else +#define KERNEL_INITIAL_ORDER 24 /* 1<<24 = 16MB */ +#endif #define KERNEL_INITIAL_SIZE (1 << KERNEL_INITIAL_ORDER) #if CONFIG_PGTABLE_LEVELS == 3 @@ -167,7 +171,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define _PAGE_NO_CACHE_BIT 24 /* (0x080) Uncached Page (U bit) */ #define _PAGE_ACCESSED_BIT 23 /* (0x100) Software: Page Accessed */ #define _PAGE_PRESENT_BIT 22 /* (0x200) Software: translation valid */ -/* bit 21 was formerly the FLUSH bit but is now unused */ +#define _PAGE_HPAGE_BIT 21 /* (0x400) Software: Huge Page */ #define _PAGE_USER_BIT 20 /* (0x800) Software: User accessible page */ /* N.B. The bits are defined in terms of a 32 bit word above, so the */ @@ -194,6 +198,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT)) #define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT)) #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) +#define _PAGE_HUGE (1 << xlate_pabit(_PAGE_HPAGE_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) @@ -217,7 +222,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #define PxD_FLAG_VALID (1 << xlate_pabit(_PxD_VALID_BIT)) #define PxD_FLAG_MASK (0xf) #define PxD_FLAG_SHIFT (4) -#define PxD_VALUE_SHIFT (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */ +#define PxD_VALUE_SHIFT (PFN_PTE_SHIFT-PxD_FLAG_SHIFT) #ifndef __ASSEMBLY__ @@ -363,6 +368,18 @@ static inline pte_t pte_mkwrite(pte_t pte) { pte_val(pte) |= _PAGE_WRITE; return static inline pte_t pte_mkspecial(pte_t pte) { return pte; } /* + * Huge pte definitions. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define pte_huge(pte) (pte_val(pte) & _PAGE_HUGE) +#define pte_mkhuge(pte) (__pte(pte_val(pte) | _PAGE_HUGE)) +#else +#define pte_huge(pte) (0) +#define pte_mkhuge(pte) (pte) +#endif + + +/* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ @@ -410,8 +427,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* Find an entry in the second-level page table.. */ #if CONFIG_PGTABLE_LEVELS == 3 +#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) #define pmd_offset(dir,address) \ -((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1))) +((pmd_t *) pgd_page_vaddr(*(dir)) + pmd_index(address)) #else #define pmd_offset(dir,addr) ((pmd_t *) dir) #endif diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 54adb60..7e759ec 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -192,33 +192,6 @@ void show_trace(struct task_struct *task, unsigned long *stack); */ typedef unsigned int elf_caddr_t; -#define start_thread_som(regs, new_pc, new_sp) do { \ - unsigned long *sp = (unsigned long *)new_sp; \ - __u32 spaceid = (__u32)current->mm->context; \ - unsigned long pc = (unsigned long)new_pc; \ - /* offset pc for priv. level */ \ - pc |= 3; \ - \ - regs->iasq[0] = spaceid; \ - regs->iasq[1] = spaceid; \ - regs->iaoq[0] = pc; \ - regs->iaoq[1] = pc + 4; \ - regs->sr[2] = LINUX_GATEWAY_SPACE; \ - regs->sr[3] = 0xffff; \ - regs->sr[4] = spaceid; \ - regs->sr[5] = spaceid; \ - regs->sr[6] = spaceid; \ - regs->sr[7] = spaceid; \ - regs->gr[ 0] = USER_PSW; \ - regs->gr[30] = ((new_sp)+63)&~63; \ - regs->gr[31] = pc; \ - \ - get_user(regs->gr[26],&sp[0]); \ - get_user(regs->gr[25],&sp[-1]); \ - get_user(regs->gr[24],&sp[-2]); \ - get_user(regs->gr[23],&sp[-3]); \ -} while(0) - /* The ELF abi wants things done a "wee bit" differently than * som does. Supporting this behavior here avoids * having our own version of create_elf_tables. diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index ecc3ae1..dd4d187 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -49,16 +49,6 @@ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ -/* The range 12-64 is reserved for page size specification. */ -#define MADV_4K_PAGES 12 /* Use 4K pages */ -#define MADV_16K_PAGES 14 /* Use 16K pages */ -#define MADV_64K_PAGES 16 /* Use 64K pages */ -#define MADV_256K_PAGES 18 /* Use 256K pages */ -#define MADV_1M_PAGES 20 /* Use 1 Megabyte pages */ -#define MADV_4M_PAGES 22 /* Use 4 Megabyte pages */ -#define MADV_16M_PAGES 24 /* Use 16 Megabyte pages */ -#define MADV_64M_PAGES 26 /* Use 64 Megabyte pages */ - #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 59001ce..d2f6257 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -290,6 +290,14 @@ int main(void) DEFINE(ASM_PFN_PTE_SHIFT, PFN_PTE_SHIFT); DEFINE(ASM_PT_INITIAL, PT_INITIAL); BLANK(); + /* HUGEPAGE_SIZE is only used in vmlinux.lds.S to align kernel text + * and kernel data on physical huge pages */ +#ifdef CONFIG_HUGETLB_PAGE + DEFINE(HUGEPAGE_SIZE, 1UL << REAL_HPAGE_SHIFT); +#else + DEFINE(HUGEPAGE_SIZE, PAGE_SIZE); +#endif + BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index c5ef408..623496c 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -502,21 +502,38 @@ STREG \pte,0(\ptp) .endm + /* We have (depending on the page size): + * - 38 to 52-bit Physical Page Number + * - 12 to 26-bit page offset + */ /* bitshift difference between a PFN (based on kernel's PAGE_SIZE) * to a CPU TLB 4k PFN (4k => 12 bits to shift) */ - #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + #define PAGE_ADD_HUGE_SHIFT (REAL_HPAGE_SHIFT-12) /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ - .macro convert_for_tlb_insert20 pte + .macro convert_for_tlb_insert20 pte,tmp +#ifdef CONFIG_HUGETLB_PAGE + copy \pte,\tmp + extrd,u \tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ + 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + + depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ + (63-58)+PAGE_ADD_SHIFT,\pte + extrd,u,*= \tmp,_PAGE_HPAGE_BIT+32,1,%r0 + depdi _HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\ + (63-58)+PAGE_ADD_HUGE_SHIFT,\pte +#else /* Huge pages disabled */ extrd,u \pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte +#endif .endm /* Convert the pte and prot to tlb insertion values. How * this happens is quite subtle, read below */ - .macro make_insert_tlb spc,pte,prot + .macro make_insert_tlb spc,pte,prot,tmp space_to_prot \spc \prot /* create prot id from space */ /* The following is the real subtlety. This is depositing * T <-> _PAGE_REFTRAP @@ -553,7 +570,7 @@ depdi 1,12,1,\prot /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ - convert_for_tlb_insert20 \pte + convert_for_tlb_insert20 \pte \tmp .endm /* Identical macro to make_insert_tlb above, except it @@ -646,17 +663,12 @@ /* - * Align fault_vector_20 on 4K boundary so that both - * fault_vector_11 and fault_vector_20 are on the - * same page. This is only necessary as long as we - * write protect the kernel text, which we may stop - * doing once we use large page translations to cover - * the static part of the kernel address space. + * Fault_vectors are architecturally required to be aligned on a 2K + * boundary */ .text - - .align 4096 + .align 2048 ENTRY(fault_vector_20) /* First vector is invalid (0) */ @@ -1147,7 +1159,7 @@ dtlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1173,7 +1185,7 @@ nadtlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1267,7 +1279,7 @@ dtlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,dtlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1295,7 +1307,7 @@ nadtlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,nadtlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1404,7 +1416,7 @@ itlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,itlb_fault update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 iitlbt pte,prot @@ -1428,7 +1440,7 @@ naitlb_miss_20w: tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20w update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 iitlbt pte,prot @@ -1514,7 +1526,7 @@ itlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,itlb_fault update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1534,7 +1546,7 @@ naitlb_miss_20: tlb_lock spc,ptp,pte,t0,t1,naitlb_check_alias_20 update_accessed ptp,pte,t0,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 @@ -1566,7 +1578,7 @@ dbit_trap_20w: tlb_lock spc,ptp,pte,t0,t1,dbit_fault update_dirty ptp,pte,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 idtlbt pte,prot @@ -1610,7 +1622,7 @@ dbit_trap_20: tlb_lock spc,ptp,pte,t0,t1,dbit_fault update_dirty ptp,pte,t1 - make_insert_tlb spc,pte,prot + make_insert_tlb spc,pte,prot,t1 f_extend pte,t1 diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index e7d6452..75aa0db 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -69,7 +69,7 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) - /* Initialize startup VM. Just map first 8/16 MB of memory */ + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */ mtctl %r4,%cr25 /* Initialize user root pointer */ @@ -107,7 +107,7 @@ $bss_loop: /* Now initialize the PTEs themselves. We use RWX for * everything ... it will get remapped correctly later */ ldo 0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */ - ldi (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ + load32 (1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */ load32 PA(pg0),%r1 $pgt_fill_loop: diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 72a3c65..f7ea626 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -130,7 +130,16 @@ void __init setup_arch(char **cmdline_p) printk(KERN_INFO "The 32-bit Kernel has started...\n"); #endif - printk(KERN_INFO "Default page size is %dKB.\n", (int)(PAGE_SIZE / 1024)); + printk(KERN_INFO "Kernel default page size is %d KB. Huge pages ", + (int)(PAGE_SIZE / 1024)); +#ifdef CONFIG_HUGETLB_PAGE + printk(KERN_CONT "enabled with %d MB physical and %d MB virtual size", + 1 << (REAL_HPAGE_SHIFT - 20), 1 << (HPAGE_SHIFT - 20)); +#else + printk(KERN_CONT "disabled"); +#endif + printk(KERN_CONT ".\n"); + pdc_console_init(); @@ -377,6 +386,7 @@ arch_initcall(parisc_init); void start_parisc(void) { extern void start_kernel(void); + extern void early_trap_init(void); int ret, cpunum; struct pdc_coproc_cfg coproc_cfg; @@ -397,6 +407,8 @@ void start_parisc(void) panic("must have an fpu to boot linux"); } + early_trap_init(); /* initialize checksum of fault_vector */ + start_kernel(); // not reached } diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 0b8d26d..3fbd725 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -369,7 +369,7 @@ tracesys_exit: ldo -16(%r30),%r29 /* Reference param save area */ #endif ldo TASK_REGS(%r1),%r26 - bl do_syscall_trace_exit,%r2 + BL do_syscall_trace_exit,%r2 STREG %r28,TASK_PT_GR28(%r1) /* save return value now */ ldo -THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1 /* get task ptr */ LDREG TI_TASK(%r1), %r1 @@ -390,7 +390,7 @@ tracesys_sigexit: #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif - bl do_syscall_trace_exit,%r2 + BL do_syscall_trace_exit,%r2 ldo TASK_REGS(%r1),%r26 ldil L%syscall_exit_rfi,%r1 diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b99b39f..553b098 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -807,7 +807,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) } -int __init check_ivt(void *iva) +void __init initialize_ivt(const void *iva) { extern u32 os_hpmc_size; extern const u32 os_hpmc[]; @@ -818,8 +818,8 @@ int __init check_ivt(void *iva) u32 *hpmcp; u32 length; - if (strcmp((char *)iva, "cows can fly")) - return -1; + if (strcmp((const char *)iva, "cows can fly")) + panic("IVT invalid"); ivap = (u32 *)iva; @@ -839,28 +839,23 @@ int __init check_ivt(void *iva) check += ivap[i]; ivap[5] = -check; - - return 0; } -#ifndef CONFIG_64BIT -extern const void fault_vector_11; -#endif -extern const void fault_vector_20; -void __init trap_init(void) +/* early_trap_init() is called before we set up kernel mappings and + * write-protect the kernel */ +void __init early_trap_init(void) { - void *iva; + extern const void fault_vector_20; - if (boot_cpu_data.cpu_type >= pcxu) - iva = (void *) &fault_vector_20; - else -#ifdef CONFIG_64BIT - panic("Can't boot 64-bit OS on PA1.1 processor!"); -#else - iva = (void *) &fault_vector_11; +#ifndef CONFIG_64BIT + extern const void fault_vector_11; + initialize_ivt(&fault_vector_11); #endif - if (check_ivt(iva)) - panic("IVT invalid"); + initialize_ivt(&fault_vector_20); +} + +void __init trap_init(void) +{ } diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 0dacc5c..308f290 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -60,7 +60,7 @@ SECTIONS EXIT_DATA } PERCPU_SECTION(8) - . = ALIGN(PAGE_SIZE); + . = ALIGN(HUGEPAGE_SIZE); __init_end = .; /* freed after init ends here */ @@ -116,7 +116,7 @@ SECTIONS * that we can properly leave these * as writable */ - . = ALIGN(PAGE_SIZE); + . = ALIGN(HUGEPAGE_SIZE); data_start = .; EXCEPTION_TABLE(8) @@ -135,8 +135,11 @@ SECTIONS _edata = .; /* BSS */ - BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 8) + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE) + + /* bootmap is allocated in setup_bootmem() directly behind bss. */ + . = ALIGN(HUGEPAGE_SIZE); _end = . ; STABS_DEBUG diff --git a/arch/parisc/mm/Makefile b/arch/parisc/mm/Makefile index 758ceef..134393d 100644 --- a/arch/parisc/mm/Makefile +++ b/arch/parisc/mm/Makefile @@ -3,3 +3,4 @@ # obj-y := init.o fault.o ioremap.o +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c new file mode 100644 index 0000000..f6fdc77 --- /dev/null +++ b/arch/parisc/mm/hugetlbpage.c @@ -0,0 +1,161 @@ +/* + * PARISC64 Huge TLB page support. + * + * This parisc implementation is heavily based on the SPARC and x86 code. + * + * Copyright (C) 2015 Helge Deller <deller@gmx.de> + */ + +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/pagemap.h> +#include <linux/sysctl.h> + +#include <asm/mman.h> +#include <asm/pgalloc.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/mmu_context.h> + + +unsigned long +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct hstate *h = hstate_file(file); + + if (len & ~huge_page_mask(h)) + return -EINVAL; + if (len > TASK_SIZE) + return -ENOMEM; + + if (flags & MAP_FIXED) + if (prepare_hugepage_range(file, addr, len)) + return -EINVAL; + + if (addr) + addr = ALIGN(addr, huge_page_size(h)); + + /* we need to make sure the colouring is OK */ + return arch_get_unmapped_area(file, addr, len, pgoff, flags); +} + + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + /* We must align the address, because our caller will run + * set_huge_pte_at() on whatever we return, which writes out + * all of the sub-ptes for the hugepage range. So we have + * to give it the first such sub-pte. + */ + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd = pmd_alloc(mm, pud, addr); + if (pmd) + pte = pte_alloc_map(mm, NULL, pmd, addr); + } + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + if (!pgd_none(*pgd)) { + pud = pud_offset(pgd, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + pte = pte_offset_map(pmd, addr); + } + } + return pte; +} + +/* Purge data and instruction TLB entries. Must be called holding + * the pa_tlb_lock. The TLB purge instructions are slow on SMP + * machines since the purge must be broadcast to all CPUs. + */ +static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long addr) +{ + int i; + + /* We may use multiple physical huge pages (e.g. 2x1 MB) to emulate + * Linux standard huge pages (e.g. 2 MB) */ + BUILD_BUG_ON(REAL_HPAGE_SHIFT > HPAGE_SHIFT); + + addr &= HPAGE_MASK; + addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; + + for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { + mtsp(mm->context, 1); + pdtlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); + addr += (1UL << REAL_HPAGE_SHIFT); + } +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long addr_start; + int i; + + addr &= HPAGE_MASK; + addr_start = addr; + + for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { + /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) + * instead, but then we get double locking on pa_tlb_lock. */ + *ptep = entry; + ptep++; + + /* Drop the PAGE_SIZE/non-huge tlb entry */ + purge_tlb_entries(mm, addr); + + addr += PAGE_SIZE; + pte_val(entry) += PAGE_SIZE; + } + + purge_tlb_entries_huge(mm, addr_start); +} + + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t entry; + + entry = *ptep; + set_huge_pte_at(mm, addr, ptep, __pte(0)); + + return entry; +} + +int pmd_huge(pmd_t pmd) +{ + return 0; +} + +int pud_huge(pud_t pud) +{ + return 0; +} diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index c5fec48..1b366c4 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -409,15 +409,11 @@ static void __init map_pages(unsigned long start_vaddr, unsigned long vaddr; unsigned long ro_start; unsigned long ro_end; - unsigned long fv_addr; - unsigned long gw_addr; - extern const unsigned long fault_vector_20; - extern void * const linux_gateway_page; + unsigned long kernel_end; ro_start = __pa((unsigned long)_text); ro_end = __pa((unsigned long)&data_start); - fv_addr = __pa((unsigned long)&fault_vector_20) & PAGE_MASK; - gw_addr = __pa((unsigned long)&linux_gateway_page) & PAGE_MASK; + kernel_end = __pa((unsigned long)&_end); end_paddr = start_paddr + size; @@ -475,24 +471,25 @@ static void __init map_pages(unsigned long start_vaddr, for (tmp2 = start_pte; tmp2 < PTRS_PER_PTE; tmp2++, pg_table++) { pte_t pte; - /* - * Map the fault vector writable so we can - * write the HPMC checksum. - */ if (force) pte = __mk_pte(address, pgprot); - else if (parisc_text_address(vaddr) && - address != fv_addr) + else if (parisc_text_address(vaddr)) { pte = __mk_pte(address, PAGE_KERNEL_EXEC); + if (address >= ro_start && address < kernel_end) + pte = pte_mkhuge(pte); + } else #if defined(CONFIG_PARISC_PAGE_SIZE_4KB) - if (address >= ro_start && address < ro_end - && address != fv_addr - && address != gw_addr) - pte = __mk_pte(address, PAGE_KERNEL_RO); - else + if (address >= ro_start && address < ro_end) { + pte = __mk_pte(address, PAGE_KERNEL_EXEC); + pte = pte_mkhuge(pte); + } else #endif + { pte = __mk_pte(address, pgprot); + if (address >= ro_start && address < kernel_end) + pte = pte_mkhuge(pte); + } if (address >= end_paddr) { if (force) @@ -536,15 +533,12 @@ void free_initmem(void) /* force the kernel to see the new TLB entries */ __flush_tlb_range(0, init_begin, init_end); - /* Attempt to catch anyone trying to execute code here - * by filling the page with BRK insns. - */ - memset((void *)init_begin, 0x00, init_end - init_begin); + /* finally dump all the instructions which were cached, since the * pages are no-longer executable */ flush_icache_range(init_begin, init_end); - free_initmem_default(-1); + free_initmem_default(POISON_FREE_INITMEM); /* set up a new led state on systems shipped LED State panel */ pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE); @@ -728,8 +722,8 @@ static void __init pagetable_init(void) unsigned long size; start_paddr = pmem_ranges[range].start_pfn << PAGE_SHIFT; - end_paddr = start_paddr + (pmem_ranges[range].pages << PAGE_SHIFT); size = pmem_ranges[range].pages << PAGE_SHIFT; + end_paddr = start_paddr + size; map_pages((unsigned long)__va(start_paddr), start_paddr, size, PAGE_KERNEL, 0); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index c9e26cb..f2b0b1b 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -382,3 +382,4 @@ COMPAT_SYS(shmat) SYSCALL(shmdt) SYSCALL(shmget) COMPAT_SYS(shmctl) +SYSCALL(mlock2) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 6d8f802..4b6b8ac 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 378 +#define __NR_syscalls 379 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 81579e9..1effea5 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -400,5 +400,6 @@ #define __NR_shmdt 375 #define __NR_shmget 376 #define __NR_shmctl 377 +#define __NR_mlock2 378 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 0c5d8ee..d1e7b0a 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -312,6 +312,7 @@ extern void css_schedule_reprobe(void); extern void reipl_ccw_dev(struct ccw_dev_id *id); struct cio_iplinfo { + u8 ssid; u16 devno; int is_qdio; }; diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 3ad48f2..bab6739 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -206,9 +206,16 @@ do { \ } while (0) #endif /* CONFIG_COMPAT */ -extern unsigned long mmap_rnd_mask; - -#define STACK_RND_MASK (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask) +/* + * Cache aliasing on the latest machines calls for a mapping granularity + * of 512KB. For 64-bit processes use a 512KB alignment and a randomization + * of up to 1GB. For 31-bit processes the virtual address space is limited, + * use no alignment and limit the randomization to 8MB. + */ +#define BRK_RND_MASK (is_32bit_task() ? 0x7ffUL : 0x3ffffUL) +#define MMAP_RND_MASK (is_32bit_task() ? 0x7ffUL : 0x3ff80UL) +#define MMAP_ALIGN_MASK (is_32bit_task() ? 0 : 0x7fUL) +#define STACK_RND_MASK MMAP_RND_MASK #define ARCH_DLINFO \ do { \ diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 39ae6a3..86634e7 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -64,7 +64,8 @@ struct ipl_block_fcp { struct ipl_block_ccw { u8 reserved1[84]; - u8 reserved2[2]; + u16 reserved2 : 13; + u8 ssid : 3; u16 devno; u8 vm_flags; u8 reserved3[3]; diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h index 7a7abf1..1aac41e 100644 --- a/arch/s390/include/asm/pci_dma.h +++ b/arch/s390/include/asm/pci_dma.h @@ -195,5 +195,7 @@ void zpci_dma_exit_device(struct zpci_dev *); void dma_free_seg_table(unsigned long); unsigned long *dma_alloc_cpu_table(void); void dma_cleanup_tables(unsigned long *); -void dma_update_cpu_trans(unsigned long *, void *, dma_addr_t, int); +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr); +void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags); + #endif diff --git a/arch/s390/include/asm/trace/diag.h b/arch/s390/include/asm/trace/diag.h index 776f307..cc6cfe7 100644 --- a/arch/s390/include/asm/trace/diag.h +++ b/arch/s390/include/asm/trace/diag.h @@ -19,7 +19,7 @@ #define TRACE_INCLUDE_PATH asm/trace #define TRACE_INCLUDE_FILE diag -TRACE_EVENT(diagnose, +TRACE_EVENT(s390_diagnose, TP_PROTO(unsigned short nr), TP_ARGS(nr), TP_STRUCT__entry( @@ -32,9 +32,9 @@ TRACE_EVENT(diagnose, ); #ifdef CONFIG_TRACEPOINTS -void trace_diagnose_norecursion(int diag_nr); +void trace_s390_diagnose_norecursion(int diag_nr); #else -static inline void trace_diagnose_norecursion(int diag_nr) { } +static inline void trace_s390_diagnose_norecursion(int diag_nr) { } #endif #endif /* _TRACE_S390_DIAG_H */ diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index a848adb..34ec202 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -192,14 +192,14 @@ #define __NR_set_tid_address 252 #define __NR_fadvise64 253 #define __NR_timer_create 254 -#define __NR_timer_settime (__NR_timer_create+1) -#define __NR_timer_gettime (__NR_timer_create+2) -#define __NR_timer_getoverrun (__NR_timer_create+3) -#define __NR_timer_delete (__NR_timer_create+4) -#define __NR_clock_settime (__NR_timer_create+5) -#define __NR_clock_gettime (__NR_timer_create+6) -#define __NR_clock_getres (__NR_timer_create+7) -#define __NR_clock_nanosleep (__NR_timer_create+8) +#define __NR_timer_settime 255 +#define __NR_timer_gettime 256 +#define __NR_timer_getoverrun 257 +#define __NR_timer_delete 258 +#define __NR_clock_settime 259 +#define __NR_clock_gettime 260 +#define __NR_clock_getres 261 +#define __NR_clock_nanosleep 262 /* Number 263 is reserved for vserver */ #define __NR_statfs64 265 #define __NR_fstatfs64 266 @@ -309,7 +309,8 @@ #define __NR_recvfrom 371 #define __NR_recvmsg 372 #define __NR_shutdown 373 -#define NR_syscalls 374 +#define __NR_mlock2 374 +#define NR_syscalls 375 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index 09f1940..fac4eed 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -176,3 +176,4 @@ COMPAT_SYSCALL_WRAP4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len); COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len); COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len); +COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags); diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index f98766e..48b37b8 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -121,14 +121,14 @@ device_initcall(show_diag_stat_init); void diag_stat_inc(enum diag_stat_enum nr) { this_cpu_inc(diag_stat.counter[nr]); - trace_diagnose(diag_map[nr].code); + trace_s390_diagnose(diag_map[nr].code); } EXPORT_SYMBOL(diag_stat_inc); void diag_stat_inc_norecursion(enum diag_stat_enum nr) { this_cpu_inc(diag_stat.counter[nr]); - trace_diagnose_norecursion(diag_map[nr].code); + trace_s390_diagnose_norecursion(diag_map[nr].code); } EXPORT_SYMBOL(diag_stat_inc_norecursion); diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 1255c6c..301ee9c 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -26,6 +26,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page.h> +#include <asm/ptrace.h> #define ARCH_OFFSET 4 @@ -59,19 +60,6 @@ __HEAD .long 0x020006e0,0x20000050 .org 0x200 -# -# subroutine to set architecture mode -# -.Lsetmode: - mvi __LC_AR_MODE_ID,1 # set esame flag - slr %r0,%r0 # set cpuid to zero - lhi %r1,2 # mode 2 = esame (dump) - sigp %r1,%r0,0x12 # switch to esame mode - bras %r13,0f - .fill 16,4,0x0 -0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs - sam31 # switch to 31 bit addressing mode - br %r14 # # subroutine to wait for end I/O @@ -159,7 +147,14 @@ __HEAD .long 0x02200050,0x00000000 iplstart: - bas %r14,.Lsetmode # Immediately switch to 64 bit mode + mvi __LC_AR_MODE_ID,1 # set esame flag + slr %r0,%r0 # set cpuid to zero + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # switch to esame mode + bras %r13,0f + .fill 16,4,0x0 +0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs + sam31 # switch to 31 bit addressing mode lh %r1,0xb8 # test if subchannel number bct %r1,.Lnoload # is valid l %r1,0xb8 # load ipl subchannel number @@ -269,71 +264,6 @@ iplstart: .Lcpuid:.fill 8,1,0 # -# SALIPL loader support. Based on a patch by Rob van der Heij. -# This entry point is called directly from the SALIPL loader and -# doesn't need a builtin ipl record. -# - .org 0x800 -ENTRY(start) - stm %r0,%r15,0x07b0 # store registers - bas %r14,.Lsetmode # Immediately switch to 64 bit mode - basr %r12,%r0 -.base: - l %r11,.parm - l %r8,.cmd # pointer to command buffer - - ltr %r9,%r9 # do we have SALIPL parameters? - bp .sk8x8 - - mvc 0(64,%r8),0x00b0 # copy saved registers - xc 64(240-64,%r8),0(%r8) # remainder of buffer - tr 0(64,%r8),.lowcase - b .gotr -.sk8x8: - mvc 0(240,%r8),0(%r9) # copy iplparms into buffer -.gotr: - slr %r0,%r0 - st %r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11) - st %r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11) - j startup # continue with startup -.cmd: .long COMMAND_LINE # address of command line buffer -.parm: .long PARMAREA -.lowcase: - .byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07 - .byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f - .byte 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17 - .byte 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f - .byte 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27 - .byte 0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f - .byte 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37 - .byte 0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f - .byte 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47 - .byte 0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f - .byte 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57 - .byte 0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f - .byte 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67 - .byte 0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f - .byte 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77 - .byte 0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f - - .byte 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87 - .byte 0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f - .byte 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97 - .byte 0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f - .byte 0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 - .byte 0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf - .byte 0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7 - .byte 0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf - .byte 0xc0,0x81,0x82,0x83,0x84,0x85,0x86,0x87 # .abcdefg - .byte 0x88,0x89,0xca,0xcb,0xcc,0xcd,0xce,0xcf # hi - .byte 0xd0,0x91,0x92,0x93,0x94,0x95,0x96,0x97 # .jklmnop - .byte 0x98,0x99,0xda,0xdb,0xdc,0xdd,0xde,0xdf # qr - .byte 0xe0,0xe1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7 # ..stuvwx - .byte 0xa8,0xa9,0xea,0xeb,0xec,0xed,0xee,0xef # yz - .byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7 - .byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff - -# # startup-code at 0x10000, running in absolute addressing mode # this is called either by the ipl loader or directly by PSW restart # or linload or SALIPL @@ -364,7 +294,7 @@ ENTRY(startup_kdump) bras %r13,0f .fill 16,4,0x0 0: lmh %r0,%r15,0(%r13) # clear high-order half of gprs - sam31 # switch to 31 bit addressing mode + sam64 # switch to 64 bit addressing mode basr %r13,0 # get base .LPG0: xc 0x200(256),0x200 # partially clear lowcore @@ -395,7 +325,7 @@ ENTRY(startup_kdump) jnz 1b j 4f 2: l %r15,.Lstack-.LPG0(%r13) - ahi %r15,-96 + ahi %r15,-STACK_FRAME_OVERHEAD la %r2,.Lals_string-.LPG0(%r13) l %r3,.Lsclp_print-.LPG0(%r13) basr %r14,%r3 @@ -429,8 +359,7 @@ ENTRY(startup_kdump) .long 1, 0xc0000000 #endif 4: - /* Continue with 64bit startup code in head64.S */ - sam64 # switch to 64 bit mode + /* Continue with startup code in head64.S */ jg startup_continue .align 8 diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index f6d8acd..b1f0a90 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -121,6 +121,7 @@ static char *dump_type_str(enum dump_type type) * Must be in data section since the bss section * is not cleared when these are accessed. */ +static u8 ipl_ssid __attribute__((__section__(".data"))) = 0; static u16 ipl_devno __attribute__((__section__(".data"))) = 0; u32 ipl_flags __attribute__((__section__(".data"))) = 0; @@ -197,6 +198,33 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ return snprintf(page, PAGE_SIZE, _format, ##args); \ } +#define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk) \ +static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + const char *buf, size_t len) \ +{ \ + unsigned long long ssid, devno; \ + \ + if (sscanf(buf, "0.%llx.%llx\n", &ssid, &devno) != 2) \ + return -EINVAL; \ + \ + if (ssid > __MAX_SSID || devno > __MAX_SUBCHANNEL) \ + return -EINVAL; \ + \ + _ipl_blk.ssid = ssid; \ + _ipl_blk.devno = devno; \ + return len; \ +} + +#define DEFINE_IPL_CCW_ATTR_RW(_prefix, _name, _ipl_blk) \ +IPL_ATTR_SHOW_FN(_prefix, _name, "0.%x.%04x\n", \ + _ipl_blk.ssid, _ipl_blk.devno); \ +IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk); \ +static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ + __ATTR(_name, (S_IRUGO | S_IWUSR), \ + sys_##_prefix##_##_name##_show, \ + sys_##_prefix##_##_name##_store) \ + #define DEFINE_IPL_ATTR_RO(_prefix, _name, _format, _value) \ IPL_ATTR_SHOW_FN(_prefix, _name, _format, _value) \ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ @@ -395,7 +423,7 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj, switch (ipl_info.type) { case IPL_TYPE_CCW: - return sprintf(page, "0.0.%04x\n", ipl_devno); + return sprintf(page, "0.%x.%04x\n", ipl_ssid, ipl_devno); case IPL_TYPE_FCP: case IPL_TYPE_FCP_DUMP: return sprintf(page, "0.0.%04x\n", ipl->ipl_info.fcp.devno); @@ -687,21 +715,14 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { + size_t scpdata_len = count; size_t padding; - size_t scpdata_len; - - if (off < 0) - return -EINVAL; - if (off >= DIAG308_SCPDATA_SIZE) - return -ENOSPC; - if (count > DIAG308_SCPDATA_SIZE - off) - count = DIAG308_SCPDATA_SIZE - off; - - memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count); - scpdata_len = off + count; + if (off) + return -EINVAL; + memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf, count); if (scpdata_len % 8) { padding = 8 - (scpdata_len % 8); memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len, @@ -717,7 +738,7 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj, } static struct bin_attribute sys_reipl_fcp_scp_data_attr = __BIN_ATTR(scp_data, (S_IRUGO | S_IWUSR), reipl_fcp_scpdata_read, - reipl_fcp_scpdata_write, PAGE_SIZE); + reipl_fcp_scpdata_write, DIAG308_SCPDATA_SIZE); static struct bin_attribute *reipl_fcp_bin_attrs[] = { &sys_reipl_fcp_scp_data_attr, @@ -814,9 +835,7 @@ static struct attribute_group reipl_fcp_attr_group = { }; /* CCW reipl device attributes */ - -DEFINE_IPL_ATTR_RW(reipl_ccw, device, "0.0.%04llx\n", "0.0.%llx\n", - reipl_block_ccw->ipl_info.ccw.devno); +DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ipl_info.ccw); /* NSS wrapper */ static ssize_t reipl_nss_loadparm_show(struct kobject *kobj, @@ -1056,8 +1075,8 @@ static void __reipl_run(void *unused) switch (reipl_method) { case REIPL_METHOD_CCW_CIO: + devid.ssid = reipl_block_ccw->ipl_info.ccw.ssid; devid.devno = reipl_block_ccw->ipl_info.ccw.devno; - devid.ssid = 0; reipl_ccw_dev(&devid); break; case REIPL_METHOD_CCW_VM: @@ -1192,6 +1211,7 @@ static int __init reipl_ccw_init(void) reipl_block_ccw_init(reipl_block_ccw); if (ipl_info.type == IPL_TYPE_CCW) { + reipl_block_ccw->ipl_info.ccw.ssid = ipl_ssid; reipl_block_ccw->ipl_info.ccw.devno = ipl_devno; reipl_block_ccw_fill_parms(reipl_block_ccw); } @@ -1336,9 +1356,7 @@ static struct attribute_group dump_fcp_attr_group = { }; /* CCW dump device attributes */ - -DEFINE_IPL_ATTR_RW(dump_ccw, device, "0.0.%04llx\n", "0.0.%llx\n", - dump_block_ccw->ipl_info.ccw.devno); +DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ipl_info.ccw); static struct attribute *dump_ccw_attrs[] = { &sys_dump_ccw_device_attr.attr, @@ -1418,8 +1436,8 @@ static void __dump_run(void *unused) switch (dump_method) { case DUMP_METHOD_CCW_CIO: + devid.ssid = dump_block_ccw->ipl_info.ccw.ssid; devid.devno = dump_block_ccw->ipl_info.ccw.devno; - devid.ssid = 0; reipl_ccw_dev(&devid); break; case DUMP_METHOD_CCW_VM: @@ -1939,14 +1957,14 @@ void __init setup_ipl(void) ipl_info.type = get_ipl_type(); switch (ipl_info.type) { case IPL_TYPE_CCW: + ipl_info.data.ccw.dev_id.ssid = ipl_ssid; ipl_info.data.ccw.dev_id.devno = ipl_devno; - ipl_info.data.ccw.dev_id.ssid = 0; break; case IPL_TYPE_FCP: case IPL_TYPE_FCP_DUMP: + ipl_info.data.fcp.dev_id.ssid = 0; ipl_info.data.fcp.dev_id.devno = IPL_PARMBLOCK_START->ipl_info.fcp.devno; - ipl_info.data.fcp.dev_id.ssid = 0; ipl_info.data.fcp.wwpn = IPL_PARMBLOCK_START->ipl_info.fcp.wwpn; ipl_info.data.fcp.lun = IPL_PARMBLOCK_START->ipl_info.fcp.lun; break; @@ -1978,6 +1996,7 @@ void __init ipl_save_parameters(void) if (cio_get_iplinfo(&iplinfo)) return; + ipl_ssid = iplinfo.ssid; ipl_devno = iplinfo.devno; ipl_flags |= IPL_DEVNO_VALID; if (!iplinfo.is_qdio) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 688a3aa..114ee8b 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -243,11 +243,7 @@ unsigned long arch_align_stack(unsigned long sp) static inline unsigned long brk_rnd(void) { - /* 8MB for 32bit, 1GB for 64bit */ - if (is_32bit_task()) - return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; - else - return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT; + return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT; } unsigned long arch_randomize_brk(struct mm_struct *mm) diff --git a/arch/s390/kernel/sclp.c b/arch/s390/kernel/sclp.c index fa0bdff..9fe7781 100644 --- a/arch/s390/kernel/sclp.c +++ b/arch/s390/kernel/sclp.c @@ -21,7 +21,7 @@ static void _sclp_wait_int(void) __ctl_load(cr0_new, 0, 0); psw_ext_save = S390_lowcore.external_new_psw; - psw_mask = __extract_psw() & (PSW_MASK_EA | PSW_MASK_BA); + psw_mask = __extract_psw(); S390_lowcore.external_new_psw.mask = psw_mask; psw_wait.mask = psw_mask | PSW_MASK_EXT | PSW_MASK_WAIT; S390_lowcore.ext_int_code = 0; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ce0cbd6..c837bca 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -764,9 +764,6 @@ static int __init setup_hwcaps(void) get_cpu_id(&cpu_id); add_device_randomness(&cpu_id, sizeof(cpu_id)); switch (cpu_id.machine) { - case 0x9672: - strcpy(elf_platform, "g5"); - break; case 0x2064: case 0x2066: default: /* Use "z900" as default for 64 bit kernels. */ diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 8c56929..5378c3e 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -382,3 +382,4 @@ SYSCALL(sys_sendmsg,compat_sys_sendmsg) /* 370 */ SYSCALL(sys_recvfrom,compat_sys_recvfrom) SYSCALL(sys_recvmsg,compat_sys_recvmsg) SYSCALL(sys_shutdown,sys_shutdown) +SYSCALL(sys_mlock2,compat_sys_mlock2) diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c index 73239bb..21a5df9 100644 --- a/arch/s390/kernel/trace.c +++ b/arch/s390/kernel/trace.c @@ -9,11 +9,11 @@ #define CREATE_TRACE_POINTS #include <asm/trace/diag.h> -EXPORT_TRACEPOINT_SYMBOL(diagnose); +EXPORT_TRACEPOINT_SYMBOL(s390_diagnose); static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth); -void trace_diagnose_norecursion(int diag_nr) +void trace_s390_diagnose_norecursion(int diag_nr) { unsigned long flags; unsigned int *depth; @@ -22,7 +22,7 @@ void trace_diagnose_norecursion(int diag_nr) depth = this_cpu_ptr(&diagnose_trace_depth); if (*depth == 0) { (*depth)++; - trace_diagnose(diag_nr); + trace_s390_diagnose(diag_nr); (*depth)--; } local_irq_restore(flags); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c3c07d3..c722400 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -48,37 +48,13 @@ EXPORT_SYMBOL(zero_page_mask); static void __init setup_zero_pages(void) { - struct cpuid cpu_id; unsigned int order; struct page *page; int i; - get_cpu_id(&cpu_id); - switch (cpu_id.machine) { - case 0x9672: /* g5 */ - case 0x2064: /* z900 */ - case 0x2066: /* z900 */ - case 0x2084: /* z990 */ - case 0x2086: /* z990 */ - case 0x2094: /* z9-109 */ - case 0x2096: /* z9-109 */ - order = 0; - break; - case 0x2097: /* z10 */ - case 0x2098: /* z10 */ - case 0x2817: /* z196 */ - case 0x2818: /* z196 */ - order = 2; - break; - case 0x2827: /* zEC12 */ - case 0x2828: /* zEC12 */ - order = 5; - break; - case 0x2964: /* z13 */ - default: - order = 7; - break; - } + /* Latest machines require a mapping granularity of 512KB */ + order = 7; + /* Limit number of empty zero pages for small memory sizes */ while (order > 2 && (totalram_pages >> 10) < (1UL << order)) order--; diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 6e552af..ea01477 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -31,9 +31,6 @@ #include <linux/security.h> #include <asm/pgalloc.h> -unsigned long mmap_rnd_mask; -static unsigned long mmap_align_mask; - static unsigned long stack_maxrandom_size(void) { if (!(current->flags & PF_RANDOMIZE)) @@ -62,10 +59,7 @@ static inline int mmap_is_legacy(void) unsigned long arch_mmap_rnd(void) { - if (is_32bit_task()) - return (get_random_int() & 0x7ff) << PAGE_SHIFT; - else - return (get_random_int() & mmap_rnd_mask) << PAGE_SHIFT; + return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT; } static unsigned long mmap_base_legacy(unsigned long rnd) @@ -92,7 +86,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct vm_unmapped_area_info info; - int do_color_align; if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; @@ -108,15 +101,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = !is_32bit_task(); - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; - info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0; + if (filp || (flags & MAP_SHARED)) + info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; + else + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } @@ -130,7 +122,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; - int do_color_align; /* requested length too big for entire address space */ if (len > TASK_SIZE - mmap_min_addr) @@ -148,15 +139,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; } - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = !is_32bit_task(); - info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = mm->mmap_base; - info.align_mask = do_color_align ? (mmap_align_mask << PAGE_SHIFT) : 0; + if (filp || (flags & MAP_SHARED)) + info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; + else + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); @@ -254,35 +244,3 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->get_unmapped_area = s390_get_unmapped_area_topdown; } } - -static int __init setup_mmap_rnd(void) -{ - struct cpuid cpu_id; - - get_cpu_id(&cpu_id); - switch (cpu_id.machine) { - case 0x9672: - case 0x2064: - case 0x2066: - case 0x2084: - case 0x2086: - case 0x2094: - case 0x2096: - case 0x2097: - case 0x2098: - case 0x2817: - case 0x2818: - case 0x2827: - case 0x2828: - mmap_rnd_mask = 0x7ffUL; - mmap_align_mask = 0UL; - break; - case 0x2964: /* z13 */ - default: - mmap_rnd_mask = 0x3ff80UL; - mmap_align_mask = 0x7fUL; - break; - } - return 0; -} -early_initcall(setup_mmap_rnd); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 37d10f7..d348f2c 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -33,7 +33,7 @@ unsigned long *dma_alloc_cpu_table(void) return NULL; for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++) - *entry = ZPCI_TABLE_INVALID | ZPCI_TABLE_PROTECTED; + *entry = ZPCI_TABLE_INVALID; return table; } @@ -51,7 +51,7 @@ static unsigned long *dma_alloc_page_table(void) return NULL; for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++) - *entry = ZPCI_PTE_INVALID | ZPCI_TABLE_PROTECTED; + *entry = ZPCI_PTE_INVALID; return table; } @@ -95,7 +95,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *entry) return pto; } -static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) { unsigned long *sto, *pto; unsigned int rtx, sx, px; @@ -114,20 +114,10 @@ static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr return &pto[px]; } -void dma_update_cpu_trans(unsigned long *dma_table, void *page_addr, - dma_addr_t dma_addr, int flags) +void dma_update_cpu_trans(unsigned long *entry, void *page_addr, int flags) { - unsigned long *entry; - - entry = dma_walk_cpu_trans(dma_table, dma_addr); - if (!entry) { - WARN_ON_ONCE(1); - return; - } - if (flags & ZPCI_PTE_INVALID) { invalidate_pt_entry(entry); - return; } else { set_pt_pfaa(entry, page_addr); validate_pt_entry(entry); @@ -146,18 +136,25 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, u8 *page_addr = (u8 *) (pa & PAGE_MASK); dma_addr_t start_dma_addr = dma_addr; unsigned long irq_flags; + unsigned long *entry; int i, rc = 0; if (!nr_pages) return -EINVAL; spin_lock_irqsave(&zdev->dma_table_lock, irq_flags); - if (!zdev->dma_table) + if (!zdev->dma_table) { + rc = -EINVAL; goto no_refresh; + } for (i = 0; i < nr_pages; i++) { - dma_update_cpu_trans(zdev->dma_table, page_addr, dma_addr, - flags); + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + if (!entry) { + rc = -ENOMEM; + goto undo_cpu_trans; + } + dma_update_cpu_trans(entry, page_addr, flags); page_addr += PAGE_SIZE; dma_addr += PAGE_SIZE; } @@ -176,6 +173,18 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, nr_pages * PAGE_SIZE); +undo_cpu_trans: + if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { + flags = ZPCI_PTE_INVALID; + while (i-- > 0) { + page_addr -= PAGE_SIZE; + dma_addr -= PAGE_SIZE; + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + if (!entry) + break; + dma_update_cpu_trans(entry, page_addr, flags); + } + } no_refresh: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); @@ -260,6 +269,16 @@ out: spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); } +static inline void zpci_err_dma(unsigned long rc, unsigned long addr) +{ + struct { + unsigned long rc; + unsigned long addr; + } __packed data = {rc, addr}; + + zpci_err_hex(&data, sizeof(data)); +} + static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction, @@ -270,33 +289,40 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, unsigned long pa = page_to_phys(page) + offset; int flags = ZPCI_PTE_VALID; dma_addr_t dma_addr; + int ret; /* This rounds up number of pages based on size and offset */ nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); iommu_page_index = dma_alloc_iommu(zdev, nr_pages); - if (iommu_page_index == -1) + if (iommu_page_index == -1) { + ret = -ENOSPC; goto out_err; + } /* Use rounded up size */ size = nr_pages * PAGE_SIZE; dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE; - if (dma_addr + size > zdev->end_dma) + if (dma_addr + size > zdev->end_dma) { + ret = -ERANGE; goto out_free; + } if (direction == DMA_NONE || direction == DMA_TO_DEVICE) flags |= ZPCI_TABLE_PROTECTED; - if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) { - atomic64_add(nr_pages, &zdev->mapped_pages); - return dma_addr + (offset & ~PAGE_MASK); - } + ret = dma_update_trans(zdev, pa, dma_addr, size, flags); + if (ret) + goto out_free; + + atomic64_add(nr_pages, &zdev->mapped_pages); + return dma_addr + (offset & ~PAGE_MASK); out_free: dma_free_iommu(zdev, iommu_page_index, nr_pages); out_err: zpci_err("map error:\n"); - zpci_err_hex(&pa, sizeof(pa)); + zpci_err_dma(ret, pa); return DMA_ERROR_CODE; } @@ -306,14 +332,16 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, { struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); unsigned long iommu_page_index; - int npages; + int npages, ret; npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); dma_addr = dma_addr & PAGE_MASK; - if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, - ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID)) { + ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, + ZPCI_PTE_INVALID); + if (ret) { zpci_err("unmap error:\n"); - zpci_err_hex(&dma_addr, sizeof(dma_addr)); + zpci_err_dma(ret, dma_addr); + return; } atomic64_add(npages, &zdev->unmapped_pages); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9f39056..690b402 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -35,7 +35,7 @@ #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd -#define MSR_NHM_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO 0x000000ce #define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -44,7 +44,6 @@ #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) -#define MSR_PLATFORM_INFO 0x000000ce #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4ddd780..c2b7522 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -273,10 +273,9 @@ __setup("nosmap", setup_disable_smap); static __always_inline void setup_smap(struct cpuinfo_x86 *c) { - unsigned long eflags; + unsigned long eflags = native_save_fl(); /* This should have been cleared long ago */ - raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); if (cpu_has(c, X86_FEATURE_SMAP)) { diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index ef29b74..31c6a60 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -385,20 +385,19 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, */ void fpu__init_prepare_fx_sw_frame(void) { - int fsave_header_size = sizeof(struct fregs_state); int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; fx_sw_reserved.extended_size = size; fx_sw_reserved.xfeatures = xfeatures_mask; fx_sw_reserved.xstate_size = xstate_size; - if (config_enabled(CONFIG_IA32_EMULATION)) { + if (config_enabled(CONFIG_IA32_EMULATION) || + config_enabled(CONFIG_X86_32)) { + int fsave_header_size = sizeof(struct fregs_state); + fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; + fx_sw_reserved_ia32.extended_size = size + fsave_header_size; } } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 6454f27..70fc312 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -694,7 +694,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) if (!boot_cpu_has(X86_FEATURE_XSAVE)) return NULL; - xsave = ¤t->thread.fpu.state.xsave; /* * We should not ever be requesting features that we * have not enabled. Remember that pcntxt_mask is diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 94ea120..87e1762 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -278,6 +278,12 @@ trace: /* save_mcount_regs fills in first two parameters */ save_mcount_regs + /* + * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not + * set (see include/asm/ftrace.h and include/linux/ftrace.h). Only the + * ip and parent ip are used and the list function is called when + * function tracing is enabled. + */ call *ftrace_trace_function restore_mcount_regs diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b0ae85f..1202d5c 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -586,6 +586,29 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, } /* + * We only want to do a 4-byte get_user() on 32-bit. Otherwise, + * we might run off the end of the bounds table if we are on + * a 64-bit kernel and try to get 8 bytes. + */ +int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, + long __user *bd_entry_ptr) +{ + u32 bd_entry_32; + int ret; + + if (is_64bit_mm(mm)) + return get_user(*bd_entry_ret, bd_entry_ptr); + + /* + * Note that get_user() uses the type of the *pointer* to + * establish the size of the get, not the destination. + */ + ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr); + *bd_entry_ret = bd_entry_32; + return ret; +} + +/* * Get the base of bounds tables pointed by specific bounds * directory entry. */ @@ -605,7 +628,7 @@ static int get_bt_addr(struct mm_struct *mm, int need_write = 0; pagefault_disable(); - ret = get_user(bd_entry, bd_entry_ptr); + ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; @@ -700,11 +723,23 @@ static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, */ static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) { - unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits); - if (is_64bit_mm(mm)) - return virt_space / MPX_BD_NR_ENTRIES_64; - else - return virt_space / MPX_BD_NR_ENTRIES_32; + unsigned long long virt_space; + unsigned long long GB = (1ULL << 30); + + /* + * This covers 32-bit emulation as well as 32-bit kernels + * running on 64-bit harware. + */ + if (!is_64bit_mm(mm)) + return (4ULL * GB) / MPX_BD_NR_ENTRIES_32; + + /* + * 'x86_virt_bits' returns what the hardware is capable + * of, and returns the full >32-bit adddress space when + * running 32-bit kernels on 64-bit hardware. + */ + virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + return virt_space / MPX_BD_NR_ENTRIES_64; } /* diff --git a/block/blk.h b/block/blk.h index da722eb..c43926d 100644 --- a/block/blk.h +++ b/block/blk.h @@ -72,8 +72,6 @@ void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); bool __blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes, unsigned int bidi_bytes); -int blk_queue_enter(struct request_queue *q, gfp_t gfp); -void blk_queue_exit(struct request_queue *q); void blk_freeze_queue(struct request_queue *q); static inline void blk_queue_enter_live(struct request_queue *q) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 3c083d2..6730f96 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -304,7 +304,7 @@ EXPORT_SYMBOL_GPL(acpi_get_psd_map); static int register_pcc_channel(int pcc_subspace_idx) { - struct acpi_pcct_subspace *cppc_ss; + struct acpi_pcct_hw_reduced *cppc_ss; unsigned int len; if (pcc_subspace_idx >= 0) { diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index f61a7c8..b420fb4 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1103,7 +1103,7 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data) } err_exit: - if (result && q) + if (result) acpi_ec_delete_query(q); if (data) *data = value; diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index bf034f8..2fa8304 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -14,7 +14,6 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/interrupt.h> -#include <linux/dmi.h> #include "sbshc.h" #define PREFIX "ACPI: " @@ -30,6 +29,7 @@ struct acpi_smb_hc { u8 query_bit; smbus_alarm_callback callback; void *context; + bool done; }; static int acpi_smbus_hc_add(struct acpi_device *device); @@ -88,8 +88,6 @@ enum acpi_smb_offset { ACPI_SMB_ALARM_DATA = 0x26, /* 2 bytes alarm data */ }; -static bool macbook; - static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data) { return ec_read(hc->offset + address, data); @@ -100,27 +98,11 @@ static inline int smb_hc_write(struct acpi_smb_hc *hc, u8 address, u8 data) return ec_write(hc->offset + address, data); } -static inline int smb_check_done(struct acpi_smb_hc *hc) -{ - union acpi_smb_status status = {.raw = 0}; - smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw); - return status.fields.done && (status.fields.status == SMBUS_OK); -} - static int wait_transaction_complete(struct acpi_smb_hc *hc, int timeout) { - if (wait_event_timeout(hc->wait, smb_check_done(hc), - msecs_to_jiffies(timeout))) + if (wait_event_timeout(hc->wait, hc->done, msecs_to_jiffies(timeout))) return 0; - /* - * After the timeout happens, OS will try to check the status of SMbus. - * If the status is what OS expected, it will be regarded as the bogus - * timeout. - */ - if (smb_check_done(hc)) - return 0; - else - return -ETIME; + return -ETIME; } static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol, @@ -135,8 +117,7 @@ static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol, } mutex_lock(&hc->lock); - if (macbook) - udelay(5); + hc->done = false; if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp)) goto end; if (temp) { @@ -235,8 +216,10 @@ static int smbus_alarm(void *context) if (smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw)) return 0; /* Check if it is only a completion notify */ - if (status.fields.done) + if (status.fields.done && status.fields.status == SMBUS_OK) { + hc->done = true; wake_up(&hc->wait); + } if (!status.fields.alarm) return 0; mutex_lock(&hc->lock); @@ -262,29 +245,12 @@ extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data); -static int macbook_dmi_match(const struct dmi_system_id *d) -{ - pr_debug("Detected MacBook, enabling workaround\n"); - macbook = true; - return 0; -} - -static struct dmi_system_id acpi_smbus_dmi_table[] = { - { macbook_dmi_match, "Apple MacBook", { - DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), - DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") }, - }, - { }, -}; - static int acpi_smbus_hc_add(struct acpi_device *device) { int status; unsigned long long val; struct acpi_smb_hc *hc; - dmi_check_system(acpi_smbus_dmi_table); - if (!device) return -EINVAL; diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index eb6e674..0d77cd6 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -68,6 +68,9 @@ int dev_pm_set_wake_irq(struct device *dev, int irq) struct wake_irq *wirq; int err; + if (irq < 0) + return -EINVAL; + wirq = kzalloc(sizeof(*wirq), GFP_KERNEL); if (!wirq) return -ENOMEM; @@ -167,6 +170,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) struct wake_irq *wirq; int err; + if (irq < 0) + return -EINVAL; + wirq = kzalloc(sizeof(*wirq), GFP_KERNEL); if (!wirq) return -ENOMEM; diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 654f6f3..55fe902 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -412,18 +412,42 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info) return rv; } -static void start_check_enables(struct smi_info *smi_info) +static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) +{ + smi_info->last_timeout_jiffies = jiffies; + mod_timer(&smi_info->si_timer, new_val); + smi_info->timer_running = true; +} + +/* + * Start a new message and (re)start the timer and thread. + */ +static void start_new_msg(struct smi_info *smi_info, unsigned char *msg, + unsigned int size) +{ + smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES); + + if (smi_info->thread) + wake_up_process(smi_info->thread); + + smi_info->handlers->start_transaction(smi_info->si_sm, msg, size); +} + +static void start_check_enables(struct smi_info *smi_info, bool start_timer) { unsigned char msg[2]; msg[0] = (IPMI_NETFN_APP_REQUEST << 2); msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD; - smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2); + if (start_timer) + start_new_msg(smi_info, msg, 2); + else + smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2); smi_info->si_state = SI_CHECKING_ENABLES; } -static void start_clear_flags(struct smi_info *smi_info) +static void start_clear_flags(struct smi_info *smi_info, bool start_timer) { unsigned char msg[3]; @@ -432,7 +456,10 @@ static void start_clear_flags(struct smi_info *smi_info) msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD; msg[2] = WDT_PRE_TIMEOUT_INT; - smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3); + if (start_timer) + start_new_msg(smi_info, msg, 3); + else + smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3); smi_info->si_state = SI_CLEARING_FLAGS; } @@ -442,10 +469,8 @@ static void start_getting_msg_queue(struct smi_info *smi_info) smi_info->curr_msg->data[1] = IPMI_GET_MSG_CMD; smi_info->curr_msg->data_size = 2; - smi_info->handlers->start_transaction( - smi_info->si_sm, - smi_info->curr_msg->data, - smi_info->curr_msg->data_size); + start_new_msg(smi_info, smi_info->curr_msg->data, + smi_info->curr_msg->data_size); smi_info->si_state = SI_GETTING_MESSAGES; } @@ -455,20 +480,11 @@ static void start_getting_events(struct smi_info *smi_info) smi_info->curr_msg->data[1] = IPMI_READ_EVENT_MSG_BUFFER_CMD; smi_info->curr_msg->data_size = 2; - smi_info->handlers->start_transaction( - smi_info->si_sm, - smi_info->curr_msg->data, - smi_info->curr_msg->data_size); + start_new_msg(smi_info, smi_info->curr_msg->data, + smi_info->curr_msg->data_size); smi_info->si_state = SI_GETTING_EVENTS; } -static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) -{ - smi_info->last_timeout_jiffies = jiffies; - mod_timer(&smi_info->si_timer, new_val); - smi_info->timer_running = true; -} - /* * When we have a situtaion where we run out of memory and cannot * allocate messages, we just leave them in the BMC and run the system @@ -478,11 +494,11 @@ static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val) * Note that we cannot just use disable_irq(), since the interrupt may * be shared. */ -static inline bool disable_si_irq(struct smi_info *smi_info) +static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer) { if ((smi_info->irq) && (!smi_info->interrupt_disabled)) { smi_info->interrupt_disabled = true; - start_check_enables(smi_info); + start_check_enables(smi_info, start_timer); return true; } return false; @@ -492,7 +508,7 @@ static inline bool enable_si_irq(struct smi_info *smi_info) { if ((smi_info->irq) && (smi_info->interrupt_disabled)) { smi_info->interrupt_disabled = false; - start_check_enables(smi_info); + start_check_enables(smi_info, true); return true; } return false; @@ -510,7 +526,7 @@ static struct ipmi_smi_msg *alloc_msg_handle_irq(struct smi_info *smi_info) msg = ipmi_alloc_smi_msg(); if (!msg) { - if (!disable_si_irq(smi_info)) + if (!disable_si_irq(smi_info, true)) smi_info->si_state = SI_NORMAL; } else if (enable_si_irq(smi_info)) { ipmi_free_smi_msg(msg); @@ -526,7 +542,7 @@ static void handle_flags(struct smi_info *smi_info) /* Watchdog pre-timeout */ smi_inc_stat(smi_info, watchdog_pretimeouts); - start_clear_flags(smi_info); + start_clear_flags(smi_info, true); smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT; if (smi_info->intf) ipmi_smi_watchdog_pretimeout(smi_info->intf); @@ -879,8 +895,7 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info, msg[0] = (IPMI_NETFN_APP_REQUEST << 2); msg[1] = IPMI_GET_MSG_FLAGS_CMD; - smi_info->handlers->start_transaction( - smi_info->si_sm, msg, 2); + start_new_msg(smi_info, msg, 2); smi_info->si_state = SI_GETTING_FLAGS; goto restart; } @@ -910,7 +925,7 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info, * disable and messages disabled. */ if (smi_info->supports_event_msg_buff || smi_info->irq) { - start_check_enables(smi_info); + start_check_enables(smi_info, true); } else { smi_info->curr_msg = alloc_msg_handle_irq(smi_info); if (!smi_info->curr_msg) @@ -920,6 +935,13 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info, } goto restart; } + + if (si_sm_result == SI_SM_IDLE && smi_info->timer_running) { + /* Ok it if fails, the timer will just go off. */ + if (del_timer(&smi_info->si_timer)) + smi_info->timer_running = false; + } + out: return si_sm_result; } @@ -2560,6 +2582,7 @@ static const struct of_device_id of_ipmi_match[] = { .data = (void *)(unsigned long) SI_BT }, {}, }; +MODULE_DEVICE_TABLE(of, of_ipmi_match); static int of_ipmi_probe(struct platform_device *dev) { @@ -2646,7 +2669,6 @@ static int of_ipmi_probe(struct platform_device *dev) } return 0; } -MODULE_DEVICE_TABLE(of, of_ipmi_match); #else #define of_ipmi_match NULL static int of_ipmi_probe(struct platform_device *dev) @@ -3613,7 +3635,7 @@ static int try_smi_init(struct smi_info *new_smi) * Start clearing the flags before we enable interrupts or the * timer to avoid racing with the timer. */ - start_clear_flags(new_smi); + start_clear_flags(new_smi, false); /* * IRQ is defined to be set when non-zero. req_events will @@ -3908,7 +3930,7 @@ static void cleanup_one_si(struct smi_info *to_clean) poll(to_clean); schedule_timeout_uninterruptible(1); } - disable_si_irq(to_clean); + disable_si_irq(to_clean, false); while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 0ac3bd1..096f0cef 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -153,6 +153,9 @@ static int timeout = 10; /* The pre-timeout is disabled by default. */ static int pretimeout; +/* Default timeout to set on panic */ +static int panic_wdt_timeout = 255; + /* Default action is to reset the board on a timeout. */ static unsigned char action_val = WDOG_TIMEOUT_RESET; @@ -293,6 +296,9 @@ MODULE_PARM_DESC(timeout, "Timeout value in seconds."); module_param(pretimeout, timeout, 0644); MODULE_PARM_DESC(pretimeout, "Pretimeout value in seconds."); +module_param(panic_wdt_timeout, timeout, 0644); +MODULE_PARM_DESC(timeout, "Timeout value on kernel panic in seconds."); + module_param_cb(action, ¶m_ops_str, action_op, 0644); MODULE_PARM_DESC(action, "Timeout action. One of: " "reset, none, power_cycle, power_off."); @@ -1189,7 +1195,7 @@ static int wdog_panic_handler(struct notifier_block *this, /* Make sure we do this only once. */ panic_event_handled = 1; - timeout = 255; + timeout = panic_wdt_timeout; pretimeout = 0; panic_halt_ipmi_set_timeout(); } diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 71cfdf7..2eb5f0e 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -1,4 +1,5 @@ menu "Clock Source drivers" + depends on !ARCH_USES_GETTIMEOFFSET config CLKSRC_OF bool diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c index 10202f1..517e1c7 100644 --- a/drivers/clocksource/fsl_ftm_timer.c +++ b/drivers/clocksource/fsl_ftm_timer.c @@ -203,7 +203,7 @@ static int __init ftm_clockevent_init(unsigned long freq, int irq) int err; ftm_writel(0x00, priv->clkevt_base + FTM_CNTIN); - ftm_writel(~0UL, priv->clkevt_base + FTM_MOD); + ftm_writel(~0u, priv->clkevt_base + FTM_MOD); ftm_reset_counter(priv->clkevt_base); @@ -230,7 +230,7 @@ static int __init ftm_clocksource_init(unsigned long freq) int err; ftm_writel(0x00, priv->clksrc_base + FTM_CNTIN); - ftm_writel(~0UL, priv->clksrc_base + FTM_MOD); + ftm_writel(~0u, priv->clksrc_base + FTM_MOD); ftm_reset_counter(priv->clksrc_base); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 1582c1c..8014c23 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -84,6 +84,7 @@ config ARM_KIRKWOOD_CPUFREQ config ARM_MT8173_CPUFREQ bool "Mediatek MT8173 CPUFreq support" depends on ARCH_MEDIATEK && REGULATOR + depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST) depends on !CPU_THERMAL || THERMAL=y select PM_OPP help diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index adbd1de..c59bdcb 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -5,7 +5,6 @@ config X86_INTEL_PSTATE bool "Intel P state control" depends on X86 - select ACPI_PROCESSOR if ACPI help This driver provides a P state for Intel core processors. The driver implements an internal governor and will become diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 2e31d09..001a532 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -34,14 +34,10 @@ #include <asm/cpu_device_id.h> #include <asm/cpufeature.h> -#if IS_ENABLED(CONFIG_ACPI) -#include <acpi/processor.h> -#endif - -#define BYT_RATIOS 0x66a -#define BYT_VIDS 0x66b -#define BYT_TURBO_RATIOS 0x66c -#define BYT_TURBO_VIDS 0x66d +#define ATOM_RATIOS 0x66a +#define ATOM_VIDS 0x66b +#define ATOM_TURBO_RATIOS 0x66c +#define ATOM_TURBO_VIDS 0x66d #define FRAC_BITS 8 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) @@ -117,9 +113,6 @@ struct cpudata { u64 prev_mperf; u64 prev_tsc; struct sample sample; -#if IS_ENABLED(CONFIG_ACPI) - struct acpi_processor_performance acpi_perf_data; -#endif }; static struct cpudata **all_cpu_data; @@ -150,7 +143,6 @@ struct cpu_defaults { static struct pstate_adjust_policy pid_params; static struct pstate_funcs pstate_funcs; static int hwp_active; -static int no_acpi_perf; struct perf_limits { int no_turbo; @@ -163,8 +155,6 @@ struct perf_limits { int max_sysfs_pct; int min_policy_pct; int min_sysfs_pct; - int max_perf_ctl; - int min_perf_ctl; }; static struct perf_limits performance_limits = { @@ -191,8 +181,6 @@ static struct perf_limits powersave_limits = { .max_sysfs_pct = 100, .min_policy_pct = 0, .min_sysfs_pct = 0, - .max_perf_ctl = 0, - .min_perf_ctl = 0, }; #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE @@ -201,153 +189,6 @@ static struct perf_limits *limits = &performance_limits; static struct perf_limits *limits = &powersave_limits; #endif -#if IS_ENABLED(CONFIG_ACPI) -/* - * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and - * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and - * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state - * ratio, out of it only high 8 bits are used. For example 0x1700 is setting - * target ratio 0x17. The _PSS control value stores in a format which can be - * directly written to PERF_CTL MSR. But in intel_pstate driver this shift - * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()). - * This function converts the _PSS control value to intel pstate driver format - * for comparison and assignment. - */ -static int convert_to_native_pstate_format(struct cpudata *cpu, int index) -{ - return cpu->acpi_perf_data.states[index].control >> 8; -} - -static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy) -{ - struct cpudata *cpu; - int ret; - bool turbo_absent = false; - int max_pstate_index; - int min_pss_ctl, max_pss_ctl, turbo_pss_ctl; - int i; - - cpu = all_cpu_data[policy->cpu]; - - pr_debug("intel_pstate: default limits 0x%x 0x%x 0x%x\n", - cpu->pstate.min_pstate, cpu->pstate.max_pstate, - cpu->pstate.turbo_pstate); - - if (!cpu->acpi_perf_data.shared_cpu_map && - zalloc_cpumask_var_node(&cpu->acpi_perf_data.shared_cpu_map, - GFP_KERNEL, cpu_to_node(policy->cpu))) { - return -ENOMEM; - } - - ret = acpi_processor_register_performance(&cpu->acpi_perf_data, - policy->cpu); - if (ret) - return ret; - - /* - * Check if the control value in _PSS is for PERF_CTL MSR, which should - * guarantee that the states returned by it map to the states in our - * list directly. - */ - if (cpu->acpi_perf_data.control_register.space_id != - ACPI_ADR_SPACE_FIXED_HARDWARE) - return -EIO; - - pr_debug("intel_pstate: CPU%u - ACPI _PSS perf data\n", policy->cpu); - for (i = 0; i < cpu->acpi_perf_data.state_count; i++) - pr_debug(" %cP%d: %u MHz, %u mW, 0x%x\n", - (i == cpu->acpi_perf_data.state ? '*' : ' '), i, - (u32) cpu->acpi_perf_data.states[i].core_frequency, - (u32) cpu->acpi_perf_data.states[i].power, - (u32) cpu->acpi_perf_data.states[i].control); - - /* - * If there is only one entry _PSS, simply ignore _PSS and continue as - * usual without taking _PSS into account - */ - if (cpu->acpi_perf_data.state_count < 2) - return 0; - - turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0); - min_pss_ctl = convert_to_native_pstate_format(cpu, - cpu->acpi_perf_data.state_count - 1); - /* Check if there is a turbo freq in _PSS */ - if (turbo_pss_ctl <= cpu->pstate.max_pstate && - turbo_pss_ctl > cpu->pstate.min_pstate) { - pr_debug("intel_pstate: no turbo range exists in _PSS\n"); - limits->no_turbo = limits->turbo_disabled = 1; - cpu->pstate.turbo_pstate = cpu->pstate.max_pstate; - turbo_absent = true; - } - - /* Check if the max non turbo p state < Intel P state max */ - max_pstate_index = turbo_absent ? 0 : 1; - max_pss_ctl = convert_to_native_pstate_format(cpu, max_pstate_index); - if (max_pss_ctl < cpu->pstate.max_pstate && - max_pss_ctl > cpu->pstate.min_pstate) - cpu->pstate.max_pstate = max_pss_ctl; - - /* check If min perf > Intel P State min */ - if (min_pss_ctl > cpu->pstate.min_pstate && - min_pss_ctl < cpu->pstate.max_pstate) { - cpu->pstate.min_pstate = min_pss_ctl; - policy->cpuinfo.min_freq = min_pss_ctl * cpu->pstate.scaling; - } - - if (turbo_absent) - policy->cpuinfo.max_freq = cpu->pstate.max_pstate * - cpu->pstate.scaling; - else { - policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * - cpu->pstate.scaling; - /* - * The _PSS table doesn't contain whole turbo frequency range. - * This just contains +1 MHZ above the max non turbo frequency, - * with control value corresponding to max turbo ratio. But - * when cpufreq set policy is called, it will call with this - * max frequency, which will cause a reduced performance as - * this driver uses real max turbo frequency as the max - * frequeny. So correct this frequency in _PSS table to - * correct max turbo frequency based on the turbo ratio. - * Also need to convert to MHz as _PSS freq is in MHz. - */ - cpu->acpi_perf_data.states[0].core_frequency = - turbo_pss_ctl * 100; - } - - pr_debug("intel_pstate: Updated limits using _PSS 0x%x 0x%x 0x%x\n", - cpu->pstate.min_pstate, cpu->pstate.max_pstate, - cpu->pstate.turbo_pstate); - pr_debug("intel_pstate: policy max_freq=%d Khz min_freq = %d KHz\n", - policy->cpuinfo.max_freq, policy->cpuinfo.min_freq); - - return 0; -} - -static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) -{ - struct cpudata *cpu; - - if (!no_acpi_perf) - return 0; - - cpu = all_cpu_data[policy->cpu]; - acpi_processor_unregister_performance(policy->cpu); - return 0; -} - -#else -static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy) -{ - return 0; -} - -static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) -{ - return 0; -} -#endif - static inline void pid_reset(struct _pid *pid, int setpoint, int busy, int deadband, int integral) { pid->setpoint = setpoint; @@ -687,31 +528,31 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); } -static int byt_get_min_pstate(void) +static int atom_get_min_pstate(void) { u64 value; - rdmsrl(BYT_RATIOS, value); + rdmsrl(ATOM_RATIOS, value); return (value >> 8) & 0x7F; } -static int byt_get_max_pstate(void) +static int atom_get_max_pstate(void) { u64 value; - rdmsrl(BYT_RATIOS, value); + rdmsrl(ATOM_RATIOS, value); return (value >> 16) & 0x7F; } -static int byt_get_turbo_pstate(void) +static int atom_get_turbo_pstate(void) { u64 value; - rdmsrl(BYT_TURBO_RATIOS, value); + rdmsrl(ATOM_TURBO_RATIOS, value); return value & 0x7F; } -static void byt_set_pstate(struct cpudata *cpudata, int pstate) +static void atom_set_pstate(struct cpudata *cpudata, int pstate) { u64 val; int32_t vid_fp; @@ -736,27 +577,42 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate) wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val); } -#define BYT_BCLK_FREQS 5 -static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800}; - -static int byt_get_scaling(void) +static int silvermont_get_scaling(void) { u64 value; int i; + /* Defined in Table 35-6 from SDM (Sept 2015) */ + static int silvermont_freq_table[] = { + 83300, 100000, 133300, 116700, 80000}; rdmsrl(MSR_FSB_FREQ, value); - i = value & 0x3; + i = value & 0x7; + WARN_ON(i > 4); - BUG_ON(i > BYT_BCLK_FREQS); + return silvermont_freq_table[i]; +} - return byt_freq_table[i] * 100; +static int airmont_get_scaling(void) +{ + u64 value; + int i; + /* Defined in Table 35-10 from SDM (Sept 2015) */ + static int airmont_freq_table[] = { + 83300, 100000, 133300, 116700, 80000, + 93300, 90000, 88900, 87500}; + + rdmsrl(MSR_FSB_FREQ, value); + i = value & 0xF; + WARN_ON(i > 8); + + return airmont_freq_table[i]; } -static void byt_get_vid(struct cpudata *cpudata) +static void atom_get_vid(struct cpudata *cpudata) { u64 value; - rdmsrl(BYT_VIDS, value); + rdmsrl(ATOM_VIDS, value); cpudata->vid.min = int_tofp((value >> 8) & 0x7f); cpudata->vid.max = int_tofp((value >> 16) & 0x7f); cpudata->vid.ratio = div_fp( @@ -764,7 +620,7 @@ static void byt_get_vid(struct cpudata *cpudata) int_tofp(cpudata->pstate.max_pstate - cpudata->pstate.min_pstate)); - rdmsrl(BYT_TURBO_VIDS, value); + rdmsrl(ATOM_TURBO_VIDS, value); cpudata->vid.turbo = value & 0x7f; } @@ -885,7 +741,7 @@ static struct cpu_defaults core_params = { }, }; -static struct cpu_defaults byt_params = { +static struct cpu_defaults silvermont_params = { .pid_policy = { .sample_rate_ms = 10, .deadband = 0, @@ -895,13 +751,33 @@ static struct cpu_defaults byt_params = { .i_gain_pct = 4, }, .funcs = { - .get_max = byt_get_max_pstate, - .get_max_physical = byt_get_max_pstate, - .get_min = byt_get_min_pstate, - .get_turbo = byt_get_turbo_pstate, - .set = byt_set_pstate, - .get_scaling = byt_get_scaling, - .get_vid = byt_get_vid, + .get_max = atom_get_max_pstate, + .get_max_physical = atom_get_max_pstate, + .get_min = atom_get_min_pstate, + .get_turbo = atom_get_turbo_pstate, + .set = atom_set_pstate, + .get_scaling = silvermont_get_scaling, + .get_vid = atom_get_vid, + }, +}; + +static struct cpu_defaults airmont_params = { + .pid_policy = { + .sample_rate_ms = 10, + .deadband = 0, + .setpoint = 60, + .p_gain_pct = 14, + .d_gain_pct = 0, + .i_gain_pct = 4, + }, + .funcs = { + .get_max = atom_get_max_pstate, + .get_max_physical = atom_get_max_pstate, + .get_min = atom_get_min_pstate, + .get_turbo = atom_get_turbo_pstate, + .set = atom_set_pstate, + .get_scaling = airmont_get_scaling, + .get_vid = atom_get_vid, }, }; @@ -938,23 +814,12 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) * policy, or by cpu specific default values determined through * experimentation. */ - if (limits->max_perf_ctl && limits->max_sysfs_pct >= - limits->max_policy_pct) { - *max = limits->max_perf_ctl; - } else { - max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), - limits->max_perf)); - *max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate, - cpu->pstate.turbo_pstate); - } + max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf)); + *max = clamp_t(int, max_perf_adj, + cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); - if (limits->min_perf_ctl) { - *min = limits->min_perf_ctl; - } else { - min_perf = fp_toint(mul_fp(int_tofp(max_perf), - limits->min_perf)); - *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf); - } + min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf)); + *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf); } static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force) @@ -1153,7 +1018,7 @@ static void intel_pstate_timer_func(unsigned long __data) static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x2a, core_params), ICPU(0x2d, core_params), - ICPU(0x37, byt_params), + ICPU(0x37, silvermont_params), ICPU(0x3a, core_params), ICPU(0x3c, core_params), ICPU(0x3d, core_params), @@ -1162,7 +1027,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { ICPU(0x45, core_params), ICPU(0x46, core_params), ICPU(0x47, core_params), - ICPU(0x4c, byt_params), + ICPU(0x4c, airmont_params), ICPU(0x4e, core_params), ICPU(0x4f, core_params), ICPU(0x5e, core_params), @@ -1229,12 +1094,6 @@ static unsigned int intel_pstate_get(unsigned int cpu_num) static int intel_pstate_set_policy(struct cpufreq_policy *policy) { -#if IS_ENABLED(CONFIG_ACPI) - struct cpudata *cpu; - int i; -#endif - pr_debug("intel_pstate: %s max %u policy->max %u\n", __func__, - policy->cpuinfo.max_freq, policy->max); if (!policy->cpuinfo.max_freq) return -ENODEV; @@ -1270,23 +1129,6 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits->max_perf = div_fp(int_tofp(limits->max_perf_pct), int_tofp(100)); -#if IS_ENABLED(CONFIG_ACPI) - cpu = all_cpu_data[policy->cpu]; - for (i = 0; i < cpu->acpi_perf_data.state_count; i++) { - int control; - - control = convert_to_native_pstate_format(cpu, i); - if (control * cpu->pstate.scaling == policy->max) - limits->max_perf_ctl = control; - if (control * cpu->pstate.scaling == policy->min) - limits->min_perf_ctl = control; - } - - pr_debug("intel_pstate: max %u policy_max %u perf_ctl [0x%x-0x%x]\n", - policy->cpuinfo.max_freq, policy->max, limits->min_perf_ctl, - limits->max_perf_ctl); -#endif - if (hwp_active) intel_pstate_hwp_set(); @@ -1341,30 +1183,18 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; - if (!no_acpi_perf) - intel_pstate_init_perf_limits(policy); - /* - * If there is no acpi perf data or error, we ignore and use Intel P - * state calculated limits, So this is not fatal error. - */ policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); return 0; } -static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) -{ - return intel_pstate_exit_perf_limits(policy); -} - static struct cpufreq_driver intel_pstate_driver = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_pstate_verify_policy, .setpolicy = intel_pstate_set_policy, .get = intel_pstate_get, .init = intel_pstate_cpu_init, - .exit = intel_pstate_cpu_exit, .stop_cpu = intel_pstate_stop_cpu, .name = "intel_pstate", }; @@ -1406,6 +1236,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs) } #if IS_ENABLED(CONFIG_ACPI) +#include <acpi/processor.h> static bool intel_pstate_no_acpi_pss(void) { @@ -1601,9 +1432,6 @@ static int __init intel_pstate_setup(char *str) force_load = 1; if (!strcmp(str, "hwp_only")) hwp_only = 1; - if (!strcmp(str, "no_acpi")) - no_acpi_perf = 1; - return 0; } early_param("intel_pstate", intel_pstate_setup); diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index 03856ad..473d36d 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -198,7 +198,7 @@ static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev, goto out_err; } - params_head = section_head->params; + params_head = section.params; while (params_head) { if (copy_from_user(&key_val, (void __user *)params_head, diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 4e55239..53d22eb 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -729,8 +729,8 @@ atc_prep_dma_interleaved(struct dma_chan *chan, return NULL; dev_info(chan2dev(chan), - "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n", - __func__, xt->src_start, xt->dst_start, xt->numf, + "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n", + __func__, &xt->src_start, &xt->dst_start, xt->numf, xt->frame_size, flags); /* @@ -824,8 +824,8 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, u32 ctrla; u32 ctrlb; - dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d0x%x s0x%x l0x%zx f0x%lx\n", - dest, src, len, flags); + dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d%pad s%pad l0x%zx f0x%lx\n", + &dest, &src, len, flags); if (unlikely(!len)) { dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n"); @@ -938,8 +938,8 @@ atc_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value, void __iomem *vaddr; dma_addr_t paddr; - dev_vdbg(chan2dev(chan), "%s: d0x%x v0x%x l0x%zx f0x%lx\n", __func__, - dest, value, len, flags); + dev_vdbg(chan2dev(chan), "%s: d%pad v0x%x l0x%zx f0x%lx\n", __func__, + &dest, value, len, flags); if (unlikely(!len)) { dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__); @@ -1022,8 +1022,8 @@ atc_prep_dma_memset_sg(struct dma_chan *chan, dma_addr_t dest = sg_dma_address(sg); size_t len = sg_dma_len(sg); - dev_vdbg(chan2dev(chan), "%s: d0x%08x, l0x%zx\n", - __func__, dest, len); + dev_vdbg(chan2dev(chan), "%s: d%pad, l0x%zx\n", + __func__, &dest, len); if (!is_dma_fill_aligned(chan->device, dest, 0, len)) { dev_err(chan2dev(chan), "%s: buffer is not aligned\n", @@ -1439,9 +1439,9 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, unsigned int periods = buf_len / period_len; unsigned int i; - dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@0x%08x - %d (%d/%d)\n", + dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@%pad - %d (%d/%d)\n", direction == DMA_MEM_TO_DEV ? "TO DEVICE" : "FROM DEVICE", - buf_addr, + &buf_addr, periods, buf_len, period_len); if (unlikely(!atslave || !buf_len || !period_len)) { diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h index d1cfc8c..7f58f06 100644 --- a/drivers/dma/at_hdmac_regs.h +++ b/drivers/dma/at_hdmac_regs.h @@ -385,9 +385,9 @@ static void vdbg_dump_regs(struct at_dma_chan *atchan) {} static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli) { dev_crit(chan2dev(&atchan->chan_common), - " desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n", - lli->saddr, lli->daddr, - lli->ctrla, lli->ctrlb, lli->dscr); + " desc: s%pad d%pad ctrl0x%x:0x%x l0x%pad\n", + &lli->saddr, &lli->daddr, + lli->ctrla, lli->ctrlb, &lli->dscr); } diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index b5e132d..7f039de 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -920,8 +920,8 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan, desc->lld.mbr_cfg = chan_cc; dev_dbg(chan2dev(chan), - "%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n", - __func__, desc->lld.mbr_sa, desc->lld.mbr_da, + "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n", + __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc, desc->lld.mbr_cfg); /* Chain lld. */ @@ -953,8 +953,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, if ((xt->numf > 1) && (xt->frame_size > 1)) return NULL; - dev_dbg(chan2dev(chan), "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n", - __func__, xt->src_start, xt->dst_start, xt->numf, + dev_dbg(chan2dev(chan), "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n", + __func__, &xt->src_start, &xt->dst_start, xt->numf, xt->frame_size, flags); src_addr = xt->src_start; @@ -1179,8 +1179,8 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan, desc->lld.mbr_cfg = chan_cc; dev_dbg(chan2dev(chan), - "%s: lld: mbr_da=0x%08x, mbr_ds=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n", - __func__, desc->lld.mbr_da, desc->lld.mbr_ds, desc->lld.mbr_ubc, + "%s: lld: mbr_da=%pad, mbr_ds=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n", + __func__, &desc->lld.mbr_da, &desc->lld.mbr_ds, desc->lld.mbr_ubc, desc->lld.mbr_cfg); return desc; @@ -1193,8 +1193,8 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value, struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan); struct at_xdmac_desc *desc; - dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n", - __func__, dest, len, value, flags); + dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n", + __func__, &dest, len, value, flags); if (unlikely(!len)) return NULL; @@ -1229,8 +1229,8 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl, /* Prepare descriptors. */ for_each_sg(sgl, sg, sg_len, i) { - dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n", - __func__, sg_dma_address(sg), sg_dma_len(sg), + dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n", + __func__, &sg_dma_address(sg), sg_dma_len(sg), value, flags); desc = at_xdmac_memset_create_desc(chan, atchan, sg_dma_address(sg), diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 6b03e4e..0675e26 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -107,7 +107,7 @@ /* CCCFG register */ #define GET_NUM_DMACH(x) (x & 0x7) /* bits 0-2 */ -#define GET_NUM_QDMACH(x) (x & 0x70 >> 4) /* bits 4-6 */ +#define GET_NUM_QDMACH(x) ((x & 0x70) >> 4) /* bits 4-6 */ #define GET_NUM_PAENTRY(x) ((x & 0x7000) >> 12) /* bits 12-14 */ #define GET_NUM_EVQUE(x) ((x & 0x70000) >> 16) /* bits 16-18 */ #define GET_NUM_REGN(x) ((x & 0x300000) >> 20) /* bits 20-21 */ @@ -1565,7 +1565,7 @@ static void edma_tc_set_pm_state(struct edma_tc *tc, bool enable) struct platform_device *tc_pdev; int ret; - if (!tc) + if (!IS_ENABLED(CONFIG_OF) || !tc) return; tc_pdev = of_find_device_by_node(tc->node); diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 7058d58..0f6fd42 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1462,7 +1462,7 @@ err_firmware: #define EVENT_REMAP_CELLS 3 -static int __init sdma_event_remap(struct sdma_engine *sdma) +static int sdma_event_remap(struct sdma_engine *sdma) { struct device_node *np = sdma->dev->of_node; struct device_node *gpr_np = of_parse_phandle(np, "gpr", 0); diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c index ebd8a5f..f1bcc2a 100644 --- a/drivers/dma/sh/usb-dmac.c +++ b/drivers/dma/sh/usb-dmac.c @@ -679,8 +679,11 @@ static int usb_dmac_runtime_suspend(struct device *dev) struct usb_dmac *dmac = dev_get_drvdata(dev); int i; - for (i = 0; i < dmac->n_channels; ++i) + for (i = 0; i < dmac->n_channels; ++i) { + if (!dmac->channels[i].iomem) + break; usb_dmac_chan_halt(&dmac->channels[i]); + } return 0; } @@ -799,11 +802,10 @@ static int usb_dmac_probe(struct platform_device *pdev) ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); - return ret; + goto error_pm; } ret = usb_dmac_init(dmac); - pm_runtime_put(&pdev->dev); if (ret) { dev_err(&pdev->dev, "failed to reset device\n"); @@ -851,10 +853,13 @@ static int usb_dmac_probe(struct platform_device *pdev) if (ret < 0) goto error; + pm_runtime_put(&pdev->dev); return 0; error: of_dma_controller_free(pdev->dev.of_node); + pm_runtime_put(&pdev->dev); +error_pm: pm_runtime_disable(&pdev->dev); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 615ce6d..306f757 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -389,7 +389,6 @@ struct amdgpu_clock { * Fences. */ struct amdgpu_fence_driver { - struct amdgpu_ring *ring; uint64_t gpu_addr; volatile uint32_t *cpu_addr; /* sync_seq is protected by ring emission lock */ @@ -398,7 +397,7 @@ struct amdgpu_fence_driver { bool initialized; struct amdgpu_irq_src *irq_src; unsigned irq_type; - struct delayed_work lockup_work; + struct timer_list fallback_timer; wait_queue_head_t fence_queue; }; @@ -917,8 +916,8 @@ struct amdgpu_ring { #define AMDGPU_VM_FAULT_STOP_ALWAYS 2 struct amdgpu_vm_pt { - struct amdgpu_bo *bo; - uint64_t addr; + struct amdgpu_bo *bo; + uint64_t addr; }; struct amdgpu_vm_id { @@ -926,8 +925,6 @@ struct amdgpu_vm_id { uint64_t pd_gpu_addr; /* last flushed PD/PT update */ struct fence *flushed_updates; - /* last use of vmid */ - struct fence *last_id_use; }; struct amdgpu_vm { @@ -957,24 +954,70 @@ struct amdgpu_vm { /* for id and flush management per ring */ struct amdgpu_vm_id ids[AMDGPU_MAX_RINGS]; + /* for interval tree */ + spinlock_t it_lock; }; struct amdgpu_vm_manager { - struct fence *active[AMDGPU_NUM_VM]; - uint32_t max_pfn; + struct { + struct fence *active; + atomic_long_t owner; + } ids[AMDGPU_NUM_VM]; + + uint32_t max_pfn; /* number of VMIDs */ - unsigned nvm; + unsigned nvm; /* vram base address for page table entry */ - u64 vram_base_offset; + u64 vram_base_offset; /* is vm enabled? */ - bool enabled; - /* for hw to save the PD addr on suspend/resume */ - uint32_t saved_table_addr[AMDGPU_NUM_VM]; + bool enabled; /* vm pte handling */ const struct amdgpu_vm_pte_funcs *vm_pte_funcs; struct amdgpu_ring *vm_pte_funcs_ring; }; +void amdgpu_vm_manager_fini(struct amdgpu_device *adev); +int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm); +void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); +struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct list_head *head); +int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, + struct amdgpu_sync *sync); +void amdgpu_vm_flush(struct amdgpu_ring *ring, + struct amdgpu_vm *vm, + struct fence *updates); +void amdgpu_vm_fence(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct fence *fence); +uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr); +int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, + struct amdgpu_vm *vm); +int amdgpu_vm_clear_freed(struct amdgpu_device *adev, + struct amdgpu_vm *vm); +int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct amdgpu_sync *sync); +int amdgpu_vm_bo_update(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + struct ttm_mem_reg *mem); +void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, + struct amdgpu_bo *bo); +struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm, + struct amdgpu_bo *bo); +struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, + struct amdgpu_vm *vm, + struct amdgpu_bo *bo); +int amdgpu_vm_bo_map(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr, uint64_t offset, + uint64_t size, uint32_t flags); +int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va, + uint64_t addr); +void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, + struct amdgpu_bo_va *bo_va); +int amdgpu_vm_free_job(struct amdgpu_job *job); + /* * context related structures */ @@ -1211,6 +1254,7 @@ struct amdgpu_cs_parser { /* relocations */ struct amdgpu_bo_list_entry *vm_bos; struct list_head validated; + struct fence *fence; struct amdgpu_ib *ibs; uint32_t num_ibs; @@ -1226,7 +1270,7 @@ struct amdgpu_job { struct amdgpu_device *adev; struct amdgpu_ib *ibs; uint32_t num_ibs; - struct mutex job_lock; + void *owner; struct amdgpu_user_fence uf; int (*free_job)(struct amdgpu_job *job); }; @@ -2257,11 +2301,6 @@ void amdgpu_pci_config_reset(struct amdgpu_device *adev); bool amdgpu_card_posted(struct amdgpu_device *adev); void amdgpu_update_display_priority(struct amdgpu_device *adev); bool amdgpu_boot_test_post_card(struct amdgpu_device *adev); -struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev, - struct drm_file *filp, - struct amdgpu_ctx *ctx, - struct amdgpu_ib *ibs, - uint32_t num_ibs); int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data); int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, @@ -2319,49 +2358,6 @@ long amdgpu_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); /* - * vm - */ -int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm); -void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); -struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev, - struct amdgpu_vm *vm, - struct list_head *head); -int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, - struct amdgpu_sync *sync); -void amdgpu_vm_flush(struct amdgpu_ring *ring, - struct amdgpu_vm *vm, - struct fence *updates); -void amdgpu_vm_fence(struct amdgpu_device *adev, - struct amdgpu_vm *vm, - struct amdgpu_fence *fence); -uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr); -int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, - struct amdgpu_vm *vm); -int amdgpu_vm_clear_freed(struct amdgpu_device *adev, - struct amdgpu_vm *vm); -int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, - struct amdgpu_vm *vm, struct amdgpu_sync *sync); -int amdgpu_vm_bo_update(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va, - struct ttm_mem_reg *mem); -void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, - struct amdgpu_bo *bo); -struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm, - struct amdgpu_bo *bo); -struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, - struct amdgpu_vm *vm, - struct amdgpu_bo *bo); -int amdgpu_vm_bo_map(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va, - uint64_t addr, uint64_t offset, - uint64_t size, uint32_t flags); -int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va, - uint64_t addr); -void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, - struct amdgpu_bo_va *bo_va); -int amdgpu_vm_free_job(struct amdgpu_job *job); -/* * functions used by amdgpu_encoder.c */ struct amdgpu_afmt_acr { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index dfc4d02..3afcf02 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -127,30 +127,6 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, return 0; } -struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev, - struct drm_file *filp, - struct amdgpu_ctx *ctx, - struct amdgpu_ib *ibs, - uint32_t num_ibs) -{ - struct amdgpu_cs_parser *parser; - int i; - - parser = kzalloc(sizeof(struct amdgpu_cs_parser), GFP_KERNEL); - if (!parser) - return NULL; - - parser->adev = adev; - parser->filp = filp; - parser->ctx = ctx; - parser->ibs = ibs; - parser->num_ibs = num_ibs; - for (i = 0; i < num_ibs; i++) - ibs[i].ctx = ctx; - - return parser; -} - int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) { union drm_amdgpu_cs *cs = data; @@ -463,8 +439,18 @@ static int cmp_size_smaller_first(void *priv, struct list_head *a, return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages; } -static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int error, bool backoff) +/** + * cs_parser_fini() - clean parser states + * @parser: parser structure holding parsing context. + * @error: error number + * + * If error is set than unvalidate buffer, otherwise just free memory + * used by parsing context. + **/ +static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff) { + unsigned i; + if (!error) { /* Sort the buffer list from the smallest to largest buffer, * which affects the order of buffers in the LRU list. @@ -479,17 +465,14 @@ static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int err list_sort(NULL, &parser->validated, cmp_size_smaller_first); ttm_eu_fence_buffer_objects(&parser->ticket, - &parser->validated, - &parser->ibs[parser->num_ibs-1].fence->base); + &parser->validated, + parser->fence); } else if (backoff) { ttm_eu_backoff_reservation(&parser->ticket, &parser->validated); } -} + fence_put(parser->fence); -static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser) -{ - unsigned i; if (parser->ctx) amdgpu_ctx_put(parser->ctx); if (parser->bo_list) @@ -499,31 +482,12 @@ static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser) for (i = 0; i < parser->nchunks; i++) drm_free_large(parser->chunks[i].kdata); kfree(parser->chunks); - if (!amdgpu_enable_scheduler) - { - if (parser->ibs) - for (i = 0; i < parser->num_ibs; i++) - amdgpu_ib_free(parser->adev, &parser->ibs[i]); - kfree(parser->ibs); - if (parser->uf.bo) - drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base); - } - - kfree(parser); -} - -/** - * cs_parser_fini() - clean parser states - * @parser: parser structure holding parsing context. - * @error: error number - * - * If error is set than unvalidate buffer, otherwise just free memory - * used by parsing context. - **/ -static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff) -{ - amdgpu_cs_parser_fini_early(parser, error, backoff); - amdgpu_cs_parser_fini_late(parser); + if (parser->ibs) + for (i = 0; i < parser->num_ibs; i++) + amdgpu_ib_free(parser->adev, &parser->ibs[i]); + kfree(parser->ibs); + if (parser->uf.bo) + drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base); } static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p, @@ -610,15 +574,9 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev, } r = amdgpu_bo_vm_update_pte(parser, vm); - if (r) { - goto out; - } - amdgpu_cs_sync_rings(parser); - if (!amdgpu_enable_scheduler) - r = amdgpu_ib_schedule(adev, parser->num_ibs, parser->ibs, - parser->filp); + if (!r) + amdgpu_cs_sync_rings(parser); -out: return r; } @@ -828,36 +786,36 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) union drm_amdgpu_cs *cs = data; struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_vm *vm = &fpriv->vm; - struct amdgpu_cs_parser *parser; + struct amdgpu_cs_parser parser = {}; bool reserved_buffers = false; int i, r; if (!adev->accel_working) return -EBUSY; - parser = amdgpu_cs_parser_create(adev, filp, NULL, NULL, 0); - if (!parser) - return -ENOMEM; - r = amdgpu_cs_parser_init(parser, data); + parser.adev = adev; + parser.filp = filp; + + r = amdgpu_cs_parser_init(&parser, data); if (r) { DRM_ERROR("Failed to initialize parser !\n"); - amdgpu_cs_parser_fini(parser, r, false); + amdgpu_cs_parser_fini(&parser, r, false); r = amdgpu_cs_handle_lockup(adev, r); return r; } mutex_lock(&vm->mutex); - r = amdgpu_cs_parser_relocs(parser); + r = amdgpu_cs_parser_relocs(&parser); if (r == -ENOMEM) DRM_ERROR("Not enough memory for command submission!\n"); else if (r && r != -ERESTARTSYS) DRM_ERROR("Failed to process the buffer list %d!\n", r); else if (!r) { reserved_buffers = true; - r = amdgpu_cs_ib_fill(adev, parser); + r = amdgpu_cs_ib_fill(adev, &parser); } if (!r) { - r = amdgpu_cs_dependencies(adev, parser); + r = amdgpu_cs_dependencies(adev, &parser); if (r) DRM_ERROR("Failed in the dependencies handling %d!\n", r); } @@ -865,62 +823,71 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (r) goto out; - for (i = 0; i < parser->num_ibs; i++) - trace_amdgpu_cs(parser, i); + for (i = 0; i < parser.num_ibs; i++) + trace_amdgpu_cs(&parser, i); - r = amdgpu_cs_ib_vm_chunk(adev, parser); + r = amdgpu_cs_ib_vm_chunk(adev, &parser); if (r) goto out; - if (amdgpu_enable_scheduler && parser->num_ibs) { + if (amdgpu_enable_scheduler && parser.num_ibs) { + struct amdgpu_ring * ring = parser.ibs->ring; + struct amd_sched_fence *fence; struct amdgpu_job *job; - struct amdgpu_ring * ring = parser->ibs->ring; + job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL); if (!job) { r = -ENOMEM; goto out; } + job->base.sched = &ring->sched; - job->base.s_entity = &parser->ctx->rings[ring->idx].entity; - job->adev = parser->adev; - job->ibs = parser->ibs; - job->num_ibs = parser->num_ibs; - job->base.owner = parser->filp; - mutex_init(&job->job_lock); + job->base.s_entity = &parser.ctx->rings[ring->idx].entity; + job->adev = parser.adev; + job->owner = parser.filp; + job->free_job = amdgpu_cs_free_job; + + job->ibs = parser.ibs; + job->num_ibs = parser.num_ibs; + parser.ibs = NULL; + parser.num_ibs = 0; + if (job->ibs[job->num_ibs - 1].user) { - memcpy(&job->uf, &parser->uf, - sizeof(struct amdgpu_user_fence)); + job->uf = parser.uf; job->ibs[job->num_ibs - 1].user = &job->uf; + parser.uf.bo = NULL; } - job->free_job = amdgpu_cs_free_job; - mutex_lock(&job->job_lock); - r = amd_sched_entity_push_job(&job->base); - if (r) { - mutex_unlock(&job->job_lock); + fence = amd_sched_fence_create(job->base.s_entity, + parser.filp); + if (!fence) { + r = -ENOMEM; amdgpu_cs_free_job(job); kfree(job); goto out; } - cs->out.handle = - amdgpu_ctx_add_fence(parser->ctx, ring, - &job->base.s_fence->base); - parser->ibs[parser->num_ibs - 1].sequence = cs->out.handle; + job->base.s_fence = fence; + parser.fence = fence_get(&fence->base); - list_sort(NULL, &parser->validated, cmp_size_smaller_first); - ttm_eu_fence_buffer_objects(&parser->ticket, - &parser->validated, - &job->base.s_fence->base); + cs->out.handle = amdgpu_ctx_add_fence(parser.ctx, ring, + &fence->base); + job->ibs[job->num_ibs - 1].sequence = cs->out.handle; - mutex_unlock(&job->job_lock); - amdgpu_cs_parser_fini_late(parser); - mutex_unlock(&vm->mutex); - return 0; + trace_amdgpu_cs_ioctl(job); + amd_sched_entity_push_job(&job->base); + + } else { + struct amdgpu_fence *fence; + + r = amdgpu_ib_schedule(adev, parser.num_ibs, parser.ibs, + parser.filp); + fence = parser.ibs[parser.num_ibs - 1].fence; + parser.fence = fence_get(&fence->base); + cs->out.handle = parser.ibs[parser.num_ibs - 1].sequence; } - cs->out.handle = parser->ibs[parser->num_ibs - 1].sequence; out: - amdgpu_cs_parser_fini(parser, r, reserved_buffers); + amdgpu_cs_parser_fini(&parser, r, reserved_buffers); mutex_unlock(&vm->mutex); r = amdgpu_cs_handle_lockup(adev, r); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 257d722..3671f9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -47,6 +47,9 @@ * that the the relevant GPU caches have been flushed. */ +static struct kmem_cache *amdgpu_fence_slab; +static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0); + /** * amdgpu_fence_write - write a fence value * @@ -85,24 +88,6 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring) } /** - * amdgpu_fence_schedule_check - schedule lockup check - * - * @ring: pointer to struct amdgpu_ring - * - * Queues a delayed work item to check for lockups. - */ -static void amdgpu_fence_schedule_check(struct amdgpu_ring *ring) -{ - /* - * Do not reset the timer here with mod_delayed_work, - * this can livelock in an interaction with TTM delayed destroy. - */ - queue_delayed_work(system_power_efficient_wq, - &ring->fence_drv.lockup_work, - AMDGPU_FENCE_JIFFIES_TIMEOUT); -} - -/** * amdgpu_fence_emit - emit a fence on the requested ring * * @ring: ring the fence is associated with @@ -118,7 +103,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner, struct amdgpu_device *adev = ring->adev; /* we are protected by the ring emission mutex */ - *fence = kmalloc(sizeof(struct amdgpu_fence), GFP_KERNEL); + *fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL); if ((*fence) == NULL) { return -ENOMEM; } @@ -132,11 +117,23 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner, amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, (*fence)->seq, AMDGPU_FENCE_FLAG_INT); - trace_amdgpu_fence_emit(ring->adev->ddev, ring->idx, (*fence)->seq); return 0; } /** + * amdgpu_fence_schedule_fallback - schedule fallback check + * + * @ring: pointer to struct amdgpu_ring + * + * Start a timer as fallback to our interrupts. + */ +static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring) +{ + mod_timer(&ring->fence_drv.fallback_timer, + jiffies + AMDGPU_FENCE_JIFFIES_TIMEOUT); +} + +/** * amdgpu_fence_activity - check for fence activity * * @ring: pointer to struct amdgpu_ring @@ -202,45 +199,38 @@ static bool amdgpu_fence_activity(struct amdgpu_ring *ring) } while (atomic64_xchg(&ring->fence_drv.last_seq, seq) > seq); if (seq < last_emitted) - amdgpu_fence_schedule_check(ring); + amdgpu_fence_schedule_fallback(ring); return wake; } /** - * amdgpu_fence_check_lockup - check for hardware lockup + * amdgpu_fence_process - process a fence * - * @work: delayed work item + * @adev: amdgpu_device pointer + * @ring: ring index the fence is associated with * - * Checks for fence activity and if there is none probe - * the hardware if a lockup occured. + * Checks the current fence value and wakes the fence queue + * if the sequence number has increased (all asics). */ -static void amdgpu_fence_check_lockup(struct work_struct *work) +void amdgpu_fence_process(struct amdgpu_ring *ring) { - struct amdgpu_fence_driver *fence_drv; - struct amdgpu_ring *ring; - - fence_drv = container_of(work, struct amdgpu_fence_driver, - lockup_work.work); - ring = fence_drv->ring; - if (amdgpu_fence_activity(ring)) wake_up_all(&ring->fence_drv.fence_queue); } /** - * amdgpu_fence_process - process a fence + * amdgpu_fence_fallback - fallback for hardware interrupts * - * @adev: amdgpu_device pointer - * @ring: ring index the fence is associated with + * @work: delayed work item * - * Checks the current fence value and wakes the fence queue - * if the sequence number has increased (all asics). + * Checks for fence activity. */ -void amdgpu_fence_process(struct amdgpu_ring *ring) +static void amdgpu_fence_fallback(unsigned long arg) { - if (amdgpu_fence_activity(ring)) - wake_up_all(&ring->fence_drv.fence_queue); + struct amdgpu_ring *ring = (void *)arg; + + amdgpu_fence_process(ring); } /** @@ -290,7 +280,7 @@ static int amdgpu_fence_ring_wait_seq(struct amdgpu_ring *ring, uint64_t seq) if (atomic64_read(&ring->fence_drv.last_seq) >= seq) return 0; - amdgpu_fence_schedule_check(ring); + amdgpu_fence_schedule_fallback(ring); wait_event(ring->fence_drv.fence_queue, ( (signaled = amdgpu_fence_seq_signaled(ring, seq)))); @@ -491,9 +481,8 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring) atomic64_set(&ring->fence_drv.last_seq, 0); ring->fence_drv.initialized = false; - INIT_DELAYED_WORK(&ring->fence_drv.lockup_work, - amdgpu_fence_check_lockup); - ring->fence_drv.ring = ring; + setup_timer(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback, + (unsigned long)ring); init_waitqueue_head(&ring->fence_drv.fence_queue); @@ -536,6 +525,13 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring) */ int amdgpu_fence_driver_init(struct amdgpu_device *adev) { + if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) { + amdgpu_fence_slab = kmem_cache_create( + "amdgpu_fence", sizeof(struct amdgpu_fence), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!amdgpu_fence_slab) + return -ENOMEM; + } if (amdgpu_debugfs_fence_init(adev)) dev_err(adev->dev, "fence debugfs file creation failed\n"); @@ -554,9 +550,12 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) { int i, r; + if (atomic_dec_and_test(&amdgpu_fence_slab_ref)) + kmem_cache_destroy(amdgpu_fence_slab); mutex_lock(&adev->ring_lock); for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; + if (!ring || !ring->fence_drv.initialized) continue; r = amdgpu_fence_wait_empty(ring); @@ -568,6 +567,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); amd_sched_fini(&ring->sched); + del_timer_sync(&ring->fence_drv.fallback_timer); ring->fence_drv.initialized = false; } mutex_unlock(&adev->ring_lock); @@ -751,18 +751,25 @@ static bool amdgpu_fence_enable_signaling(struct fence *f) fence->fence_wake.func = amdgpu_fence_check_signaled; __add_wait_queue(&ring->fence_drv.fence_queue, &fence->fence_wake); fence_get(f); - amdgpu_fence_schedule_check(ring); + if (!timer_pending(&ring->fence_drv.fallback_timer)) + amdgpu_fence_schedule_fallback(ring); FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx); return true; } +static void amdgpu_fence_release(struct fence *f) +{ + struct amdgpu_fence *fence = to_amdgpu_fence(f); + kmem_cache_free(amdgpu_fence_slab, fence); +} + const struct fence_ops amdgpu_fence_ops = { .get_driver_name = amdgpu_fence_get_driver_name, .get_timeline_name = amdgpu_fence_get_timeline_name, .enable_signaling = amdgpu_fence_enable_signaling, .signaled = amdgpu_fence_is_signaled, .wait = fence_default_wait, - .release = NULL, + .release = amdgpu_fence_release, }; /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 0873328..00c5b58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -483,6 +483,9 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (domain == AMDGPU_GEM_DOMAIN_CPU) goto error_unreserve; } + r = amdgpu_vm_update_page_directory(adev, bo_va->vm); + if (r) + goto error_unreserve; r = amdgpu_vm_clear_freed(adev, bo_va->vm); if (r) @@ -512,6 +515,9 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_bo *rbo; struct amdgpu_bo_va *bo_va; + struct ttm_validate_buffer tv, tv_pd; + struct ww_acquire_ctx ticket; + struct list_head list, duplicates; uint32_t invalid_flags, va_flags = 0; int r = 0; @@ -549,7 +555,18 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, return -ENOENT; mutex_lock(&fpriv->vm.mutex); rbo = gem_to_amdgpu_bo(gobj); - r = amdgpu_bo_reserve(rbo, false); + INIT_LIST_HEAD(&list); + INIT_LIST_HEAD(&duplicates); + tv.bo = &rbo->tbo; + tv.shared = true; + list_add(&tv.head, &list); + + if (args->operation == AMDGPU_VA_OP_MAP) { + tv_pd.bo = &fpriv->vm.page_directory->tbo; + tv_pd.shared = true; + list_add(&tv_pd.head, &list); + } + r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates); if (r) { mutex_unlock(&fpriv->vm.mutex); drm_gem_object_unreference_unlocked(gobj); @@ -558,7 +575,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, bo_va = amdgpu_vm_bo_find(&fpriv->vm, rbo); if (!bo_va) { - amdgpu_bo_unreserve(rbo); + ttm_eu_backoff_reservation(&ticket, &list); + drm_gem_object_unreference_unlocked(gobj); mutex_unlock(&fpriv->vm.mutex); return -ENOENT; } @@ -581,7 +599,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, default: break; } - + ttm_eu_backoff_reservation(&ticket, &list); if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE)) amdgpu_gem_va_update_vm(adev, bo_va, args->operation); mutex_unlock(&fpriv->vm.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index e659877..9e25eda 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -62,7 +62,7 @@ int amdgpu_ib_get(struct amdgpu_ring *ring, struct amdgpu_vm *vm, int r; if (size) { - r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo, + r = amdgpu_sa_bo_new(&adev->ring_tmp_bo, &ib->sa_bo, size, 256); if (r) { dev_err(adev->dev, "failed to get a new IB (%d)\n", r); @@ -216,7 +216,7 @@ int amdgpu_ib_schedule(struct amdgpu_device *adev, unsigned num_ibs, } if (ib->vm) - amdgpu_vm_fence(adev, ib->vm, ib->fence); + amdgpu_vm_fence(adev, ib->vm, &ib->fence->base); amdgpu_ring_unlock_commit(ring); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 3c2ff45..ea756e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -189,10 +189,9 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev, struct amdgpu_sa_manager *sa_manager); int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev, struct amdgpu_sa_manager *sa_manager); -int amdgpu_sa_bo_new(struct amdgpu_device *adev, - struct amdgpu_sa_manager *sa_manager, - struct amdgpu_sa_bo **sa_bo, - unsigned size, unsigned align); +int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, + struct amdgpu_sa_bo **sa_bo, + unsigned size, unsigned align); void amdgpu_sa_bo_free(struct amdgpu_device *adev, struct amdgpu_sa_bo **sa_bo, struct fence *fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c index 0212b31..8b88edb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c @@ -311,8 +311,7 @@ static bool amdgpu_sa_bo_next_hole(struct amdgpu_sa_manager *sa_manager, return false; } -int amdgpu_sa_bo_new(struct amdgpu_device *adev, - struct amdgpu_sa_manager *sa_manager, +int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, struct amdgpu_sa_bo **sa_bo, unsigned size, unsigned align) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index dcf4a8a..438c052 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -26,6 +26,7 @@ #include <linux/sched.h> #include <drm/drmP.h> #include "amdgpu.h" +#include "amdgpu_trace.h" static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job) { @@ -44,11 +45,8 @@ static struct fence *amdgpu_sched_run_job(struct amd_sched_job *sched_job) return NULL; } job = to_amdgpu_job(sched_job); - mutex_lock(&job->job_lock); - r = amdgpu_ib_schedule(job->adev, - job->num_ibs, - job->ibs, - job->base.owner); + trace_amdgpu_sched_run_job(job); + r = amdgpu_ib_schedule(job->adev, job->num_ibs, job->ibs, job->owner); if (r) { DRM_ERROR("Error scheduling IBs (%d)\n", r); goto err; @@ -61,8 +59,6 @@ err: if (job->free_job) job->free_job(job); - mutex_unlock(&job->job_lock); - fence_put(&job->base.s_fence->base); kfree(job); return fence ? &fence->base : NULL; } @@ -88,21 +84,19 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev, return -ENOMEM; job->base.sched = &ring->sched; job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity; + job->base.s_fence = amd_sched_fence_create(job->base.s_entity, owner); + if (!job->base.s_fence) { + kfree(job); + return -ENOMEM; + } + *f = fence_get(&job->base.s_fence->base); + job->adev = adev; job->ibs = ibs; job->num_ibs = num_ibs; - job->base.owner = owner; - mutex_init(&job->job_lock); + job->owner = owner; job->free_job = free_job; - mutex_lock(&job->job_lock); - r = amd_sched_entity_push_job(&job->base); - if (r) { - mutex_unlock(&job->job_lock); - kfree(job); - return r; - } - *f = fence_get(&job->base.s_fence->base); - mutex_unlock(&job->job_lock); + amd_sched_entity_push_job(&job->base); } else { r = amdgpu_ib_schedule(adev, num_ibs, ibs, owner); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c index ff3ca52..1caaf20 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c @@ -40,7 +40,7 @@ int amdgpu_semaphore_create(struct amdgpu_device *adev, if (*semaphore == NULL) { return -ENOMEM; } - r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo, + r = amdgpu_sa_bo_new(&adev->ring_tmp_bo, &(*semaphore)->sa_bo, 8, 8); if (r) { kfree(*semaphore); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index a6697fd..dd005c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -302,8 +302,14 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, return -EINVAL; } - if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores || - (count >= AMDGPU_NUM_SYNCS)) { + if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) { + r = fence_wait(&fence->base, true); + if (r) + return r; + continue; + } + + if (count >= AMDGPU_NUM_SYNCS) { /* not enough room, wait manually */ r = fence_wait(&fence->base, false); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 76ecbaf..8f9834ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -48,6 +48,57 @@ TRACE_EVENT(amdgpu_cs, __entry->fences) ); +TRACE_EVENT(amdgpu_cs_ioctl, + TP_PROTO(struct amdgpu_job *job), + TP_ARGS(job), + TP_STRUCT__entry( + __field(struct amdgpu_device *, adev) + __field(struct amd_sched_job *, sched_job) + __field(struct amdgpu_ib *, ib) + __field(struct fence *, fence) + __field(char *, ring_name) + __field(u32, num_ibs) + ), + + TP_fast_assign( + __entry->adev = job->adev; + __entry->sched_job = &job->base; + __entry->ib = job->ibs; + __entry->fence = &job->base.s_fence->base; + __entry->ring_name = job->ibs[0].ring->name; + __entry->num_ibs = job->num_ibs; + ), + TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u", + __entry->adev, __entry->sched_job, __entry->ib, + __entry->fence, __entry->ring_name, __entry->num_ibs) +); + +TRACE_EVENT(amdgpu_sched_run_job, + TP_PROTO(struct amdgpu_job *job), + TP_ARGS(job), + TP_STRUCT__entry( + __field(struct amdgpu_device *, adev) + __field(struct amd_sched_job *, sched_job) + __field(struct amdgpu_ib *, ib) + __field(struct fence *, fence) + __field(char *, ring_name) + __field(u32, num_ibs) + ), + + TP_fast_assign( + __entry->adev = job->adev; + __entry->sched_job = &job->base; + __entry->ib = job->ibs; + __entry->fence = &job->base.s_fence->base; + __entry->ring_name = job->ibs[0].ring->name; + __entry->num_ibs = job->num_ibs; + ), + TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u", + __entry->adev, __entry->sched_job, __entry->ib, + __entry->fence, __entry->ring_name, __entry->num_ibs) +); + + TRACE_EVENT(amdgpu_vm_grab_id, TP_PROTO(unsigned vmid, int ring), TP_ARGS(vmid, ring), @@ -196,49 +247,6 @@ TRACE_EVENT(amdgpu_bo_list_set, TP_printk("list=%p, bo=%p", __entry->list, __entry->bo) ); -DECLARE_EVENT_CLASS(amdgpu_fence_request, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno), - - TP_STRUCT__entry( - __field(u32, dev) - __field(int, ring) - __field(u32, seqno) - ), - - TP_fast_assign( - __entry->dev = dev->primary->index; - __entry->ring = ring; - __entry->seqno = seqno; - ), - - TP_printk("dev=%u, ring=%d, seqno=%u", - __entry->dev, __entry->ring, __entry->seqno) -); - -DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_emit, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno) -); - -DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_begin, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno) -); - -DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_end, - - TP_PROTO(struct drm_device *dev, int ring, u32 seqno), - - TP_ARGS(dev, ring, seqno) -); - DECLARE_EVENT_CLASS(amdgpu_semaphore_request, TP_PROTO(int ring, struct amdgpu_semaphore *sem), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 81bb8e9..d4bac5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1073,10 +1073,10 @@ static int amdgpu_mm_dump_table(struct seq_file *m, void *data) ret = drm_mm_dump_table(m, mm); spin_unlock(&glob->lru_lock); if (ttm_pl == TTM_PL_VRAM) - seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n", + seq_printf(m, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n", adev->mman.bdev.man[ttm_pl].size, - atomic64_read(&adev->vram_usage) >> 20, - atomic64_read(&adev->vram_vis_usage) >> 20); + (u64)atomic64_read(&adev->vram_usage) >> 20, + (u64)atomic64_read(&adev->vram_vis_usage) >> 20); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 633a32a..159ce54 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -143,10 +143,15 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, unsigned i; /* check if the id is still valid */ - if (vm_id->id && vm_id->last_id_use && - vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) { - trace_amdgpu_vm_grab_id(vm_id->id, ring->idx); - return 0; + if (vm_id->id) { + unsigned id = vm_id->id; + long owner; + + owner = atomic_long_read(&adev->vm_manager.ids[id].owner); + if (owner == (long)vm) { + trace_amdgpu_vm_grab_id(vm_id->id, ring->idx); + return 0; + } } /* we definately need to flush */ @@ -154,7 +159,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, /* skip over VMID 0, since it is the system VM */ for (i = 1; i < adev->vm_manager.nvm; ++i) { - struct fence *fence = adev->vm_manager.active[i]; + struct fence *fence = adev->vm_manager.ids[i].active; struct amdgpu_ring *fring; if (fence == NULL) { @@ -176,7 +181,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, if (choices[i]) { struct fence *fence; - fence = adev->vm_manager.active[choices[i]]; + fence = adev->vm_manager.ids[choices[i]].active; vm_id->id = choices[i]; trace_amdgpu_vm_grab_id(choices[i], ring->idx); @@ -207,24 +212,21 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory); struct amdgpu_vm_id *vm_id = &vm->ids[ring->idx]; struct fence *flushed_updates = vm_id->flushed_updates; - bool is_earlier = false; - - if (flushed_updates && updates) { - BUG_ON(flushed_updates->context != updates->context); - is_earlier = (updates->seqno - flushed_updates->seqno <= - INT_MAX) ? true : false; - } + bool is_later; - if (pd_addr != vm_id->pd_gpu_addr || !flushed_updates || - is_earlier) { + if (!flushed_updates) + is_later = true; + else if (!updates) + is_later = false; + else + is_later = fence_is_later(updates, flushed_updates); + if (pd_addr != vm_id->pd_gpu_addr || is_later) { trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id->id); - if (is_earlier) { + if (is_later) { vm_id->flushed_updates = fence_get(updates); fence_put(flushed_updates); } - if (!flushed_updates) - vm_id->flushed_updates = fence_get(updates); vm_id->pd_gpu_addr = pd_addr; amdgpu_ring_emit_vm_flush(ring, vm_id->id, vm_id->pd_gpu_addr); } @@ -244,16 +246,14 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring, */ void amdgpu_vm_fence(struct amdgpu_device *adev, struct amdgpu_vm *vm, - struct amdgpu_fence *fence) + struct fence *fence) { - unsigned ridx = fence->ring->idx; - unsigned vm_id = vm->ids[ridx].id; - - fence_put(adev->vm_manager.active[vm_id]); - adev->vm_manager.active[vm_id] = fence_get(&fence->base); + struct amdgpu_ring *ring = amdgpu_ring_from_fence(fence); + unsigned vm_id = vm->ids[ring->idx].id; - fence_put(vm->ids[ridx].last_id_use); - vm->ids[ridx].last_id_use = fence_get(&fence->base); + fence_put(adev->vm_manager.ids[vm_id].active); + adev->vm_manager.ids[vm_id].active = fence_get(fence); + atomic_long_set(&adev->vm_manager.ids[vm_id].owner, (long)vm); } /** @@ -332,6 +332,8 @@ int amdgpu_vm_free_job(struct amdgpu_job *job) * * @adev: amdgpu_device pointer * @bo: bo to clear + * + * need to reserve bo first before calling it. */ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, struct amdgpu_bo *bo) @@ -343,24 +345,20 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, uint64_t addr; int r; - r = amdgpu_bo_reserve(bo, false); - if (r) - return r; - r = reservation_object_reserve_shared(bo->tbo.resv); if (r) return r; r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false); if (r) - goto error_unreserve; + goto error; addr = amdgpu_bo_gpu_offset(bo); entries = amdgpu_bo_size(bo) / 8; ib = kzalloc(sizeof(struct amdgpu_ib), GFP_KERNEL); if (!ib) - goto error_unreserve; + goto error; r = amdgpu_ib_get(ring, NULL, entries * 2 + 64, ib); if (r) @@ -378,16 +376,14 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, if (!r) amdgpu_bo_fence(bo, fence, true); fence_put(fence); - if (amdgpu_enable_scheduler) { - amdgpu_bo_unreserve(bo); + if (amdgpu_enable_scheduler) return 0; - } + error_free: amdgpu_ib_free(adev, ib); kfree(ib); -error_unreserve: - amdgpu_bo_unreserve(bo); +error: return r; } @@ -989,7 +985,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev, * Add a mapping of the BO at the specefied addr into the VM. * Returns 0 for success, error for failure. * - * Object has to be reserved and gets unreserved by this function! + * Object has to be reserved and unreserved outside! */ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, @@ -1005,30 +1001,27 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, /* validate the parameters */ if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) { - amdgpu_bo_unreserve(bo_va->bo); + size == 0 || size & AMDGPU_GPU_PAGE_MASK) return -EINVAL; - } /* make sure object fit at this offset */ eaddr = saddr + size; - if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) { - amdgpu_bo_unreserve(bo_va->bo); + if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) return -EINVAL; - } last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE; if (last_pfn > adev->vm_manager.max_pfn) { dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n", last_pfn, adev->vm_manager.max_pfn); - amdgpu_bo_unreserve(bo_va->bo); return -EINVAL; } saddr /= AMDGPU_GPU_PAGE_SIZE; eaddr /= AMDGPU_GPU_PAGE_SIZE; + spin_lock(&vm->it_lock); it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1); + spin_unlock(&vm->it_lock); if (it) { struct amdgpu_bo_va_mapping *tmp; tmp = container_of(it, struct amdgpu_bo_va_mapping, it); @@ -1036,14 +1029,12 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, dev_err(adev->dev, "bo %p va 0x%010Lx-0x%010Lx conflict with " "0x%010lx-0x%010lx\n", bo_va->bo, saddr, eaddr, tmp->it.start, tmp->it.last + 1); - amdgpu_bo_unreserve(bo_va->bo); r = -EINVAL; goto error; } mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); if (!mapping) { - amdgpu_bo_unreserve(bo_va->bo); r = -ENOMEM; goto error; } @@ -1055,7 +1046,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, mapping->flags = flags; list_add(&mapping->list, &bo_va->invalids); + spin_lock(&vm->it_lock); interval_tree_insert(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_map(bo_va, mapping); /* Make sure the page tables are allocated */ @@ -1067,8 +1060,6 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, if (eaddr > vm->max_pde_used) vm->max_pde_used = eaddr; - amdgpu_bo_unreserve(bo_va->bo); - /* walk over the address space and allocate the page tables */ for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) { struct reservation_object *resv = vm->page_directory->tbo.resv; @@ -1077,13 +1068,11 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, if (vm->page_tables[pt_idx].bo) continue; - ww_mutex_lock(&resv->lock, NULL); r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8, AMDGPU_GPU_PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_VRAM, AMDGPU_GEM_CREATE_NO_CPU_ACCESS, NULL, resv, &pt); - ww_mutex_unlock(&resv->lock); if (r) goto error_free; @@ -1101,7 +1090,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, error_free: list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); kfree(mapping); @@ -1119,7 +1110,7 @@ error: * Remove a mapping of the BO at the specefied addr from the VM. * Returns 0 for success, error for failure. * - * Object has to be reserved and gets unreserved by this function! + * Object has to be reserved and unreserved outside! */ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, @@ -1144,21 +1135,20 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev, break; } - if (&mapping->list == &bo_va->invalids) { - amdgpu_bo_unreserve(bo_va->bo); + if (&mapping->list == &bo_va->invalids) return -ENOENT; - } } list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); if (valid) list_add(&mapping->list, &vm->freed); else kfree(mapping); - amdgpu_bo_unreserve(bo_va->bo); return 0; } @@ -1187,13 +1177,17 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, list_for_each_entry_safe(mapping, next, &bo_va->valids, list) { list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); trace_amdgpu_vm_bo_unmap(bo_va, mapping); list_add(&mapping->list, &vm->freed); } list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) { list_del(&mapping->list); + spin_lock(&vm->it_lock); interval_tree_remove(&mapping->it, &vm->va); + spin_unlock(&vm->it_lock); kfree(mapping); } @@ -1241,7 +1235,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { vm->ids[i].id = 0; vm->ids[i].flushed_updates = NULL; - vm->ids[i].last_id_use = NULL; } mutex_init(&vm->mutex); vm->va = RB_ROOT; @@ -1249,7 +1242,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) INIT_LIST_HEAD(&vm->invalidated); INIT_LIST_HEAD(&vm->cleared); INIT_LIST_HEAD(&vm->freed); - + spin_lock_init(&vm->it_lock); pd_size = amdgpu_vm_directory_size(adev); pd_entries = amdgpu_vm_num_pdes(adev); @@ -1269,8 +1262,14 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) NULL, NULL, &vm->page_directory); if (r) return r; - + r = amdgpu_bo_reserve(vm->page_directory, false); + if (r) { + amdgpu_bo_unref(&vm->page_directory); + vm->page_directory = NULL; + return r; + } r = amdgpu_vm_clear_bo(adev, vm->page_directory); + amdgpu_bo_unreserve(vm->page_directory); if (r) { amdgpu_bo_unref(&vm->page_directory); vm->page_directory = NULL; @@ -1313,11 +1312,28 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); - for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + unsigned id = vm->ids[i].id; + + atomic_long_cmpxchg(&adev->vm_manager.ids[id].owner, + (long)vm, 0); fence_put(vm->ids[i].flushed_updates); - fence_put(vm->ids[i].last_id_use); } mutex_destroy(&vm->mutex); } + +/** + * amdgpu_vm_manager_fini - cleanup VM manager + * + * @adev: amdgpu_device pointer + * + * Cleanup the VM manager and free resources. + */ +void amdgpu_vm_manager_fini(struct amdgpu_device *adev) +{ + unsigned i; + + for (i = 0; i < AMDGPU_NUM_VM; ++i) + fence_put(adev->vm_manager.ids[i].active); +} diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index a1a35a5..57a2e34 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -6569,12 +6569,12 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev, switch (state) { case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; + cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; + cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; default: @@ -6586,12 +6586,12 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev, switch (state) { case AMDGPU_IRQ_STATE_DISABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; + cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; case AMDGPU_IRQ_STATE_ENABLE: cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT); - cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; + cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK; WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 6776cf7..e1dcab9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -268,7 +268,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmCGTT_CP_CLK_CTRL, 0xffffffff, 0x00000100, mmCGTT_CPC_CLK_CTRL, 0xffffffff, 0x00000100, mmCGTT_CPF_CLK_CTRL, 0xffffffff, 0x40000100, - mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100, mmCGTT_GDS_CLK_CTRL, 0xffffffff, 0x00000100, mmCGTT_IA_CLK_CTRL, 0xffffffff, 0x06000100, mmCGTT_PA_CLK_CTRL, 0xffffffff, 0x00000100, @@ -296,10 +295,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96e00200, mmCP_RB_WPTR_POLL_CNTL, 0xffffffff, 0x00900100, mmRLC_CGCG_CGLS_CTRL, 0xffffffff, 0x0020003c, - mmPCIE_INDEX, 0xffffffff, 0x0140001c, - mmPCIE_DATA, 0x000f0000, 0x00000000, - mmCGTT_DRM_CLK_CTRL0, 0xff000fff, 0x00000100, - mmHDP_XDP_CGTT_BLK_CTRL, 0xc0000fff, 0x00000104, mmCP_MEM_SLP_CNTL, 0x00000001, 0x00000001, }; @@ -1000,7 +995,7 @@ static void gfx_v8_0_gpu_early_init(struct amdgpu_device *adev) adev->gfx.config.max_cu_per_sh = 16; adev->gfx.config.max_sh_per_se = 1; adev->gfx.config.max_backends_per_se = 4; - adev->gfx.config.max_texture_channel_caches = 8; + adev->gfx.config.max_texture_channel_caches = 16; adev->gfx.config.max_gprs = 256; adev->gfx.config.max_gs_threads = 32; adev->gfx.config.max_hw_contexts = 8; @@ -1613,6 +1608,296 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev) WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden); } case CHIP_FIJI: + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) { + switch (reg_offset) { + case 0: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 1: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 2: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 3: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 4: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 5: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 6: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 7: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING)); + break; + case 8: + gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16)); + break; + case 9: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 10: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 11: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 12: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 13: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 14: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 15: + gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 16: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 17: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 18: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 19: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 20: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 21: + gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 22: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 23: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 24: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 25: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_XTHICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 26: + gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_XTHICK) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1)); + break; + case 27: + gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 28: + gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2)); + break; + case 29: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + case 30: + gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_16x16) | + MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) | + SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8)); + break; + default: + gb_tile_moden = 0; + break; + } + adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden; + WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden); + } + for (reg_offset = 0; reg_offset < num_secondary_tile_mode_states; reg_offset++) { + switch (reg_offset) { + case 0: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 1: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 2: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 3: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 4: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 5: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 6: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 8: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 9: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 10: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 11: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 12: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 13: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) | + NUM_BANKS(ADDR_SURF_8_BANK)); + break; + case 14: + gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) | + NUM_BANKS(ADDR_SURF_4_BANK)); + break; + case 7: + /* unused idx */ + continue; + default: + gb_tile_moden = 0; + break; + } + adev->gfx.config.macrotile_mode_array[reg_offset] = gb_tile_moden; + WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden); + } + break; case CHIP_TONGA: for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) { switch (reg_offset) { @@ -2971,10 +3256,13 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev) amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START); switch (adev->asic_type) { case CHIP_TONGA: - case CHIP_FIJI: amdgpu_ring_write(ring, 0x16000012); amdgpu_ring_write(ring, 0x0000002A); break; + case CHIP_FIJI: + amdgpu_ring_write(ring, 0x3a00161a); + amdgpu_ring_write(ring, 0x0000002e); + break; case CHIP_TOPAZ: case CHIP_CARRIZO: amdgpu_ring_write(ring, 0x00000002); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 85bbcdc..7427d8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -40,7 +40,7 @@ static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev); -MODULE_FIRMWARE("radeon/boniare_mc.bin"); +MODULE_FIRMWARE("radeon/bonaire_mc.bin"); MODULE_FIRMWARE("radeon/hawaii_mc.bin"); /** @@ -501,6 +501,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1); WREG32(mmVM_L2_CNTL, tmp); tmp = REG_SET_FIELD(0, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1); @@ -960,12 +961,10 @@ static int gmc_v7_0_sw_init(void *handle) static int gmc_v7_0_sw_fini(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v7_0_vm_fini(adev); adev->vm_manager.enabled = false; } @@ -1010,12 +1009,10 @@ static int gmc_v7_0_hw_fini(void *handle) static int gmc_v7_0_suspend(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v7_0_vm_fini(adev); adev->vm_manager.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 1bcc4e7..cb0e50e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -629,6 +629,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1); + tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1); WREG32(mmVM_L2_CNTL, tmp); tmp = RREG32(mmVM_L2_CNTL2); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1); @@ -979,12 +980,10 @@ static int gmc_v8_0_sw_init(void *handle) static int gmc_v8_0_sw_fini(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v8_0_vm_fini(adev); adev->vm_manager.enabled = false; } @@ -1031,12 +1030,10 @@ static int gmc_v8_0_hw_fini(void *handle) static int gmc_v8_0_suspend(void *handle) { - int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; if (adev->vm_manager.enabled) { - for (i = 0; i < AMDGPU_NUM_VM; ++i) - fence_put(adev->vm_manager.active[i]); + amdgpu_vm_manager_fini(adev); gmc_v8_0_vm_fini(adev); adev->vm_manager.enabled = false; } diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h index 144f50a..c89dc77 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h @@ -16,6 +16,8 @@ TRACE_EVENT(amd_sched_job, TP_ARGS(sched_job), TP_STRUCT__entry( __field(struct amd_sched_entity *, entity) + __field(struct amd_sched_job *, sched_job) + __field(struct fence *, fence) __field(const char *, name) __field(u32, job_count) __field(int, hw_job_count) @@ -23,16 +25,32 @@ TRACE_EVENT(amd_sched_job, TP_fast_assign( __entry->entity = sched_job->s_entity; + __entry->sched_job = sched_job; + __entry->fence = &sched_job->s_fence->base; __entry->name = sched_job->sched->name; __entry->job_count = kfifo_len( &sched_job->s_entity->job_queue) / sizeof(sched_job); __entry->hw_job_count = atomic_read( &sched_job->sched->hw_rq_count); ), - TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d", - __entry->entity, __entry->name, __entry->job_count, - __entry->hw_job_count) + TP_printk("entity=%p, sched job=%p, fence=%p, ring=%s, job count:%u, hw job count:%d", + __entry->entity, __entry->sched_job, __entry->fence, __entry->name, + __entry->job_count, __entry->hw_job_count) ); + +TRACE_EVENT(amd_sched_process_job, + TP_PROTO(struct amd_sched_fence *fence), + TP_ARGS(fence), + TP_STRUCT__entry( + __field(struct fence *, fence) + ), + + TP_fast_assign( + __entry->fence = &fence->base; + ), + TP_printk("fence=%p signaled", __entry->fence) +); + #endif /* This part must be outside protection */ diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index 89619a5..ea30d6a 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -34,6 +34,9 @@ static struct amd_sched_job * amd_sched_entity_pop_job(struct amd_sched_entity *entity); static void amd_sched_wakeup(struct amd_gpu_scheduler *sched); +struct kmem_cache *sched_fence_slab; +atomic_t sched_fence_slab_ref = ATOMIC_INIT(0); + /* Initialize a given run queue struct */ static void amd_sched_rq_init(struct amd_sched_rq *rq) { @@ -273,22 +276,13 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job) * * Returns 0 for success, negative error code otherwise. */ -int amd_sched_entity_push_job(struct amd_sched_job *sched_job) +void amd_sched_entity_push_job(struct amd_sched_job *sched_job) { struct amd_sched_entity *entity = sched_job->s_entity; - struct amd_sched_fence *fence = amd_sched_fence_create( - entity, sched_job->owner); - - if (!fence) - return -ENOMEM; - - fence_get(&fence->base); - sched_job->s_fence = fence; wait_event(entity->sched->job_scheduled, amd_sched_entity_in(sched_job)); trace_amd_sched_job(sched_job); - return 0; } /** @@ -343,6 +337,7 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb) list_del_init(&s_fence->list); spin_unlock_irqrestore(&sched->fence_list_lock, flags); } + trace_amd_sched_process_job(s_fence); fence_put(&s_fence->base); wake_up_interruptible(&sched->wake_up_worker); } @@ -450,6 +445,13 @@ int amd_sched_init(struct amd_gpu_scheduler *sched, init_waitqueue_head(&sched->wake_up_worker); init_waitqueue_head(&sched->job_scheduled); atomic_set(&sched->hw_rq_count, 0); + if (atomic_inc_return(&sched_fence_slab_ref) == 1) { + sched_fence_slab = kmem_cache_create( + "amd_sched_fence", sizeof(struct amd_sched_fence), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!sched_fence_slab) + return -ENOMEM; + } /* Each scheduler will run on a seperate kernel thread */ sched->thread = kthread_run(amd_sched_main, sched, sched->name); @@ -470,4 +472,6 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched) { if (sched->thread) kthread_stop(sched->thread); + if (atomic_dec_and_test(&sched_fence_slab_ref)) + kmem_cache_destroy(sched_fence_slab); } diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h index 929e9ac..939692b 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h @@ -30,6 +30,9 @@ struct amd_gpu_scheduler; struct amd_sched_rq; +extern struct kmem_cache *sched_fence_slab; +extern atomic_t sched_fence_slab_ref; + /** * A scheduler entity is a wrapper around a job queue or a group * of other entities. Entities take turns emitting jobs from their @@ -76,7 +79,6 @@ struct amd_sched_job { struct amd_gpu_scheduler *sched; struct amd_sched_entity *s_entity; struct amd_sched_fence *s_fence; - void *owner; }; extern const struct fence_ops amd_sched_fence_ops; @@ -128,7 +130,7 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched, uint32_t jobs); void amd_sched_entity_fini(struct amd_gpu_scheduler *sched, struct amd_sched_entity *entity); -int amd_sched_entity_push_job(struct amd_sched_job *sched_job); +void amd_sched_entity_push_job(struct amd_sched_job *sched_job); struct amd_sched_fence *amd_sched_fence_create( struct amd_sched_entity *s_entity, void *owner); diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c index d802638..8d2130b 100644 --- a/drivers/gpu/drm/amd/scheduler/sched_fence.c +++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c @@ -32,7 +32,7 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity struct amd_sched_fence *fence = NULL; unsigned seq; - fence = kzalloc(sizeof(struct amd_sched_fence), GFP_KERNEL); + fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL); if (fence == NULL) return NULL; fence->owner = owner; @@ -71,11 +71,17 @@ static bool amd_sched_fence_enable_signaling(struct fence *f) return true; } +static void amd_sched_fence_release(struct fence *f) +{ + struct amd_sched_fence *fence = to_amd_sched_fence(f); + kmem_cache_free(sched_fence_slab, fence); +} + const struct fence_ops amd_sched_fence_ops = { .get_driver_name = amd_sched_fence_get_driver_name, .get_timeline_name = amd_sched_fence_get_timeline_name, .enable_signaling = amd_sched_fence_enable_signaling, .signaled = NULL, .wait = fence_default_wait, - .release = NULL, + .release = amd_sched_fence_release, }; diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 7bb3845..aeee083 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1432,6 +1432,45 @@ static int atomic_set_prop(struct drm_atomic_state *state, return ret; } +/** + * drm_atomic_update_old_fb -- Unset old_fb pointers and set plane->fb pointers. + * + * @dev: drm device to check. + * @plane_mask: plane mask for planes that were updated. + * @ret: return value, can be -EDEADLK for a retry. + * + * Before doing an update plane->old_fb is set to plane->fb, + * but before dropping the locks old_fb needs to be set to NULL + * and plane->fb updated. This is a common operation for each + * atomic update, so this call is split off as a helper. + */ +void drm_atomic_clean_old_fb(struct drm_device *dev, + unsigned plane_mask, + int ret) +{ + struct drm_plane *plane; + + /* if succeeded, fixup legacy plane crtc/fb ptrs before dropping + * locks (ie. while it is still safe to deref plane->state). We + * need to do this here because the driver entry points cannot + * distinguish between legacy and atomic ioctls. + */ + drm_for_each_plane_mask(plane, dev, plane_mask) { + if (ret == 0) { + struct drm_framebuffer *new_fb = plane->state->fb; + if (new_fb) + drm_framebuffer_reference(new_fb); + plane->fb = new_fb; + plane->crtc = plane->state->crtc; + + if (plane->old_fb) + drm_framebuffer_unreference(plane->old_fb); + } + plane->old_fb = NULL; + } +} +EXPORT_SYMBOL(drm_atomic_clean_old_fb); + int drm_mode_atomic_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { @@ -1446,7 +1485,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, struct drm_plane *plane; struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; - unsigned plane_mask = 0; + unsigned plane_mask; int ret = 0; unsigned int i, j; @@ -1486,6 +1525,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET); retry: + plane_mask = 0; copied_objs = 0; copied_props = 0; @@ -1576,24 +1616,7 @@ retry: } out: - /* if succeeded, fixup legacy plane crtc/fb ptrs before dropping - * locks (ie. while it is still safe to deref plane->state). We - * need to do this here because the driver entry points cannot - * distinguish between legacy and atomic ioctls. - */ - drm_for_each_plane_mask(plane, dev, plane_mask) { - if (ret == 0) { - struct drm_framebuffer *new_fb = plane->state->fb; - if (new_fb) - drm_framebuffer_reference(new_fb); - plane->fb = new_fb; - plane->crtc = plane->state->crtc; - - if (plane->old_fb) - drm_framebuffer_unreference(plane->old_fb); - } - plane->old_fb = NULL; - } + drm_atomic_clean_old_fb(dev, plane_mask, ret); if (ret && arg->flags & DRM_MODE_PAGE_FLIP_EVENT) { /* diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 0c6f621..e5aec45 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -210,6 +210,14 @@ update_connector_routing(struct drm_atomic_state *state, int conn_idx) return -EINVAL; } + if (!drm_encoder_crtc_ok(new_encoder, connector_state->crtc)) { + DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] incompatible with [CRTC:%d]\n", + new_encoder->base.id, + new_encoder->name, + connector_state->crtc->base.id); + return -EINVAL; + } + if (new_encoder == connector_state->best_encoder) { DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] keeps [ENCODER:%d:%s], now on [CRTC:%d]\n", connector->base.id, @@ -1553,6 +1561,9 @@ retry: goto fail; } + if (plane_state->crtc && (plane == plane->crtc->cursor)) + plane_state->state->legacy_cursor_update = true; + ret = __drm_atomic_helper_disable_plane(plane, plane_state); if (ret != 0) goto fail; @@ -1605,9 +1616,6 @@ int __drm_atomic_helper_disable_plane(struct drm_plane *plane, plane_state->src_h = 0; plane_state->src_w = 0; - if (plane->crtc && (plane == plane->crtc->cursor)) - plane_state->state->legacy_cursor_update = true; - return 0; } @@ -1741,6 +1749,7 @@ int __drm_atomic_helper_set_config(struct drm_mode_set *set, struct drm_crtc_state *crtc_state; struct drm_plane_state *primary_state; struct drm_crtc *crtc = set->crtc; + int hdisplay, vdisplay; int ret; crtc_state = drm_atomic_get_crtc_state(state, crtc); @@ -1783,19 +1792,21 @@ int __drm_atomic_helper_set_config(struct drm_mode_set *set, if (ret != 0) return ret; + drm_crtc_get_hv_timing(set->mode, &hdisplay, &vdisplay); + drm_atomic_set_fb_for_plane(primary_state, set->fb); primary_state->crtc_x = 0; primary_state->crtc_y = 0; - primary_state->crtc_h = set->mode->vdisplay; - primary_state->crtc_w = set->mode->hdisplay; + primary_state->crtc_h = vdisplay; + primary_state->crtc_w = hdisplay; primary_state->src_x = set->x << 16; primary_state->src_y = set->y << 16; if (primary_state->rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270))) { - primary_state->src_h = set->mode->hdisplay << 16; - primary_state->src_w = set->mode->vdisplay << 16; + primary_state->src_h = hdisplay << 16; + primary_state->src_w = vdisplay << 16; } else { - primary_state->src_h = set->mode->vdisplay << 16; - primary_state->src_w = set->mode->hdisplay << 16; + primary_state->src_h = vdisplay << 16; + primary_state->src_w = hdisplay << 16; } commit: diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index e673c13..69cbab5 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -342,6 +342,7 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper) struct drm_plane *plane; struct drm_atomic_state *state; int i, ret; + unsigned plane_mask; state = drm_atomic_state_alloc(dev); if (!state) @@ -349,11 +350,10 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper) state->acquire_ctx = dev->mode_config.acquire_ctx; retry: + plane_mask = 0; drm_for_each_plane(plane, dev) { struct drm_plane_state *plane_state; - plane->old_fb = plane->fb; - plane_state = drm_atomic_get_plane_state(state, plane); if (IS_ERR(plane_state)) { ret = PTR_ERR(plane_state); @@ -362,6 +362,9 @@ retry: plane_state->rotation = BIT(DRM_ROTATE_0); + plane->old_fb = plane->fb; + plane_mask |= 1 << drm_plane_index(plane); + /* disable non-primary: */ if (plane->type == DRM_PLANE_TYPE_PRIMARY) continue; @@ -382,19 +385,7 @@ retry: ret = drm_atomic_commit(state); fail: - drm_for_each_plane(plane, dev) { - if (ret == 0) { - struct drm_framebuffer *new_fb = plane->state->fb; - if (new_fb) - drm_framebuffer_reference(new_fb); - plane->fb = new_fb; - plane->crtc = plane->state->crtc; - - if (plane->old_fb) - drm_framebuffer_unreference(plane->old_fb); - } - plane->old_fb = NULL; - } + drm_atomic_clean_old_fb(dev, plane_mask, ret); if (ret == -EDEADLK) goto backoff; @@ -1236,7 +1227,9 @@ static int pan_display_atomic(struct fb_var_screeninfo *var, struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; struct drm_atomic_state *state; + struct drm_plane *plane; int i, ret; + unsigned plane_mask; state = drm_atomic_state_alloc(dev); if (!state) @@ -1244,19 +1237,22 @@ static int pan_display_atomic(struct fb_var_screeninfo *var, state->acquire_ctx = dev->mode_config.acquire_ctx; retry: + plane_mask = 0; for(i = 0; i < fb_helper->crtc_count; i++) { struct drm_mode_set *mode_set; mode_set = &fb_helper->crtc_info[i].mode_set; - mode_set->crtc->primary->old_fb = mode_set->crtc->primary->fb; - mode_set->x = var->xoffset; mode_set->y = var->yoffset; ret = __drm_atomic_helper_set_config(mode_set, state); if (ret != 0) goto fail; + + plane = mode_set->crtc->primary; + plane_mask |= drm_plane_index(plane); + plane->old_fb = plane->fb; } ret = drm_atomic_commit(state); @@ -1268,26 +1264,7 @@ retry: fail: - for(i = 0; i < fb_helper->crtc_count; i++) { - struct drm_mode_set *mode_set; - struct drm_plane *plane; - - mode_set = &fb_helper->crtc_info[i].mode_set; - plane = mode_set->crtc->primary; - - if (ret == 0) { - struct drm_framebuffer *new_fb = plane->state->fb; - - if (new_fb) - drm_framebuffer_reference(new_fb); - plane->fb = new_fb; - plane->crtc = plane->state->crtc; - - if (plane->old_fb) - drm_framebuffer_unreference(plane->old_fb); - } - plane->old_fb = NULL; - } + drm_atomic_clean_old_fb(dev, plane_mask, ret); if (ret == -EDEADLK) goto backoff; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8afda45..95bb27d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -351,6 +351,8 @@ enum intel_dpll_id { /* hsw/bdw */ DPLL_ID_WRPLL1 = 0, DPLL_ID_WRPLL2 = 1, + DPLL_ID_SPLL = 2, + /* skl */ DPLL_ID_SKL_DPLL1 = 0, DPLL_ID_SKL_DPLL2 = 1, @@ -367,6 +369,7 @@ struct intel_dpll_hw_state { /* hsw, bdw */ uint32_t wrpll; + uint32_t spll; /* skl */ /* @@ -2648,6 +2651,7 @@ struct i915_params { int enable_cmd_parser; /* leave bools at the end to not create holes */ bool enable_hangcheck; + bool fastboot; bool prefault_disable; bool load_detect_test; bool reset; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 5cf4a19..91bb1fc 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3809,6 +3809,7 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data, int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_caching *args = data; struct drm_i915_gem_object *obj; enum i915_cache_level level; @@ -3837,9 +3838,11 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data, return -EINVAL; } + intel_runtime_pm_get(dev_priv); + ret = i915_mutex_lock_interruptible(dev); if (ret) - return ret; + goto rpm_put; obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle)); if (&obj->base == NULL) { @@ -3852,6 +3855,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data, drm_gem_object_unreference(&obj->base); unlock: mutex_unlock(&dev->struct_mutex); +rpm_put: + intel_runtime_pm_put(dev_priv); + return ret; } diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 96bb238..4be13a5 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -40,6 +40,7 @@ struct i915_params i915 __read_mostly = { .preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT), .disable_power_well = -1, .enable_ips = 1, + .fastboot = 0, .prefault_disable = 0, .load_detect_test = 0, .reset = true, @@ -133,6 +134,10 @@ MODULE_PARM_DESC(disable_power_well, module_param_named_unsafe(enable_ips, i915.enable_ips, int, 0600); MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)"); +module_param_named(fastboot, i915.fastboot, bool, 0600); +MODULE_PARM_DESC(fastboot, + "Try to skip unnecessary mode sets at boot time (default: false)"); + module_param_named_unsafe(prefault_disable, i915.prefault_disable, bool, 0600); MODULE_PARM_DESC(prefault_disable, "Disable page prefaulting for pread/pwrite/reloc (default:false). " diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index b84aaa0..6a2c76e 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -138,18 +138,6 @@ static void hsw_crt_get_config(struct intel_encoder *encoder, pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder); } -static void hsw_crt_pre_enable(struct intel_encoder *encoder) -{ - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - - WARN(I915_READ(SPLL_CTL) & SPLL_PLL_ENABLE, "SPLL already enabled\n"); - I915_WRITE(SPLL_CTL, - SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC); - POSTING_READ(SPLL_CTL); - udelay(20); -} - /* Note: The caller is required to filter out dpms modes not supported by the * platform. */ static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode) @@ -216,19 +204,6 @@ static void pch_post_disable_crt(struct intel_encoder *encoder) intel_disable_crt(encoder); } -static void hsw_crt_post_disable(struct intel_encoder *encoder) -{ - struct drm_device *dev = encoder->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t val; - - DRM_DEBUG_KMS("Disabling SPLL\n"); - val = I915_READ(SPLL_CTL); - WARN_ON(!(val & SPLL_PLL_ENABLE)); - I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE); - POSTING_READ(SPLL_CTL); -} - static void intel_enable_crt(struct intel_encoder *encoder) { struct intel_crt *crt = intel_encoder_to_crt(encoder); @@ -280,6 +255,10 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder, if (HAS_DDI(dev)) { pipe_config->ddi_pll_sel = PORT_CLK_SEL_SPLL; pipe_config->port_clock = 135000 * 2; + + pipe_config->dpll_hw_state.wrpll = 0; + pipe_config->dpll_hw_state.spll = + SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC; } return true; @@ -860,8 +839,6 @@ void intel_crt_init(struct drm_device *dev) if (HAS_DDI(dev)) { crt->base.get_config = hsw_crt_get_config; crt->base.get_hw_state = intel_ddi_get_hw_state; - crt->base.pre_enable = hsw_crt_pre_enable; - crt->base.post_disable = hsw_crt_post_disable; } else { crt->base.get_config = intel_crt_get_config; crt->base.get_hw_state = intel_crt_get_hw_state; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index b25e99a..a6752a6 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1286,6 +1286,18 @@ hsw_ddi_pll_select(struct intel_crtc *intel_crtc, } crtc_state->ddi_pll_sel = PORT_CLK_SEL_WRPLL(pll->id); + } else if (crtc_state->ddi_pll_sel == PORT_CLK_SEL_SPLL) { + struct drm_atomic_state *state = crtc_state->base.state; + struct intel_shared_dpll_config *spll = + &intel_atomic_get_shared_dpll_state(state)[DPLL_ID_SPLL]; + + if (spll->crtc_mask && + WARN_ON(spll->hw_state.spll != crtc_state->dpll_hw_state.spll)) + return false; + + crtc_state->shared_dpll = DPLL_ID_SPLL; + spll->hw_state.spll = crtc_state->dpll_hw_state.spll; + spll->crtc_mask |= 1 << intel_crtc->pipe; } return true; @@ -2437,7 +2449,7 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder) } } -static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv, +static void hsw_ddi_wrpll_enable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { I915_WRITE(WRPLL_CTL(pll->id), pll->config.hw_state.wrpll); @@ -2445,9 +2457,17 @@ static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv, udelay(20); } -static void hsw_ddi_pll_disable(struct drm_i915_private *dev_priv, +static void hsw_ddi_spll_enable(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { + I915_WRITE(SPLL_CTL, pll->config.hw_state.spll); + POSTING_READ(SPLL_CTL); + udelay(20); +} + +static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ uint32_t val; val = I915_READ(WRPLL_CTL(pll->id)); @@ -2455,9 +2475,19 @@ static void hsw_ddi_pll_disable(struct drm_i915_private *dev_priv, POSTING_READ(WRPLL_CTL(pll->id)); } -static bool hsw_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, - struct intel_shared_dpll *pll, - struct intel_dpll_hw_state *hw_state) +static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll) +{ + uint32_t val; + + val = I915_READ(SPLL_CTL); + I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE); + POSTING_READ(SPLL_CTL); +} + +static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll, + struct intel_dpll_hw_state *hw_state) { uint32_t val; @@ -2470,25 +2500,50 @@ static bool hsw_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, return val & WRPLL_PLL_ENABLE; } +static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv, + struct intel_shared_dpll *pll, + struct intel_dpll_hw_state *hw_state) +{ + uint32_t val; + + if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + return false; + + val = I915_READ(SPLL_CTL); + hw_state->spll = val; + + return val & SPLL_PLL_ENABLE; +} + + static const char * const hsw_ddi_pll_names[] = { "WRPLL 1", "WRPLL 2", + "SPLL" }; static void hsw_shared_dplls_init(struct drm_i915_private *dev_priv) { int i; - dev_priv->num_shared_dpll = 2; + dev_priv->num_shared_dpll = 3; - for (i = 0; i < dev_priv->num_shared_dpll; i++) { + for (i = 0; i < 2; i++) { dev_priv->shared_dplls[i].id = i; dev_priv->shared_dplls[i].name = hsw_ddi_pll_names[i]; - dev_priv->shared_dplls[i].disable = hsw_ddi_pll_disable; - dev_priv->shared_dplls[i].enable = hsw_ddi_pll_enable; + dev_priv->shared_dplls[i].disable = hsw_ddi_wrpll_disable; + dev_priv->shared_dplls[i].enable = hsw_ddi_wrpll_enable; dev_priv->shared_dplls[i].get_hw_state = - hsw_ddi_pll_get_hw_state; + hsw_ddi_wrpll_get_hw_state; } + + /* SPLL is special, but needs to be initialized anyway.. */ + dev_priv->shared_dplls[i].id = i; + dev_priv->shared_dplls[i].name = hsw_ddi_pll_names[i]; + dev_priv->shared_dplls[i].disable = hsw_ddi_spll_disable; + dev_priv->shared_dplls[i].enable = hsw_ddi_spll_enable; + dev_priv->shared_dplls[i].get_hw_state = hsw_ddi_spll_get_hw_state; + } static const char * const skl_ddi_pll_names[] = { diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index f62ffc0..71860f8 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2646,11 +2646,13 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, return; valid_fb: - plane_state->src_x = plane_state->src_y = 0; + plane_state->src_x = 0; + plane_state->src_y = 0; plane_state->src_w = fb->width << 16; plane_state->src_h = fb->height << 16; - plane_state->crtc_x = plane_state->src_y = 0; + plane_state->crtc_x = 0; + plane_state->crtc_y = 0; plane_state->crtc_w = fb->width; plane_state->crtc_h = fb->height; @@ -4237,6 +4239,7 @@ struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, struct intel_shared_dpll *pll; struct intel_shared_dpll_config *shared_dpll; enum intel_dpll_id i; + int max = dev_priv->num_shared_dpll; shared_dpll = intel_atomic_get_shared_dpll_state(crtc_state->base.state); @@ -4271,9 +4274,11 @@ struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, WARN_ON(shared_dpll[i].crtc_mask); goto found; - } + } else if (INTEL_INFO(dev_priv)->gen < 9 && HAS_DDI(dev_priv)) + /* Do not consider SPLL */ + max = 2; - for (i = 0; i < dev_priv->num_shared_dpll; i++) { + for (i = 0; i < max; i++) { pll = &dev_priv->shared_dplls[i]; /* Only want to check enabled timings first */ @@ -9723,6 +9728,8 @@ static void haswell_get_ddi_pll(struct drm_i915_private *dev_priv, case PORT_CLK_SEL_WRPLL2: pipe_config->shared_dpll = DPLL_ID_WRPLL2; break; + case PORT_CLK_SEL_SPLL: + pipe_config->shared_dpll = DPLL_ID_SPLL; } } @@ -12003,9 +12010,10 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc, pipe_config->dpll_hw_state.cfgcr1, pipe_config->dpll_hw_state.cfgcr2); } else if (HAS_DDI(dev)) { - DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: wrpll: 0x%x\n", + DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: wrpll: 0x%x spll: 0x%x\n", pipe_config->ddi_pll_sel, - pipe_config->dpll_hw_state.wrpll); + pipe_config->dpll_hw_state.wrpll, + pipe_config->dpll_hw_state.spll); } else { DRM_DEBUG_KMS("dpll_hw_state: dpll: 0x%x, dpll_md: 0x%x, " "fp0: 0x%x, fp1: 0x%x\n", @@ -12528,6 +12536,7 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_X(dpll_hw_state.fp0); PIPE_CONF_CHECK_X(dpll_hw_state.fp1); PIPE_CONF_CHECK_X(dpll_hw_state.wrpll); + PIPE_CONF_CHECK_X(dpll_hw_state.spll); PIPE_CONF_CHECK_X(dpll_hw_state.ctrl1); PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr1); PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr2); @@ -13032,6 +13041,9 @@ static int intel_atomic_check(struct drm_device *dev, struct intel_crtc_state *pipe_config = to_intel_crtc_state(crtc_state); + memset(&to_intel_crtc(crtc)->atomic, 0, + sizeof(struct intel_crtc_atomic_commit)); + /* Catch I915_MODE_FLAG_INHERITED */ if (crtc_state->mode.private_flags != crtc->state->mode.private_flags) crtc_state->mode_changed = true; @@ -13056,7 +13068,8 @@ static int intel_atomic_check(struct drm_device *dev, if (ret) return ret; - if (intel_pipe_config_compare(state->dev, + if (i915.fastboot && + intel_pipe_config_compare(state->dev, to_intel_crtc_state(crtc->state), pipe_config, true)) { crtc_state->mode_changed = false; @@ -14364,16 +14377,17 @@ static int intel_framebuffer_init(struct drm_device *dev, static struct drm_framebuffer * intel_user_framebuffer_create(struct drm_device *dev, struct drm_file *filp, - struct drm_mode_fb_cmd2 *mode_cmd) + struct drm_mode_fb_cmd2 *user_mode_cmd) { struct drm_i915_gem_object *obj; + struct drm_mode_fb_cmd2 mode_cmd = *user_mode_cmd; obj = to_intel_bo(drm_gem_object_lookup(dev, filp, - mode_cmd->handles[0])); + mode_cmd.handles[0])); if (&obj->base == NULL) return ERR_PTR(-ENOENT); - return intel_framebuffer_create(dev, mode_cmd, obj); + return intel_framebuffer_create(dev, &mode_cmd, obj); } #ifndef CONFIG_DRM_FBDEV_EMULATION @@ -14705,6 +14719,9 @@ static struct intel_quirk intel_quirks[] = { /* Apple Macbook 2,1 (Core 2 T7400) */ { 0x27a2, 0x8086, 0x7270, quirk_backlight_present }, + /* Apple Macbook 4,1 */ + { 0x2a02, 0x106b, 0x00a1, quirk_backlight_present }, + /* Toshiba CB35 Chromebook (Celeron 2955U) */ { 0x0a06, 0x1179, 0x0a88, quirk_backlight_present }, diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index d52a15d..071a76b 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4449,7 +4449,7 @@ static void gen6_set_rps(struct drm_device *dev, u8 val) POSTING_READ(GEN6_RPNSWREQ); dev_priv->rps.cur_freq = val; - trace_intel_gpu_freq_change(val * 50); + trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val)); } static void valleyview_set_rps(struct drm_device *dev, u8 val) @@ -7255,7 +7255,8 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val) int intel_gpu_freq(struct drm_i915_private *dev_priv, int val) { if (IS_GEN9(dev_priv->dev)) - return (val * GT_FREQUENCY_MULTIPLIER) / GEN9_FREQ_SCALER; + return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER, + GEN9_FREQ_SCALER); else if (IS_CHERRYVIEW(dev_priv->dev)) return chv_gpu_freq(dev_priv, val); else if (IS_VALLEYVIEW(dev_priv->dev)) @@ -7267,13 +7268,14 @@ int intel_gpu_freq(struct drm_i915_private *dev_priv, int val) int intel_freq_opcode(struct drm_i915_private *dev_priv, int val) { if (IS_GEN9(dev_priv->dev)) - return (val * GEN9_FREQ_SCALER) / GT_FREQUENCY_MULTIPLIER; + return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER, + GT_FREQUENCY_MULTIPLIER); else if (IS_CHERRYVIEW(dev_priv->dev)) return chv_freq_opcode(dev_priv, val); else if (IS_VALLEYVIEW(dev_priv->dev)) return byt_freq_opcode(dev_priv, val); else - return val / GT_FREQUENCY_MULTIPLIER; + return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER); } struct request_boost { diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c index 4f2068f..a7bf6a9 100644 --- a/drivers/gpu/drm/mgag200/mgag200_cursor.c +++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c @@ -70,6 +70,11 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc, BUG_ON(pixels_2 != pixels_current && pixels_2 != pixels_prev); BUG_ON(pixels_current == pixels_prev); + if (!handle || !file_priv) { + mga_hide_cursor(mdev); + return 0; + } + obj = drm_gem_object_lookup(dev, file_priv, handle); if (!obj) return -ENOENT; @@ -88,12 +93,6 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc, goto out_unreserve1; } - if (!handle) { - mga_hide_cursor(mdev); - ret = 0; - goto out1; - } - /* Move cursor buffers into VRAM if they aren't already */ if (!pixels_1->pin_count) { ret = mgag200_bo_pin(pixels_1, TTM_PL_FLAG_VRAM, diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index d302488..84d4563 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -221,11 +221,17 @@ int radeon_bo_create(struct radeon_device *rdev, if (!(rdev->flags & RADEON_IS_PCIE)) bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); + /* Write-combined CPU mappings of GTT cause GPU hangs with RV6xx + * See https://bugs.freedesktop.org/show_bug.cgi?id=91268 + */ + if (rdev->family >= CHIP_RV610 && rdev->family <= CHIP_RV635) + bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); + #ifdef CONFIG_X86_32 /* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit * See https://bugs.freedesktop.org/show_bug.cgi?id=84627 */ - bo->flags &= ~RADEON_GEM_GTT_WC; + bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); #elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT) /* Don't try to enable write-combining when it can't work, or things * may be slow @@ -235,9 +241,10 @@ int radeon_bo_create(struct radeon_device *rdev, #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \ thanks to write-combining - DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " - "better performance thanks to write-combining\n"); - bo->flags &= ~RADEON_GEM_GTT_WC; + if (bo->flags & RADEON_GEM_GTT_WC) + DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " + "better performance thanks to write-combining\n"); + bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); #endif radeon_ttm_placement_from_domain(bo, domain); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 6d80dde..f4f03dc 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1542,8 +1542,7 @@ int radeon_pm_late_init(struct radeon_device *rdev) ret = device_create_file(rdev->dev, &dev_attr_power_method); if (ret) DRM_ERROR("failed to create device file for power method\n"); - if (!ret) - rdev->pm.sysfs_initialized = true; + rdev->pm.sysfs_initialized = true; } mutex_lock(&rdev->pm.mutex); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index e72bf46..a82b891 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2927,7 +2927,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, - { PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, { 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 7a9f476..265064c 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -168,7 +168,7 @@ static int vc4_get_clock_select(struct drm_crtc *crtc) struct drm_connector *connector; drm_for_each_connector(connector, crtc->dev) { - if (connector && connector->state->crtc == crtc) { + if (connector->state->crtc == crtc) { struct drm_encoder *encoder = connector->encoder; struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder); @@ -401,7 +401,8 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc, dlist_next++; HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel), - (u32 *)vc4_crtc->dlist - (u32 *)vc4->hvs->dlist); + (u32 __iomem *)vc4_crtc->dlist - + (u32 __iomem *)vc4->hvs->dlist); /* Make the next display list start after ours. */ vc4_crtc->dlist_size -= (dlist_next - vc4_crtc->dlist); @@ -591,14 +592,14 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data) * that will take too much. */ primary_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_PRIMARY); - if (!primary_plane) { + if (IS_ERR(primary_plane)) { dev_err(dev, "failed to construct primary plane\n"); ret = PTR_ERR(primary_plane); goto err; } cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR); - if (!cursor_plane) { + if (IS_ERR(cursor_plane)) { dev_err(dev, "failed to construct cursor plane\n"); ret = PTR_ERR(cursor_plane); goto err_primary; diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 6e73060..d5db9e0 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -259,7 +259,6 @@ static struct platform_driver vc4_platform_driver = { .remove = vc4_platform_drm_remove, .driver = { .name = "vc4-drm", - .owner = THIS_MODULE, .of_match_table = vc4_of_match, }, }; diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index ab1673f..8098c5b 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -75,10 +75,10 @@ void vc4_hvs_dump_state(struct drm_device *dev) for (i = 0; i < 64; i += 4) { DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n", i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D", - ((uint32_t *)vc4->hvs->dlist)[i + 0], - ((uint32_t *)vc4->hvs->dlist)[i + 1], - ((uint32_t *)vc4->hvs->dlist)[i + 2], - ((uint32_t *)vc4->hvs->dlist)[i + 3]); + readl((u32 __iomem *)vc4->hvs->dlist + i + 0), + readl((u32 __iomem *)vc4->hvs->dlist + i + 1), + readl((u32 __iomem *)vc4->hvs->dlist + i + 2), + readl((u32 __iomem *)vc4->hvs->dlist + i + 3)); } } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index cdd8b10..887f3ca 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -70,7 +70,7 @@ static bool plane_enabled(struct drm_plane_state *state) return state->fb && state->crtc; } -struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane) +static struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane) { struct vc4_plane_state *vc4_state; @@ -97,8 +97,8 @@ struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane) return &vc4_state->base; } -void vc4_plane_destroy_state(struct drm_plane *plane, - struct drm_plane_state *state) +static void vc4_plane_destroy_state(struct drm_plane *plane, + struct drm_plane_state *state) { struct vc4_plane_state *vc4_state = to_vc4_plane_state(state); @@ -108,7 +108,7 @@ void vc4_plane_destroy_state(struct drm_plane *plane, } /* Called during init to allocate the plane's atomic state. */ -void vc4_plane_reset(struct drm_plane *plane) +static void vc4_plane_reset(struct drm_plane *plane) { struct vc4_plane_state *vc4_state; @@ -157,6 +157,16 @@ static int vc4_plane_mode_set(struct drm_plane *plane, int crtc_w = state->crtc_w; int crtc_h = state->crtc_h; + if (state->crtc_w << 16 != state->src_w || + state->crtc_h << 16 != state->src_h) { + /* We don't support scaling yet, which involves + * allocating the LBM memory for scaling temporary + * storage, and putting filter kernels in the HVS + * context. + */ + return -EINVAL; + } + if (crtc_x < 0) { offset += drm_format_plane_cpp(fb->pixel_format, 0) * -crtc_x; crtc_w += crtc_x; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 8b29949..01a4f05 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2481,7 +2481,7 @@ void wacom_setup_device_quirks(struct wacom *wacom) if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) { if (features->touch_max) features->device_type |= WACOM_DEVICETYPE_TOUCH; - if (features->type >= INTUOSHT || features->type <= BAMBOO_PT) + if (features->type >= INTUOSHT && features->type <= BAMBOO_PT) features->device_type |= WACOM_DEVICETYPE_PAD; features->x_max = 4096; @@ -3213,7 +3213,8 @@ static const struct wacom_features wacom_features_0x32F = WACOM_DTU_OFFSET, WACOM_DTU_OFFSET }; static const struct wacom_features wacom_features_0x336 = { "Wacom DTU1141", 23472, 13203, 1023, 0, - DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 }; + DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4, + WACOM_DTU_OFFSET, WACOM_DTU_OFFSET }; static const struct wacom_features wacom_features_0x57 = { "Wacom DTK2241", 95640, 54060, 2047, 63, DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 6, diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 842b004..8f59f05 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -324,6 +324,7 @@ config SENSORS_APPLESMC config SENSORS_ARM_SCPI tristate "ARM SCPI Sensors" depends on ARM_SCPI_PROTOCOL + depends on THERMAL || !THERMAL_OF help This driver provides support for temperature, voltage, current and power sensors available on ARM Ltd's SCP based platforms. The @@ -1471,6 +1472,7 @@ config SENSORS_INA209 config SENSORS_INA2XX tristate "Texas Instruments INA219 and compatibles" depends on I2C + select REGMAP_I2C help If you say yes here you get support for INA219, INA220, INA226, INA230, and INA231 power monitor chips. diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 1f5e956..0af7fd3 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -537,7 +537,7 @@ static int applesmc_init_index(struct applesmc_registers *s) static int applesmc_init_smcreg_try(void) { struct applesmc_registers *s = &smcreg; - bool left_light_sensor, right_light_sensor; + bool left_light_sensor = 0, right_light_sensor = 0; unsigned int count; u8 tmp[1]; int ret; diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c index 2c1241b..7e20567 100644 --- a/drivers/hwmon/scpi-hwmon.c +++ b/drivers/hwmon/scpi-hwmon.c @@ -117,7 +117,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev) struct scpi_ops *scpi_ops; struct device *hwdev, *dev = &pdev->dev; struct scpi_sensors *scpi_sensors; - int ret; + int ret, idx; scpi_ops = get_scpi_ops(); if (!scpi_ops) @@ -146,8 +146,8 @@ static int scpi_hwmon_probe(struct platform_device *pdev) scpi_sensors->scpi_ops = scpi_ops; - for (i = 0; i < nr_sensors; i++) { - struct sensor_data *sensor = &scpi_sensors->data[i]; + for (i = 0, idx = 0; i < nr_sensors; i++) { + struct sensor_data *sensor = &scpi_sensors->data[idx]; ret = scpi_ops->sensor_get_info(i, &sensor->info); if (ret) @@ -183,7 +183,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev) num_power++; break; default: - break; + continue; } sensor->dev_attr_input.attr.mode = S_IRUGO; @@ -194,11 +194,12 @@ static int scpi_hwmon_probe(struct platform_device *pdev) sensor->dev_attr_label.show = scpi_show_label; sensor->dev_attr_label.attr.name = sensor->label; - scpi_sensors->attrs[i << 1] = &sensor->dev_attr_input.attr; - scpi_sensors->attrs[(i << 1) + 1] = &sensor->dev_attr_label.attr; + scpi_sensors->attrs[idx << 1] = &sensor->dev_attr_input.attr; + scpi_sensors->attrs[(idx << 1) + 1] = &sensor->dev_attr_label.attr; - sysfs_attr_init(scpi_sensors->attrs[i << 1]); - sysfs_attr_init(scpi_sensors->attrs[(i << 1) + 1]); + sysfs_attr_init(scpi_sensors->attrs[idx << 1]); + sysfs_attr_init(scpi_sensors->attrs[(idx << 1) + 1]); + idx++; } scpi_sensors->group.attrs = scpi_sensors->attrs; @@ -236,8 +237,8 @@ static int scpi_hwmon_probe(struct platform_device *pdev) zone->sensor_id = i; zone->scpi_sensors = scpi_sensors; - zone->tzd = thermal_zone_of_sensor_register(dev, i, zone, - &scpi_sensor_ops); + zone->tzd = thermal_zone_of_sensor_register(dev, + sensor->info.sensor_id, zone, &scpi_sensor_ops); /* * The call to thermal_zone_of_sensor_register returns * an error for sensors that are not associated with diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index e24c2b6..7b0aa82 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -126,6 +126,7 @@ config I2C_I801 Sunrise Point-LP (PCH) DNV (SOC) Broxton (SOC) + Lewisburg (PCH) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index c306751..f62d697 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -62,6 +62,8 @@ * Sunrise Point-LP (PCH) 0x9d23 32 hard yes yes yes * DNV (SOC) 0x19df 32 hard yes yes yes * Broxton (SOC) 0x5ad4 32 hard yes yes yes + * Lewisburg (PCH) 0xa1a3 32 hard yes yes yes + * Lewisburg Supersku (PCH) 0xa223 32 hard yes yes yes * * Features supported by this driver: * Software PEC no @@ -206,6 +208,8 @@ #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS 0x9d23 #define PCI_DEVICE_ID_INTEL_DNV_SMBUS 0x19df #define PCI_DEVICE_ID_INTEL_BROXTON_SMBUS 0x5ad4 +#define PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS 0xa1a3 +#define PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS 0xa223 struct i801_mux_config { char *gpio_chip; @@ -869,6 +873,8 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS) }, { 0, } }; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 1e4d99d..9bb0b05 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -50,6 +50,7 @@ #include <linux/of_device.h> #include <linux/of_dma.h> #include <linux/of_gpio.h> +#include <linux/pinctrl/consumer.h> #include <linux/platform_data/i2c-imx.h> #include <linux/platform_device.h> #include <linux/sched.h> diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index e23a7b0..0b20449 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -662,8 +662,10 @@ static void __xiic_start_xfer(struct xiic_i2c *i2c) static void xiic_start_xfer(struct xiic_i2c *i2c) { - + spin_lock(&i2c->lock); + xiic_reinit(i2c); __xiic_start_xfer(i2c); + spin_unlock(&i2c->lock); } static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 040af5c..ba8eb08 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -715,7 +715,7 @@ static int i2c_device_probe(struct device *dev) if (wakeirq > 0 && wakeirq != client->irq) status = dev_pm_set_dedicated_wake_irq(dev, wakeirq); else if (client->irq > 0) - status = dev_pm_set_wake_irq(dev, wakeirq); + status = dev_pm_set_wake_irq(dev, client->irq); else status = 0; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index cbe198c..471ee36 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -216,6 +216,7 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain, u8 *page_addr = (u8 *) (pa & PAGE_MASK); dma_addr_t start_dma_addr = dma_addr; unsigned long irq_flags, nr_pages, i; + unsigned long *entry; int rc = 0; if (dma_addr < s390_domain->domain.geometry.aperture_start || @@ -228,8 +229,12 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain, spin_lock_irqsave(&s390_domain->dma_table_lock, irq_flags); for (i = 0; i < nr_pages; i++) { - dma_update_cpu_trans(s390_domain->dma_table, page_addr, - dma_addr, flags); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + if (!entry) { + rc = -ENOMEM; + goto undo_cpu_trans; + } + dma_update_cpu_trans(entry, page_addr, flags); page_addr += PAGE_SIZE; dma_addr += PAGE_SIZE; } @@ -242,6 +247,20 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain, break; } spin_unlock(&s390_domain->list_lock); + +undo_cpu_trans: + if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { + flags = ZPCI_PTE_INVALID; + while (i-- > 0) { + page_addr -= PAGE_SIZE; + dma_addr -= PAGE_SIZE; + entry = dma_walk_cpu_trans(s390_domain->dma_table, + dma_addr); + if (!entry) + break; + dma_update_cpu_trans(entry, page_addr, flags); + } + } spin_unlock_irqrestore(&s390_domain->dma_table_lock, irq_flags); return rc; diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index 44a077f..f174ce0 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -84,12 +84,15 @@ void __init gic_dist_config(void __iomem *base, int gic_irqs, writel_relaxed(GICD_INT_DEF_PRI_X4, base + GIC_DIST_PRI + i); /* - * Disable all interrupts. Leave the PPI and SGIs alone - * as they are enabled by redistributor registers. + * Deactivate and disable all SPIs. Leave the PPI and SGIs + * alone as they are in the redistributor registers on GICv3. */ - for (i = 32; i < gic_irqs; i += 32) + for (i = 32; i < gic_irqs; i += 32) { writel_relaxed(GICD_INT_EN_CLR_X32, - base + GIC_DIST_ENABLE_CLEAR + i / 8); + base + GIC_DIST_ACTIVE_CLEAR + i / 8); + writel_relaxed(GICD_INT_EN_CLR_X32, + base + GIC_DIST_ENABLE_CLEAR + i / 8); + } if (sync_access) sync_access(); @@ -102,7 +105,9 @@ void gic_cpu_config(void __iomem *base, void (*sync_access)(void)) /* * Deal with the banked PPI and SGI interrupts - disable all * PPI interrupts, ensure all SGI interrupts are enabled. + * Make sure everything is deactivated. */ + writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ACTIVE_CLEAR); writel_relaxed(GICD_INT_EN_CLR_PPI, base + GIC_DIST_ENABLE_CLEAR); writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET); diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 515c823..abf2ffa 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -73,9 +73,11 @@ struct gic_chip_data { union gic_base cpu_base; #ifdef CONFIG_CPU_PM u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)]; + u32 saved_spi_active[DIV_ROUND_UP(1020, 32)]; u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)]; u32 saved_spi_target[DIV_ROUND_UP(1020, 4)]; u32 __percpu *saved_ppi_enable; + u32 __percpu *saved_ppi_active; u32 __percpu *saved_ppi_conf; #endif struct irq_domain *domain; @@ -566,6 +568,10 @@ static void gic_dist_save(unsigned int gic_nr) for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) gic_data[gic_nr].saved_spi_enable[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) + gic_data[gic_nr].saved_spi_active[i] = + readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4); } /* @@ -604,9 +610,19 @@ static void gic_dist_restore(unsigned int gic_nr) writel_relaxed(gic_data[gic_nr].saved_spi_target[i], dist_base + GIC_DIST_TARGET + i * 4); - for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) { + writel_relaxed(GICD_INT_EN_CLR_X32, + dist_base + GIC_DIST_ENABLE_CLEAR + i * 4); writel_relaxed(gic_data[gic_nr].saved_spi_enable[i], dist_base + GIC_DIST_ENABLE_SET + i * 4); + } + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) { + writel_relaxed(GICD_INT_EN_CLR_X32, + dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4); + writel_relaxed(gic_data[gic_nr].saved_spi_active[i], + dist_base + GIC_DIST_ACTIVE_SET + i * 4); + } writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL); } @@ -631,6 +647,10 @@ static void gic_cpu_save(unsigned int gic_nr) for (i = 0; i < DIV_ROUND_UP(32, 32); i++) ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4); + ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_active); + for (i = 0; i < DIV_ROUND_UP(32, 32); i++) + ptr[i] = readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4); + ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf); for (i = 0; i < DIV_ROUND_UP(32, 16); i++) ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4); @@ -654,8 +674,18 @@ static void gic_cpu_restore(unsigned int gic_nr) return; ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable); - for (i = 0; i < DIV_ROUND_UP(32, 32); i++) + for (i = 0; i < DIV_ROUND_UP(32, 32); i++) { + writel_relaxed(GICD_INT_EN_CLR_X32, + dist_base + GIC_DIST_ENABLE_CLEAR + i * 4); writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4); + } + + ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_active); + for (i = 0; i < DIV_ROUND_UP(32, 32); i++) { + writel_relaxed(GICD_INT_EN_CLR_X32, + dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4); + writel_relaxed(ptr[i], dist_base + GIC_DIST_ACTIVE_SET + i * 4); + } ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf); for (i = 0; i < DIV_ROUND_UP(32, 16); i++) @@ -710,6 +740,10 @@ static void __init gic_pm_init(struct gic_chip_data *gic) sizeof(u32)); BUG_ON(!gic->saved_ppi_enable); + gic->saved_ppi_active = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4, + sizeof(u32)); + BUG_ON(!gic->saved_ppi_active); + gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4, sizeof(u32)); BUG_ON(!gic->saved_ppi_conf); diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c index 35759a9..e8f8472 100644 --- a/drivers/media/pci/cx23885/cx23885-core.c +++ b/drivers/media/pci/cx23885/cx23885-core.c @@ -1992,9 +1992,9 @@ static int cx23885_initdev(struct pci_dev *pci_dev, (unsigned long long)pci_resource_start(pci_dev, 0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + err = pci_set_dma_mask(pci_dev, 0xffffffff); + if (err) { printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail_context; } diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c index dbc695f..0042803 100644 --- a/drivers/media/pci/cx25821/cx25821-core.c +++ b/drivers/media/pci/cx25821/cx25821-core.c @@ -1319,7 +1319,8 @@ static int cx25821_initdev(struct pci_dev *pci_dev, dev->pci_lat, (unsigned long long)dev->base_io_addr); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + err = pci_set_dma_mask(pci_dev, 0xffffffff); + if (err) { pr_err("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); err = -EIO; goto fail_irq; diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c index 0ed1b65..1b5268f 100644 --- a/drivers/media/pci/cx88/cx88-alsa.c +++ b/drivers/media/pci/cx88/cx88-alsa.c @@ -890,9 +890,9 @@ static int snd_cx88_create(struct snd_card *card, struct pci_dev *pci, return err; } - if (!pci_set_dma_mask(pci,DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci,DMA_BIT_MASK(32)); + if (err) { dprintk(0, "%s/1: Oops: no 32bit PCI DMA ???\n",core->name); - err = -EIO; cx88_core_put(core, pci); return err; } diff --git a/drivers/media/pci/cx88/cx88-mpeg.c b/drivers/media/pci/cx88/cx88-mpeg.c index 9db7767..f34c229 100644 --- a/drivers/media/pci/cx88/cx88-mpeg.c +++ b/drivers/media/pci/cx88/cx88-mpeg.c @@ -393,7 +393,8 @@ static int cx8802_init_common(struct cx8802_dev *dev) if (pci_enable_device(dev->pci)) return -EIO; pci_set_master(dev->pci); - if (!pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32)); + if (err) { printk("%s/2: Oops: no 32bit PCI DMA ???\n",dev->core->name); return -EIO; } diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index 0de1ad5..aef9acf 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -1314,9 +1314,9 @@ static int cx8800_initdev(struct pci_dev *pci_dev, dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32)); + if (err) { printk("%s/0: Oops: no 32bit PCI DMA ???\n",core->name); - err = -EIO; goto fail_core; } dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev); diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 60b2d46..3fdbd81 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -810,7 +810,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, "%s(): board vendor 0x%x, revision 0x%x\n", __func__, board_vendor, board_revision); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + if (pci_set_dma_mask(pci_dev, 0xffffffff) < 0) { dev_err(&pci_dev->dev, "%s(): 32bit PCI DMA is not supported\n", __func__); goto pci_detect_err; diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c index e79d63e..f720cea 100644 --- a/drivers/media/pci/saa7134/saa7134-core.c +++ b/drivers/media/pci/saa7134/saa7134-core.c @@ -951,9 +951,9 @@ static int saa7134_initdev(struct pci_dev *pci_dev, pci_name(pci_dev), dev->pci_rev, pci_dev->irq, dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); + if (err) { pr_warn("%s: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail1; } diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c index 8f36b48..8bbd092 100644 --- a/drivers/media/pci/saa7164/saa7164-core.c +++ b/drivers/media/pci/saa7164/saa7164-core.c @@ -1264,9 +1264,9 @@ static int saa7164_initdev(struct pci_dev *pci_dev, pci_set_master(pci_dev); /* TODO */ - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + err = pci_set_dma_mask(pci_dev, 0xffffffff); + if (err) { printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail_irq; } diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c index 8c5655d..4e77618 100644 --- a/drivers/media/pci/tw68/tw68-core.c +++ b/drivers/media/pci/tw68/tw68-core.c @@ -257,9 +257,9 @@ static int tw68_initdev(struct pci_dev *pci_dev, dev->name, pci_name(pci_dev), dev->pci_rev, pci_dev->irq, dev->pci_lat, (u64)pci_resource_start(pci_dev, 0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); + if (err) { pr_info("%s: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail1; } diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 23b6c8e..d848616 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -65,8 +65,7 @@ MODULE_ALIAS("mmc:block"); #define MMC_SANITIZE_REQ_TIMEOUT 240000 #define MMC_EXTRACT_INDEX_FROM_ARG(x) ((x & 0x00FF0000) >> 16) -#define mmc_req_rel_wr(req) (((req->cmd_flags & REQ_FUA) || \ - (req->cmd_flags & REQ_META)) && \ +#define mmc_req_rel_wr(req) ((req->cmd_flags & REQ_FUA) && \ (rq_data_dir(req) == WRITE)) #define PACKED_CMD_VER 0x01 #define PACKED_CMD_WR 0x02 @@ -1467,13 +1466,9 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, /* * Reliable writes are used to implement Forced Unit Access and - * REQ_META accesses, and are supported only on MMCs. - * - * XXX: this really needs a good explanation of why REQ_META - * is treated special. + * are supported only on MMCs. */ - bool do_rel_wr = ((req->cmd_flags & REQ_FUA) || - (req->cmd_flags & REQ_META)) && + bool do_rel_wr = (req->cmd_flags & REQ_FUA) && (rq_data_dir(req) == WRITE) && (md->flags & MMC_BLK_REL_WR); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index c793fda..3a9a79e 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1040,9 +1040,24 @@ static int mmc_select_hs_ddr(struct mmc_card *card) return err; } +/* Caller must hold re-tuning */ +static int mmc_switch_status(struct mmc_card *card) +{ + u32 status; + int err; + + err = mmc_send_status(card, &status); + if (err) + return err; + + return mmc_switch_status_error(card->host, status); +} + static int mmc_select_hs400(struct mmc_card *card) { struct mmc_host *host = card->host; + bool send_status = true; + unsigned int max_dtr; int err = 0; u8 val; @@ -1053,25 +1068,36 @@ static int mmc_select_hs400(struct mmc_card *card) host->ios.bus_width == MMC_BUS_WIDTH_8)) return 0; - /* - * Before switching to dual data rate operation for HS400, - * it is required to convert from HS200 mode to HS mode. - */ - mmc_set_timing(card->host, MMC_TIMING_MMC_HS); - mmc_set_bus_speed(card); + if (host->caps & MMC_CAP_WAIT_WHILE_BUSY) + send_status = false; + /* Reduce frequency to HS frequency */ + max_dtr = card->ext_csd.hs_max_dtr; + mmc_set_clock(host, max_dtr); + + /* Switch card to HS mode */ val = EXT_CSD_TIMING_HS | card->drive_strength << EXT_CSD_DRV_STR_SHIFT; err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING, val, card->ext_csd.generic_cmd6_time, - true, true, true); + true, send_status, true); if (err) { pr_err("%s: switch to high-speed from hs200 failed, err:%d\n", mmc_hostname(host), err); return err; } + /* Set host controller to HS timing */ + mmc_set_timing(card->host, MMC_TIMING_MMC_HS); + + if (!send_status) { + err = mmc_switch_status(card); + if (err) + goto out_err; + } + + /* Switch card to DDR */ err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_BUS_WIDTH, EXT_CSD_DDR_BUS_WIDTH_8, @@ -1082,22 +1108,35 @@ static int mmc_select_hs400(struct mmc_card *card) return err; } + /* Switch card to HS400 */ val = EXT_CSD_TIMING_HS400 | card->drive_strength << EXT_CSD_DRV_STR_SHIFT; err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING, val, card->ext_csd.generic_cmd6_time, - true, true, true); + true, send_status, true); if (err) { pr_err("%s: switch to hs400 failed, err:%d\n", mmc_hostname(host), err); return err; } + /* Set host controller to HS400 timing and frequency */ mmc_set_timing(host, MMC_TIMING_MMC_HS400); mmc_set_bus_speed(card); + if (!send_status) { + err = mmc_switch_status(card); + if (err) + goto out_err; + } + return 0; + +out_err: + pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host), + __func__, err); + return err; } int mmc_hs200_to_hs400(struct mmc_card *card) @@ -1105,19 +1144,6 @@ int mmc_hs200_to_hs400(struct mmc_card *card) return mmc_select_hs400(card); } -/* Caller must hold re-tuning */ -static int mmc_switch_status(struct mmc_card *card) -{ - u32 status; - int err; - - err = mmc_send_status(card, &status); - if (err) - return err; - - return mmc_switch_status_error(card->host, status); -} - int mmc_hs400_to_hs200(struct mmc_card *card) { struct mmc_host *host = card->host; @@ -1219,6 +1245,8 @@ static void mmc_select_driver_type(struct mmc_card *card) static int mmc_select_hs200(struct mmc_card *card) { struct mmc_host *host = card->host; + bool send_status = true; + unsigned int old_timing; int err = -EINVAL; u8 val; @@ -1234,6 +1262,9 @@ static int mmc_select_hs200(struct mmc_card *card) mmc_select_driver_type(card); + if (host->caps & MMC_CAP_WAIT_WHILE_BUSY) + send_status = false; + /* * Set the bus width(4 or 8) with host's support and * switch to HS200 mode if bus width is set successfully. @@ -1245,11 +1276,25 @@ static int mmc_select_hs200(struct mmc_card *card) err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING, val, card->ext_csd.generic_cmd6_time, - true, true, true); - if (!err) - mmc_set_timing(host, MMC_TIMING_MMC_HS200); + true, send_status, true); + if (err) + goto err; + old_timing = host->ios.timing; + mmc_set_timing(host, MMC_TIMING_MMC_HS200); + if (!send_status) { + err = mmc_switch_status(card); + /* + * mmc_select_timing() assumes timing has not changed if + * it is a switch error. + */ + if (err == -EBADMSG) + mmc_set_timing(host, old_timing); + } } err: + if (err) + pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host), + __func__, err); return err; } diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index af71de5..1dee533 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -473,6 +473,7 @@ config MMC_DAVINCI config MMC_GOLDFISH tristate "goldfish qemu Multimedia Card Interface support" + depends on HAS_DMA depends on GOLDFISH || COMPILE_TEST help This selects the Goldfish Multimedia card Interface emulation diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 39568cc..33dfd7e 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -1276,7 +1276,7 @@ static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u32 delay) int start = 0, len = 0; int start_final = 0, len_final = 0; u8 final_phase = 0xff; - struct msdc_delay_phase delay_phase; + struct msdc_delay_phase delay_phase = { 0, }; if (delay == 0) { dev_err(host->dev, "phase error: [map:%x]\n", delay); diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 8cadd74..ce08896 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -805,7 +805,7 @@ static int pxamci_probe(struct platform_device *pdev) goto out; } else { mmc->caps |= host->pdata->gpio_card_ro_invert ? - MMC_CAP2_RO_ACTIVE_HIGH : 0; + 0 : MMC_CAP2_RO_ACTIVE_HIGH; } if (gpio_is_valid(gpio_cd)) diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c index dc4e844..5a99a93 100644 --- a/drivers/mtd/nand/jz4740_nand.c +++ b/drivers/mtd/nand/jz4740_nand.c @@ -25,6 +25,7 @@ #include <linux/gpio.h> +#include <asm/mach-jz4740/gpio.h> #include <asm/mach-jz4740/jz4740_nand.h> #define JZ_REG_NAND_CTRL 0x50 diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index cc74142..ece544e 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3110,7 +3110,7 @@ static void nand_resume(struct mtd_info *mtd) */ static void nand_shutdown(struct mtd_info *mtd) { - nand_get_device(mtd, FL_SHUTDOWN); + nand_get_device(mtd, FL_PM_SUSPENDED); } /* Set default functions */ diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 9093577..0527f48 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -15,9 +15,7 @@ #include <linux/netdevice.h> #include <linux/phy.h> #include <net/dsa.h> - -#define REG_PORT(p) (8 + (p)) -#define REG_GLOBAL 0x0f +#include "mv88e6060.h" static int reg_read(struct dsa_switch *ds, int addr, int reg) { @@ -67,13 +65,14 @@ static char *mv88e6060_probe(struct device *host_dev, int sw_addr) if (bus == NULL) return NULL; - ret = mdiobus_read(bus, sw_addr + REG_PORT(0), 0x03); + ret = mdiobus_read(bus, sw_addr + REG_PORT(0), PORT_SWITCH_ID); if (ret >= 0) { - if (ret == 0x0600) + if (ret == PORT_SWITCH_ID_6060) return "Marvell 88E6060 (A0)"; - if (ret == 0x0601 || ret == 0x0602) + if (ret == PORT_SWITCH_ID_6060_R1 || + ret == PORT_SWITCH_ID_6060_R2) return "Marvell 88E6060 (B0)"; - if ((ret & 0xfff0) == 0x0600) + if ((ret & PORT_SWITCH_ID_6060_MASK) == PORT_SWITCH_ID_6060) return "Marvell 88E6060"; } @@ -87,22 +86,26 @@ static int mv88e6060_switch_reset(struct dsa_switch *ds) unsigned long timeout; /* Set all ports to the disabled state. */ - for (i = 0; i < 6; i++) { - ret = REG_READ(REG_PORT(i), 0x04); - REG_WRITE(REG_PORT(i), 0x04, ret & 0xfffc); + for (i = 0; i < MV88E6060_PORTS; i++) { + ret = REG_READ(REG_PORT(i), PORT_CONTROL); + REG_WRITE(REG_PORT(i), PORT_CONTROL, + ret & ~PORT_CONTROL_STATE_MASK); } /* Wait for transmit queues to drain. */ usleep_range(2000, 4000); /* Reset the switch. */ - REG_WRITE(REG_GLOBAL, 0x0a, 0xa130); + REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_SWRESET | + GLOBAL_ATU_CONTROL_ATUSIZE_1024 | + GLOBAL_ATU_CONTROL_ATE_AGE_5MIN); /* Wait up to one second for reset to complete. */ timeout = jiffies + 1 * HZ; while (time_before(jiffies, timeout)) { - ret = REG_READ(REG_GLOBAL, 0x00); - if ((ret & 0x8000) == 0x0000) + ret = REG_READ(REG_GLOBAL, GLOBAL_STATUS); + if (ret & GLOBAL_STATUS_INIT_READY) break; usleep_range(1000, 2000); @@ -119,13 +122,15 @@ static int mv88e6060_setup_global(struct dsa_switch *ds) * set the maximum frame size to 1536 bytes, and mask all * interrupt sources. */ - REG_WRITE(REG_GLOBAL, 0x04, 0x0800); + REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL, GLOBAL_CONTROL_MAX_FRAME_1536); /* Enable automatic address learning, set the address * database size to 1024 entries, and set the default aging * time to 5 minutes. */ - REG_WRITE(REG_GLOBAL, 0x0a, 0x2130); + REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL, + GLOBAL_ATU_CONTROL_ATUSIZE_1024 | + GLOBAL_ATU_CONTROL_ATE_AGE_5MIN); return 0; } @@ -139,25 +144,30 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) * state to Forwarding. Additionally, if this is the CPU * port, enable Ingress and Egress Trailer tagging mode. */ - REG_WRITE(addr, 0x04, dsa_is_cpu_port(ds, p) ? 0x4103 : 0x0003); + REG_WRITE(addr, PORT_CONTROL, + dsa_is_cpu_port(ds, p) ? + PORT_CONTROL_TRAILER | + PORT_CONTROL_INGRESS_MODE | + PORT_CONTROL_STATE_FORWARDING : + PORT_CONTROL_STATE_FORWARDING); /* Port based VLAN map: give each port its own address * database, allow the CPU port to talk to each of the 'real' * ports, and allow each of the 'real' ports to only talk to * the CPU port. */ - REG_WRITE(addr, 0x06, - ((p & 0xf) << 12) | - (dsa_is_cpu_port(ds, p) ? - ds->phys_port_mask : - (1 << ds->dst->cpu_port))); + REG_WRITE(addr, PORT_VLAN_MAP, + ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | + (dsa_is_cpu_port(ds, p) ? + ds->phys_port_mask : + BIT(ds->dst->cpu_port))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using * a port bitmap that has only the bit for this port set and * the other bits clear. */ - REG_WRITE(addr, 0x0b, 1 << p); + REG_WRITE(addr, PORT_ASSOC_VECTOR, BIT(p)); return 0; } @@ -177,7 +187,7 @@ static int mv88e6060_setup(struct dsa_switch *ds) if (ret < 0) return ret; - for (i = 0; i < 6; i++) { + for (i = 0; i < MV88E6060_PORTS; i++) { ret = mv88e6060_setup_port(ds, i); if (ret < 0) return ret; @@ -188,16 +198,17 @@ static int mv88e6060_setup(struct dsa_switch *ds) static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr) { - REG_WRITE(REG_GLOBAL, 0x01, (addr[0] << 8) | addr[1]); - REG_WRITE(REG_GLOBAL, 0x02, (addr[2] << 8) | addr[3]); - REG_WRITE(REG_GLOBAL, 0x03, (addr[4] << 8) | addr[5]); + /* Use the same MAC Address as FD Pause frames for all ports */ + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); return 0; } static int mv88e6060_port_to_phy_addr(int port) { - if (port >= 0 && port <= 5) + if (port >= 0 && port < MV88E6060_PORTS) return port; return -1; } @@ -225,54 +236,6 @@ mv88e6060_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) return reg_write(ds, addr, regnum, val); } -static void mv88e6060_poll_link(struct dsa_switch *ds) -{ - int i; - - for (i = 0; i < DSA_MAX_PORTS; i++) { - struct net_device *dev; - int uninitialized_var(port_status); - int link; - int speed; - int duplex; - int fc; - - dev = ds->ports[i]; - if (dev == NULL) - continue; - - link = 0; - if (dev->flags & IFF_UP) { - port_status = reg_read(ds, REG_PORT(i), 0x00); - if (port_status < 0) - continue; - - link = !!(port_status & 0x1000); - } - - if (!link) { - if (netif_carrier_ok(dev)) { - netdev_info(dev, "link down\n"); - netif_carrier_off(dev); - } - continue; - } - - speed = (port_status & 0x0100) ? 100 : 10; - duplex = (port_status & 0x0200) ? 1 : 0; - fc = ((port_status & 0xc000) == 0xc000) ? 1 : 0; - - if (!netif_carrier_ok(dev)) { - netdev_info(dev, - "link up, %d Mb/s, %s duplex, flow control %sabled\n", - speed, - duplex ? "full" : "half", - fc ? "en" : "dis"); - netif_carrier_on(dev); - } - } -} - static struct dsa_switch_driver mv88e6060_switch_driver = { .tag_protocol = DSA_TAG_PROTO_TRAILER, .probe = mv88e6060_probe, @@ -280,7 +243,6 @@ static struct dsa_switch_driver mv88e6060_switch_driver = { .set_addr = mv88e6060_set_addr, .phy_read = mv88e6060_phy_read, .phy_write = mv88e6060_phy_write, - .poll_link = mv88e6060_poll_link, }; static int __init mv88e6060_init(void) diff --git a/drivers/net/dsa/mv88e6060.h b/drivers/net/dsa/mv88e6060.h new file mode 100644 index 0000000..cc9b2ed --- /dev/null +++ b/drivers/net/dsa/mv88e6060.h @@ -0,0 +1,111 @@ +/* + * drivers/net/dsa/mv88e6060.h - Marvell 88e6060 switch chip support + * Copyright (c) 2015 Neil Armstrong + * + * Based on mv88e6xxx.h + * Copyright (c) 2008 Marvell Semiconductor + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __MV88E6060_H +#define __MV88E6060_H + +#define MV88E6060_PORTS 6 + +#define REG_PORT(p) (0x8 + (p)) +#define PORT_STATUS 0x00 +#define PORT_STATUS_PAUSE_EN BIT(15) +#define PORT_STATUS_MY_PAUSE BIT(14) +#define PORT_STATUS_FC (PORT_STATUS_MY_PAUSE | PORT_STATUS_PAUSE_EN) +#define PORT_STATUS_RESOLVED BIT(13) +#define PORT_STATUS_LINK BIT(12) +#define PORT_STATUS_PORTMODE BIT(11) +#define PORT_STATUS_PHYMODE BIT(10) +#define PORT_STATUS_DUPLEX BIT(9) +#define PORT_STATUS_SPEED BIT(8) +#define PORT_SWITCH_ID 0x03 +#define PORT_SWITCH_ID_6060 0x0600 +#define PORT_SWITCH_ID_6060_MASK 0xfff0 +#define PORT_SWITCH_ID_6060_R1 0x0601 +#define PORT_SWITCH_ID_6060_R2 0x0602 +#define PORT_CONTROL 0x04 +#define PORT_CONTROL_FORCE_FLOW_CTRL BIT(15) +#define PORT_CONTROL_TRAILER BIT(14) +#define PORT_CONTROL_HEADER BIT(11) +#define PORT_CONTROL_INGRESS_MODE BIT(8) +#define PORT_CONTROL_VLAN_TUNNEL BIT(7) +#define PORT_CONTROL_STATE_MASK 0x03 +#define PORT_CONTROL_STATE_DISABLED 0x00 +#define PORT_CONTROL_STATE_BLOCKING 0x01 +#define PORT_CONTROL_STATE_LEARNING 0x02 +#define PORT_CONTROL_STATE_FORWARDING 0x03 +#define PORT_VLAN_MAP 0x06 +#define PORT_VLAN_MAP_DBNUM_SHIFT 12 +#define PORT_VLAN_MAP_TABLE_MASK 0x1f +#define PORT_ASSOC_VECTOR 0x0b +#define PORT_ASSOC_VECTOR_MONITOR BIT(15) +#define PORT_ASSOC_VECTOR_PAV_MASK 0x1f +#define PORT_RX_CNTR 0x10 +#define PORT_TX_CNTR 0x11 + +#define REG_GLOBAL 0x0f +#define GLOBAL_STATUS 0x00 +#define GLOBAL_STATUS_SW_MODE_MASK (0x3 << 12) +#define GLOBAL_STATUS_SW_MODE_0 (0x0 << 12) +#define GLOBAL_STATUS_SW_MODE_1 (0x1 << 12) +#define GLOBAL_STATUS_SW_MODE_2 (0x2 << 12) +#define GLOBAL_STATUS_SW_MODE_3 (0x3 << 12) +#define GLOBAL_STATUS_INIT_READY BIT(11) +#define GLOBAL_STATUS_ATU_FULL BIT(3) +#define GLOBAL_STATUS_ATU_DONE BIT(2) +#define GLOBAL_STATUS_PHY_INT BIT(1) +#define GLOBAL_STATUS_EEINT BIT(0) +#define GLOBAL_MAC_01 0x01 +#define GLOBAL_MAC_01_DIFF_ADDR BIT(8) +#define GLOBAL_MAC_23 0x02 +#define GLOBAL_MAC_45 0x03 +#define GLOBAL_CONTROL 0x04 +#define GLOBAL_CONTROL_DISCARD_EXCESS BIT(13) +#define GLOBAL_CONTROL_MAX_FRAME_1536 BIT(10) +#define GLOBAL_CONTROL_RELOAD_EEPROM BIT(9) +#define GLOBAL_CONTROL_CTRMODE BIT(8) +#define GLOBAL_CONTROL_ATU_FULL_EN BIT(3) +#define GLOBAL_CONTROL_ATU_DONE_EN BIT(2) +#define GLOBAL_CONTROL_PHYINT_EN BIT(1) +#define GLOBAL_CONTROL_EEPROM_DONE_EN BIT(0) +#define GLOBAL_ATU_CONTROL 0x0a +#define GLOBAL_ATU_CONTROL_SWRESET BIT(15) +#define GLOBAL_ATU_CONTROL_LEARNDIS BIT(14) +#define GLOBAL_ATU_CONTROL_ATUSIZE_256 (0x0 << 12) +#define GLOBAL_ATU_CONTROL_ATUSIZE_512 (0x1 << 12) +#define GLOBAL_ATU_CONTROL_ATUSIZE_1024 (0x2 << 12) +#define GLOBAL_ATU_CONTROL_ATE_AGE_SHIFT 4 +#define GLOBAL_ATU_CONTROL_ATE_AGE_MASK (0xff << 4) +#define GLOBAL_ATU_CONTROL_ATE_AGE_5MIN (0x13 << 4) +#define GLOBAL_ATU_OP 0x0b +#define GLOBAL_ATU_OP_BUSY BIT(15) +#define GLOBAL_ATU_OP_NOP (0 << 12) +#define GLOBAL_ATU_OP_FLUSH_ALL ((1 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_UNLOCKED ((2 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_LOAD_DB ((3 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_GET_NEXT_DB ((4 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_DB ((5 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_UNLOCKED_DB ((6 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_DATA 0x0c +#define GLOBAL_ATU_DATA_PORT_VECTOR_MASK 0x3f0 +#define GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT 4 +#define GLOBAL_ATU_DATA_STATE_MASK 0x0f +#define GLOBAL_ATU_DATA_STATE_UNUSED 0x00 +#define GLOBAL_ATU_DATA_STATE_UC_STATIC 0x0e +#define GLOBAL_ATU_DATA_STATE_UC_LOCKED 0x0f +#define GLOBAL_ATU_DATA_STATE_MC_STATIC 0x07 +#define GLOBAL_ATU_DATA_STATE_MC_LOCKED 0x0e +#define GLOBAL_ATU_MAC_01 0x0d +#define GLOBAL_ATU_MAC_23 0x0e +#define GLOBAL_ATU_MAC_45 0x0f + +#endif diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 05aa759..955d06b 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -78,7 +78,6 @@ source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" -source "drivers/net/ethernet/icplus/Kconfig" config JME tristate "JMicron(R) PCI-Express Gigabit Ethernet support" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index ddfc808..4a2ee98 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -41,7 +41,6 @@ obj-$(CONFIG_NET_VENDOR_IBM) += ibm/ obj-$(CONFIG_NET_VENDOR_INTEL) += intel/ obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/ obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/ -obj-$(CONFIG_IP1000) += icplus/ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_KORINA) += korina.o obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index e2afabf..7ccebae 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1500,10 +1500,11 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } - if (!pci_set_dma_mask(pdev, PCNET32_DMA_MASK)) { + err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK); + if (err) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("architecture does not support 32bit PCI busmaster DMA\n"); - return -ENODEV; + return err; } if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) { if (pcnet32_debug & NETIF_MSG_PROBE) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index f1d62d5..c9b0367 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13207,7 +13207,7 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, /* VF with OLD Hypervisor or old PF do not support filtering */ if (IS_PF(bp)) { - if (CHIP_IS_E1x(bp)) + if (chip_is_e1x) bp->accept_any_vlan = true; else dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index f683d97..b895044 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -560,7 +560,7 @@ static int liquidio_resume(struct pci_dev *pdev) #endif /* For PCI-E Advanced Error Recovery (AER) Interface */ -static struct pci_error_handlers liquidio_err_handler = { +static const struct pci_error_handlers liquidio_err_handler = { .error_detected = liquidio_pcie_error_detected, .mmio_enabled = liquidio_pcie_mmio_enabled, .slot_reset = liquidio_pcie_slot_reset, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index a937772..7f709cb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1583,8 +1583,14 @@ err_disable_device: static void nicvf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct nicvf *nic = netdev_priv(netdev); - struct net_device *pnetdev = nic->pnicvf->netdev; + struct nicvf *nic; + struct net_device *pnetdev; + + if (!netdev) + return; + + nic = netdev_priv(netdev); + pnetdev = nic->pnicvf->netdev; /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig index f6e858d..ebdc832 100644 --- a/drivers/net/ethernet/dlink/Kconfig +++ b/drivers/net/ethernet/dlink/Kconfig @@ -17,15 +17,16 @@ config NET_VENDOR_DLINK if NET_VENDOR_DLINK config DL2K - tristate "DL2000/TC902x-based Gigabit Ethernet support" + tristate "DL2000/TC902x/IP1000A-based Gigabit Ethernet support" depends on PCI select CRC32 ---help--- - This driver supports DL2000/TC902x-based Gigabit ethernet cards, + This driver supports DL2000/TC902x/IP1000A-based Gigabit ethernet cards, which includes D-Link DGE-550T Gigabit Ethernet Adapter. D-Link DL2000-based Gigabit Ethernet Adapter. Sundance/Tamarack TC902x Gigabit Ethernet Adapter. + ICPlus IP1000A-based cards To compile this driver as a module, choose M here: the module will be called dl2k. diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index cf0a5fc..ccca479 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -253,6 +253,19 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_out_unmap_rx; + if (np->chip_id == CHIP_IP1000A && + (np->pdev->revision == 0x40 || np->pdev->revision == 0x41)) { + /* PHY magic taken from ipg driver, undocumented registers */ + mii_write(dev, np->phy_addr, 31, 0x0001); + mii_write(dev, np->phy_addr, 27, 0x01e0); + mii_write(dev, np->phy_addr, 31, 0x0002); + mii_write(dev, np->phy_addr, 27, 0xeb8e); + mii_write(dev, np->phy_addr, 31, 0x0000); + mii_write(dev, np->phy_addr, 30, 0x005e); + /* advertise 1000BASE-T half & full duplex, prefer MASTER */ + mii_write(dev, np->phy_addr, MII_CTRL1000, 0x0700); + } + /* Fiber device? */ np->phy_media = (dr16(ASICCtrl) & PhyMedia) ? 1 : 0; np->link_status = 0; @@ -361,6 +374,11 @@ parse_eeprom (struct net_device *dev) for (i = 0; i < 6; i++) dev->dev_addr[i] = psrom->mac_addr[i]; + if (np->chip_id == CHIP_IP1000A) { + np->led_mode = psrom->led_mode; + return 0; + } + if (np->pdev->vendor != PCI_VENDOR_ID_DLINK) { return 0; } @@ -406,6 +424,28 @@ parse_eeprom (struct net_device *dev) return 0; } +static void rio_set_led_mode(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->ioaddr; + u32 mode; + + if (np->chip_id != CHIP_IP1000A) + return; + + mode = dr32(ASICCtrl); + mode &= ~(IPG_AC_LED_MODE_BIT_1 | IPG_AC_LED_MODE | IPG_AC_LED_SPEED); + + if (np->led_mode & 0x01) + mode |= IPG_AC_LED_MODE; + if (np->led_mode & 0x02) + mode |= IPG_AC_LED_MODE_BIT_1; + if (np->led_mode & 0x08) + mode |= IPG_AC_LED_SPEED; + + dw32(ASICCtrl, mode); +} + static int rio_open (struct net_device *dev) { @@ -424,6 +464,8 @@ rio_open (struct net_device *dev) GlobalReset | DMAReset | FIFOReset | NetworkReset | HostReset); mdelay(10); + rio_set_led_mode(dev); + /* DebugCtrl bit 4, 5, 9 must set */ dw32(DebugCtrl, dr32(DebugCtrl) | 0x0230); @@ -433,9 +475,13 @@ rio_open (struct net_device *dev) alloc_list (dev); - /* Get station address */ - for (i = 0; i < 6; i++) - dw8(StationAddr0 + i, dev->dev_addr[i]); + /* Set station address */ + /* 16 or 32-bit access is required by TC9020 datasheet but 8-bit works + * too. However, it doesn't work on IP1000A so we use 16-bit access. + */ + for (i = 0; i < 3; i++) + dw16(StationAddr0 + 2 * i, + cpu_to_le16(((u16 *)dev->dev_addr)[i])); set_multicast (dev); if (np->coalesce) { @@ -780,6 +826,7 @@ tx_error (struct net_device *dev, int tx_status) break; mdelay (1); } + rio_set_led_mode(dev); rio_free_tx (dev, 1); /* Reset TFDListPtr */ dw32(TFDListPtr0, np->tx_ring_dma + @@ -799,6 +846,7 @@ tx_error (struct net_device *dev, int tx_status) break; mdelay (1); } + rio_set_led_mode(dev); /* Let TxStartThresh stay default value */ } /* Maximum Collisions */ @@ -965,6 +1013,7 @@ rio_error (struct net_device *dev, int int_status) dev->name, int_status); dw16(ASICCtrl + 2, GlobalReset | HostReset); mdelay (500); + rio_set_led_mode(dev); } } diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h index 23c07b0..8f4f612 100644 --- a/drivers/net/ethernet/dlink/dl2k.h +++ b/drivers/net/ethernet/dlink/dl2k.h @@ -211,6 +211,10 @@ enum ASICCtrl_HiWord_bits { ResetBusy = 0x0400, }; +#define IPG_AC_LED_MODE BIT(14) +#define IPG_AC_LED_SPEED BIT(27) +#define IPG_AC_LED_MODE_BIT_1 BIT(29) + /* Transmit Frame Control bits */ enum TFC_bits { DwordAlign = 0x00000000, @@ -332,7 +336,10 @@ typedef struct t_SROM { u16 asic_ctrl; /* 0x02 */ u16 sub_vendor_id; /* 0x04 */ u16 sub_system_id; /* 0x06 */ - u16 reserved1[12]; /* 0x08-0x1f */ + u16 pci_base_1; /* 0x08 (IP1000A only) */ + u16 pci_base_2; /* 0x0a (IP1000A only) */ + u16 led_mode; /* 0x0c (IP1000A only) */ + u16 reserved1[9]; /* 0x0e-0x1f */ u8 mac_addr[6]; /* 0x20-0x25 */ u8 reserved2[10]; /* 0x26-0x2f */ u8 sib[204]; /* 0x30-0xfb */ @@ -397,6 +404,7 @@ struct netdev_private { u16 advertising; /* NWay media advertisement */ u16 negotiate; /* Negotiated media */ int phy_addr; /* PHY addresses. */ + u16 led_mode; /* LED mode read from EEPROM (IP1000A only) */ }; /* The station address location in the EEPROM. */ @@ -407,10 +415,15 @@ struct netdev_private { class_mask of the class are honored during the comparison. driver_data Data private to the driver. */ +#define CHIP_IP1000A 1 static const struct pci_device_id rio_pci_tbl[] = { {0x1186, 0x4000, PCI_ANY_ID, PCI_ANY_ID, }, {0x13f0, 0x1021, PCI_ANY_ID, PCI_ANY_ID, }, + { PCI_VDEVICE(SUNDANCE, 0x1023), CHIP_IP1000A }, + { PCI_VDEVICE(SUNDANCE, 0x2021), CHIP_IP1000A }, + { PCI_VDEVICE(DLINK, 0x9021), CHIP_IP1000A }, + { PCI_VDEVICE(DLINK, 0x4020), CHIP_IP1000A }, { } }; MODULE_DEVICE_TABLE (pci, rio_pci_tbl); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index f4cb8e4..734f655 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -1062,9 +1062,7 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, static int be_set_rss_hash_opts(struct be_adapter *adapter, struct ethtool_rxnfc *cmd) { - struct be_rx_obj *rxo; - int status = 0, i, j; - u8 rsstable[128]; + int status; u32 rss_flags = adapter->rss_info.rss_flags; if (cmd->data != L3_RSS_FLAGS && @@ -1113,20 +1111,11 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter, } if (rss_flags == adapter->rss_info.rss_flags) - return status; - - if (be_multi_rxq(adapter)) { - for (j = 0; j < 128; j += adapter->num_rss_qs) { - for_all_rss_queues(adapter, rxo, i) { - if ((j + i) >= 128) - break; - rsstable[j + i] = rxo->rss_id; - } - } - } + return 0; status = be_cmd_rss_config(adapter, adapter->rss_info.rsstable, - rss_flags, 128, adapter->rss_info.rss_hkey); + rss_flags, RSS_INDIR_TABLE_LEN, + adapter->rss_info.rss_hkey); if (!status) adapter->rss_info.rss_flags = rss_flags; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index eb48a97..b6ad029 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3518,7 +3518,7 @@ static int be_rx_qs_create(struct be_adapter *adapter) netdev_rss_key_fill(rss_key, RSS_HASH_KEY_LEN); rc = be_cmd_rss_config(adapter, rss->rsstable, rss->rss_flags, - 128, rss_key); + RSS_INDIR_TABLE_LEN, rss_key); if (rc) { rss->rss_flags = RSS_ENABLE_NONE; return rc; diff --git a/drivers/net/ethernet/icplus/Kconfig b/drivers/net/ethernet/icplus/Kconfig deleted file mode 100644 index 14a66e9..0000000 --- a/drivers/net/ethernet/icplus/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# -# IC Plus device configuration -# - -config IP1000 - tristate "IP1000 Gigabit Ethernet support" - depends on PCI - select MII - ---help--- - This driver supports IP1000 gigabit Ethernet cards. - - To compile this driver as a module, choose M here: the module - will be called ipg. This is recommended. diff --git a/drivers/net/ethernet/icplus/Makefile b/drivers/net/ethernet/icplus/Makefile deleted file mode 100644 index 5bc87c1..0000000 --- a/drivers/net/ethernet/icplus/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# -# Makefile for the IC Plus device drivers -# - -obj-$(CONFIG_IP1000) += ipg.o diff --git a/drivers/net/ethernet/icplus/ipg.c b/drivers/net/ethernet/icplus/ipg.c deleted file mode 100644 index c3b6af8..0000000 --- a/drivers/net/ethernet/icplus/ipg.c +++ /dev/null @@ -1,2300 +0,0 @@ -/* - * ipg.c: Device Driver for the IP1000 Gigabit Ethernet Adapter - * - * Copyright (C) 2003, 2007 IC Plus Corp - * - * Original Author: - * - * Craig Rich - * Sundance Technology, Inc. - * www.sundanceti.com - * craig_rich@sundanceti.com - * - * Current Maintainer: - * - * Sorbica Shieh. - * http://www.icplus.com.tw - * sorbica@icplus.com.tw - * - * Jesse Huang - * http://www.icplus.com.tw - * jesse@icplus.com.tw - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/crc32.h> -#include <linux/ethtool.h> -#include <linux/interrupt.h> -#include <linux/gfp.h> -#include <linux/mii.h> -#include <linux/mutex.h> - -#include <asm/div64.h> - -#define IPG_RX_RING_BYTES (sizeof(struct ipg_rx) * IPG_RFDLIST_LENGTH) -#define IPG_TX_RING_BYTES (sizeof(struct ipg_tx) * IPG_TFDLIST_LENGTH) -#define IPG_RESET_MASK \ - (IPG_AC_GLOBAL_RESET | IPG_AC_RX_RESET | IPG_AC_TX_RESET | \ - IPG_AC_DMA | IPG_AC_FIFO | IPG_AC_NETWORK | IPG_AC_HOST | \ - IPG_AC_AUTO_INIT) - -#define ipg_w32(val32, reg) iowrite32((val32), ioaddr + (reg)) -#define ipg_w16(val16, reg) iowrite16((val16), ioaddr + (reg)) -#define ipg_w8(val8, reg) iowrite8((val8), ioaddr + (reg)) - -#define ipg_r32(reg) ioread32(ioaddr + (reg)) -#define ipg_r16(reg) ioread16(ioaddr + (reg)) -#define ipg_r8(reg) ioread8(ioaddr + (reg)) - -enum { - netdev_io_size = 128 -}; - -#include "ipg.h" -#define DRV_NAME "ipg" - -MODULE_AUTHOR("IC Plus Corp. 2003"); -MODULE_DESCRIPTION("IC Plus IP1000 Gigabit Ethernet Adapter Linux Driver"); -MODULE_LICENSE("GPL"); - -/* - * Defaults - */ -#define IPG_MAX_RXFRAME_SIZE 0x0600 -#define IPG_RXFRAG_SIZE 0x0600 -#define IPG_RXSUPPORT_SIZE 0x0600 -#define IPG_IS_JUMBO false - -/* - * Variable record -- index by leading revision/length - * Revision/Length(=N*4), Address1, Data1, Address2, Data2,...,AddressN,DataN - */ -static const unsigned short DefaultPhyParam[] = { - /* 11/12/03 IP1000A v1-3 rev=0x40 */ - /*-------------------------------------------------------------------------- - (0x4000|(15*4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 22, 0x85bd, 24, 0xfff2, - 27, 0x0c10, 28, 0x0c10, 29, 0x2c10, 31, 0x0003, 23, 0x92f6, - 31, 0x0000, 23, 0x003d, 30, 0x00de, 20, 0x20e7, 9, 0x0700, - --------------------------------------------------------------------------*/ - /* 12/17/03 IP1000A v1-4 rev=0x40 */ - (0x4000 | (07 * 4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 27, 0xeb8e, 31, - 0x0000, - 30, 0x005e, 9, 0x0700, - /* 01/09/04 IP1000A v1-5 rev=0x41 */ - (0x4100 | (07 * 4)), 31, 0x0001, 27, 0x01e0, 31, 0x0002, 27, 0xeb8e, 31, - 0x0000, - 30, 0x005e, 9, 0x0700, - 0x0000 -}; - -static const char * const ipg_brand_name[] = { - "IC PLUS IP1000 1000/100/10 based NIC", - "Sundance Technology ST2021 based NIC", - "Tamarack Microelectronics TC9020/9021 based NIC", - "D-Link NIC IP1000A" -}; - -static const struct pci_device_id ipg_pci_tbl[] = { - { PCI_VDEVICE(SUNDANCE, 0x1023), 0 }, - { PCI_VDEVICE(SUNDANCE, 0x2021), 1 }, - { PCI_VDEVICE(DLINK, 0x9021), 2 }, - { PCI_VDEVICE(DLINK, 0x4020), 3 }, - { 0, } -}; - -MODULE_DEVICE_TABLE(pci, ipg_pci_tbl); - -static inline void __iomem *ipg_ioaddr(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - return sp->ioaddr; -} - -#ifdef IPG_DEBUG -static void ipg_dump_rfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - u32 offset; - - IPG_DEBUG_MSG("_dump_rfdlist\n"); - - netdev_info(dev, "rx_current = %02x\n", sp->rx_current); - netdev_info(dev, "rx_dirty = %02x\n", sp->rx_dirty); - netdev_info(dev, "RFDList start address = %016lx\n", - (unsigned long)sp->rxd_map); - netdev_info(dev, "RFDListPtr register = %08x%08x\n", - ipg_r32(IPG_RFDLISTPTR1), ipg_r32(IPG_RFDLISTPTR0)); - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - offset = (u32) &sp->rxd[i].next_desc - (u32) sp->rxd; - netdev_info(dev, "%02x %04x RFDNextPtr = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].next_desc); - offset = (u32) &sp->rxd[i].rfs - (u32) sp->rxd; - netdev_info(dev, "%02x %04x RFS = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].rfs); - offset = (u32) &sp->rxd[i].frag_info - (u32) sp->rxd; - netdev_info(dev, "%02x %04x frag_info = %016lx\n", - i, offset, (unsigned long)sp->rxd[i].frag_info); - } -} - -static void ipg_dump_tfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - u32 offset; - - IPG_DEBUG_MSG("_dump_tfdlist\n"); - - netdev_info(dev, "tx_current = %02x\n", sp->tx_current); - netdev_info(dev, "tx_dirty = %02x\n", sp->tx_dirty); - netdev_info(dev, "TFDList start address = %016lx\n", - (unsigned long) sp->txd_map); - netdev_info(dev, "TFDListPtr register = %08x%08x\n", - ipg_r32(IPG_TFDLISTPTR1), ipg_r32(IPG_TFDLISTPTR0)); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - offset = (u32) &sp->txd[i].next_desc - (u32) sp->txd; - netdev_info(dev, "%02x %04x TFDNextPtr = %016lx\n", - i, offset, (unsigned long)sp->txd[i].next_desc); - - offset = (u32) &sp->txd[i].tfc - (u32) sp->txd; - netdev_info(dev, "%02x %04x TFC = %016lx\n", - i, offset, (unsigned long) sp->txd[i].tfc); - offset = (u32) &sp->txd[i].frag_info - (u32) sp->txd; - netdev_info(dev, "%02x %04x frag_info = %016lx\n", - i, offset, (unsigned long) sp->txd[i].frag_info); - } -} -#endif - -static void ipg_write_phy_ctl(void __iomem *ioaddr, u8 data) -{ - ipg_w8(IPG_PC_RSVD_MASK & data, PHY_CTRL); - ndelay(IPG_PC_PHYCTRLWAIT_NS); -} - -static void ipg_drive_phy_ctl_low_high(void __iomem *ioaddr, u8 data) -{ - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | data); - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | data); -} - -static void send_three_state(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - phyctrlpolarity |= (IPG_PC_MGMTDATA & 0) | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, phyctrlpolarity); -} - -static void send_end(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - ipg_w8((IPG_PC_MGMTCLK_LO | (IPG_PC_MGMTDATA & 0) | IPG_PC_MGMTDIR | - phyctrlpolarity) & IPG_PC_RSVD_MASK, PHY_CTRL); -} - -static u16 read_phy_bit(void __iomem *ioaddr, u8 phyctrlpolarity) -{ - u16 bit_data; - - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | phyctrlpolarity); - - bit_data = ((ipg_r8(PHY_CTRL) & IPG_PC_MGMTDATA) >> 1) & 1; - - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | phyctrlpolarity); - - return bit_data; -} - -/* - * Read a register from the Physical Layer device located - * on the IPG NIC, using the IPG PHYCTRL register. - */ -static int mdio_read(struct net_device *dev, int phy_id, int phy_reg) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - /* - * The GMII mangement frame structure for a read is as follows: - * - * |Preamble|st|op|phyad|regad|ta| data |idle| - * |< 32 1s>|01|10|AAAAA|RRRRR|z0|DDDDDDDDDDDDDDDD|z | - * - * <32 1s> = 32 consecutive logic 1 values - * A = bit of Physical Layer device address (MSB first) - * R = bit of register address (MSB first) - * z = High impedance state - * D = bit of read data (MSB first) - * - * Transmission order is 'Preamble' field first, bits transmitted - * left to right (first to last). - */ - struct { - u32 field; - unsigned int len; - } p[] = { - { GMII_PREAMBLE, 32 }, /* Preamble */ - { GMII_ST, 2 }, /* ST */ - { GMII_READ, 2 }, /* OP */ - { phy_id, 5 }, /* PHYAD */ - { phy_reg, 5 }, /* REGAD */ - { 0x0000, 2 }, /* TA */ - { 0x0000, 16 }, /* DATA */ - { 0x0000, 1 } /* IDLE */ - }; - unsigned int i, j; - u8 polarity, data; - - polarity = ipg_r8(PHY_CTRL); - polarity &= (IPG_PC_DUPLEX_POLARITY | IPG_PC_LINK_POLARITY); - - /* Create the Preamble, ST, OP, PHYAD, and REGAD field. */ - for (j = 0; j < 5; j++) { - for (i = 0; i < p[j].len; i++) { - /* For each variable length field, the MSB must be - * transmitted first. Rotate through the field bits, - * starting with the MSB, and move each bit into the - * the 1st (2^1) bit position (this is the bit position - * corresponding to the MgmtData bit of the PhyCtrl - * register for the IPG). - * - * Example: ST = 01; - * - * First write a '0' to bit 1 of the PhyCtrl - * register, then write a '1' to bit 1 of the - * PhyCtrl register. - * - * To do this, right shift the MSB of ST by the value: - * [field length - 1 - #ST bits already written] - * then left shift this result by 1. - */ - data = (p[j].field >> (p[j].len - 1 - i)) << 1; - data &= IPG_PC_MGMTDATA; - data |= polarity | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, data); - } - } - - send_three_state(ioaddr, polarity); - - read_phy_bit(ioaddr, polarity); - - /* - * For a read cycle, the bits for the next two fields (TA and - * DATA) are driven by the PHY (the IPG reads these bits). - */ - for (i = 0; i < p[6].len; i++) { - p[6].field |= - (read_phy_bit(ioaddr, polarity) << (p[6].len - 1 - i)); - } - - send_three_state(ioaddr, polarity); - send_three_state(ioaddr, polarity); - send_three_state(ioaddr, polarity); - send_end(ioaddr, polarity); - - /* Return the value of the DATA field. */ - return p[6].field; -} - -/* - * Write to a register from the Physical Layer device located - * on the IPG NIC, using the IPG PHYCTRL register. - */ -static void mdio_write(struct net_device *dev, int phy_id, int phy_reg, int val) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - /* - * The GMII mangement frame structure for a read is as follows: - * - * |Preamble|st|op|phyad|regad|ta| data |idle| - * |< 32 1s>|01|10|AAAAA|RRRRR|z0|DDDDDDDDDDDDDDDD|z | - * - * <32 1s> = 32 consecutive logic 1 values - * A = bit of Physical Layer device address (MSB first) - * R = bit of register address (MSB first) - * z = High impedance state - * D = bit of write data (MSB first) - * - * Transmission order is 'Preamble' field first, bits transmitted - * left to right (first to last). - */ - struct { - u32 field; - unsigned int len; - } p[] = { - { GMII_PREAMBLE, 32 }, /* Preamble */ - { GMII_ST, 2 }, /* ST */ - { GMII_WRITE, 2 }, /* OP */ - { phy_id, 5 }, /* PHYAD */ - { phy_reg, 5 }, /* REGAD */ - { 0x0002, 2 }, /* TA */ - { val & 0xffff, 16 }, /* DATA */ - { 0x0000, 1 } /* IDLE */ - }; - unsigned int i, j; - u8 polarity, data; - - polarity = ipg_r8(PHY_CTRL); - polarity &= (IPG_PC_DUPLEX_POLARITY | IPG_PC_LINK_POLARITY); - - /* Create the Preamble, ST, OP, PHYAD, and REGAD field. */ - for (j = 0; j < 7; j++) { - for (i = 0; i < p[j].len; i++) { - /* For each variable length field, the MSB must be - * transmitted first. Rotate through the field bits, - * starting with the MSB, and move each bit into the - * the 1st (2^1) bit position (this is the bit position - * corresponding to the MgmtData bit of the PhyCtrl - * register for the IPG). - * - * Example: ST = 01; - * - * First write a '0' to bit 1 of the PhyCtrl - * register, then write a '1' to bit 1 of the - * PhyCtrl register. - * - * To do this, right shift the MSB of ST by the value: - * [field length - 1 - #ST bits already written] - * then left shift this result by 1. - */ - data = (p[j].field >> (p[j].len - 1 - i)) << 1; - data &= IPG_PC_MGMTDATA; - data |= polarity | IPG_PC_MGMTDIR; - - ipg_drive_phy_ctl_low_high(ioaddr, data); - } - } - - /* The last cycle is a tri-state, so read from the PHY. */ - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity); - ipg_r8(PHY_CTRL); - ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity); -} - -static void ipg_set_led_mode(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - u32 mode; - - mode = ipg_r32(ASIC_CTRL); - mode &= ~(IPG_AC_LED_MODE_BIT_1 | IPG_AC_LED_MODE | IPG_AC_LED_SPEED); - - if ((sp->led_mode & 0x03) > 1) - mode |= IPG_AC_LED_MODE_BIT_1; /* Write Asic Control Bit 29 */ - - if ((sp->led_mode & 0x01) == 1) - mode |= IPG_AC_LED_MODE; /* Write Asic Control Bit 14 */ - - if ((sp->led_mode & 0x08) == 8) - mode |= IPG_AC_LED_SPEED; /* Write Asic Control Bit 27 */ - - ipg_w32(mode, ASIC_CTRL); -} - -static void ipg_set_phy_set(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - int physet; - - physet = ipg_r8(PHY_SET); - physet &= ~(IPG_PS_MEM_LENB9B | IPG_PS_MEM_LEN9 | IPG_PS_NON_COMPDET); - physet |= ((sp->led_mode & 0x70) >> 4); - ipg_w8(physet, PHY_SET); -} - -static int ipg_reset(struct net_device *dev, u32 resetflags) -{ - /* Assert functional resets via the IPG AsicCtrl - * register as specified by the 'resetflags' input - * parameter. - */ - void __iomem *ioaddr = ipg_ioaddr(dev); - unsigned int timeout_count = 0; - - IPG_DEBUG_MSG("_reset\n"); - - ipg_w32(ipg_r32(ASIC_CTRL) | resetflags, ASIC_CTRL); - - /* Delay added to account for problem with 10Mbps reset. */ - mdelay(IPG_AC_RESETWAIT); - - while (IPG_AC_RESET_BUSY & ipg_r32(ASIC_CTRL)) { - mdelay(IPG_AC_RESETWAIT); - if (++timeout_count > IPG_AC_RESET_TIMEOUT) - return -ETIME; - } - /* Set LED Mode in Asic Control */ - ipg_set_led_mode(dev); - - /* Set PHYSet Register Value */ - ipg_set_phy_set(dev); - return 0; -} - -/* Find the GMII PHY address. */ -static int ipg_find_phyaddr(struct net_device *dev) -{ - unsigned int phyaddr, i; - - for (i = 0; i < 32; i++) { - u32 status; - - /* Search for the correct PHY address among 32 possible. */ - phyaddr = (IPG_NIC_PHY_ADDRESS + i) % 32; - - /* 10/22/03 Grace change verify from GMII_PHY_STATUS to - GMII_PHY_ID1 - */ - - status = mdio_read(dev, phyaddr, MII_BMSR); - - if ((status != 0xFFFF) && (status != 0)) - return phyaddr; - } - - return 0x1f; -} - -/* - * Configure IPG based on result of IEEE 802.3 PHY - * auto-negotiation. - */ -static int ipg_config_autoneg(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int txflowcontrol; - unsigned int rxflowcontrol; - unsigned int fullduplex; - u32 mac_ctrl_val; - u32 asicctrl; - u8 phyctrl; - const char *speed; - const char *duplex; - const char *tx_desc; - const char *rx_desc; - - IPG_DEBUG_MSG("_config_autoneg\n"); - - asicctrl = ipg_r32(ASIC_CTRL); - phyctrl = ipg_r8(PHY_CTRL); - mac_ctrl_val = ipg_r32(MAC_CTRL); - - /* Set flags for use in resolving auto-negotiation, assuming - * non-1000Mbps, half duplex, no flow control. - */ - fullduplex = 0; - txflowcontrol = 0; - rxflowcontrol = 0; - - /* To accommodate a problem in 10Mbps operation, - * set a global flag if PHY running in 10Mbps mode. - */ - sp->tenmbpsmode = 0; - - /* Determine actual speed of operation. */ - switch (phyctrl & IPG_PC_LINK_SPEED) { - case IPG_PC_LINK_SPEED_10MBPS: - speed = "10Mbps"; - sp->tenmbpsmode = 1; - break; - case IPG_PC_LINK_SPEED_100MBPS: - speed = "100Mbps"; - break; - case IPG_PC_LINK_SPEED_1000MBPS: - speed = "1000Mbps"; - break; - default: - speed = "undefined!"; - return 0; - } - - netdev_info(dev, "Link speed = %s\n", speed); - if (sp->tenmbpsmode == 1) - netdev_info(dev, "10Mbps operational mode enabled\n"); - - if (phyctrl & IPG_PC_DUPLEX_STATUS) { - fullduplex = 1; - txflowcontrol = 1; - rxflowcontrol = 1; - } - - /* Configure full duplex, and flow control. */ - if (fullduplex == 1) { - - /* Configure IPG for full duplex operation. */ - - duplex = "full"; - - mac_ctrl_val |= IPG_MC_DUPLEX_SELECT_FD; - - if (txflowcontrol == 1) { - tx_desc = ""; - mac_ctrl_val |= IPG_MC_TX_FLOW_CONTROL_ENABLE; - } else { - tx_desc = "no "; - mac_ctrl_val &= ~IPG_MC_TX_FLOW_CONTROL_ENABLE; - } - - if (rxflowcontrol == 1) { - rx_desc = ""; - mac_ctrl_val |= IPG_MC_RX_FLOW_CONTROL_ENABLE; - } else { - rx_desc = "no "; - mac_ctrl_val &= ~IPG_MC_RX_FLOW_CONTROL_ENABLE; - } - } else { - duplex = "half"; - tx_desc = "no "; - rx_desc = "no "; - mac_ctrl_val &= (~IPG_MC_DUPLEX_SELECT_FD & - ~IPG_MC_TX_FLOW_CONTROL_ENABLE & - ~IPG_MC_RX_FLOW_CONTROL_ENABLE); - } - - netdev_info(dev, "setting %s duplex, %sTX, %sRX flow control\n", - duplex, tx_desc, rx_desc); - ipg_w32(mac_ctrl_val, MAC_CTRL); - - return 0; -} - -/* Determine and configure multicast operation and set - * receive mode for IPG. - */ -static void ipg_nic_set_multicast_list(struct net_device *dev) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - struct netdev_hw_addr *ha; - unsigned int hashindex; - u32 hashtable[2]; - u8 receivemode; - - IPG_DEBUG_MSG("_nic_set_multicast_list\n"); - - receivemode = IPG_RM_RECEIVEUNICAST | IPG_RM_RECEIVEBROADCAST; - - if (dev->flags & IFF_PROMISC) { - /* NIC to be configured in promiscuous mode. */ - receivemode = IPG_RM_RECEIVEALLFRAMES; - } else if ((dev->flags & IFF_ALLMULTI) || - ((dev->flags & IFF_MULTICAST) && - (netdev_mc_count(dev) > IPG_MULTICAST_HASHTABLE_SIZE))) { - /* NIC to be configured to receive all multicast - * frames. */ - receivemode |= IPG_RM_RECEIVEMULTICAST; - } else if ((dev->flags & IFF_MULTICAST) && !netdev_mc_empty(dev)) { - /* NIC to be configured to receive selected - * multicast addresses. */ - receivemode |= IPG_RM_RECEIVEMULTICASTHASH; - } - - /* Calculate the bits to set for the 64 bit, IPG HASHTABLE. - * The IPG applies a cyclic-redundancy-check (the same CRC - * used to calculate the frame data FCS) to the destination - * address all incoming multicast frames whose destination - * address has the multicast bit set. The least significant - * 6 bits of the CRC result are used as an addressing index - * into the hash table. If the value of the bit addressed by - * this index is a 1, the frame is passed to the host system. - */ - - /* Clear hashtable. */ - hashtable[0] = 0x00000000; - hashtable[1] = 0x00000000; - - /* Cycle through all multicast addresses to filter. */ - netdev_for_each_mc_addr(ha, dev) { - /* Calculate CRC result for each multicast address. */ - hashindex = crc32_le(0xffffffff, ha->addr, - ETH_ALEN); - - /* Use only the least significant 6 bits. */ - hashindex = hashindex & 0x3F; - - /* Within "hashtable", set bit number "hashindex" - * to a logic 1. - */ - set_bit(hashindex, (void *)hashtable); - } - - /* Write the value of the hashtable, to the 4, 16 bit - * HASHTABLE IPG registers. - */ - ipg_w32(hashtable[0], HASHTABLE_0); - ipg_w32(hashtable[1], HASHTABLE_1); - - ipg_w8(IPG_RM_RSVD_MASK & receivemode, RECEIVE_MODE); - - IPG_DEBUG_MSG("ReceiveMode = %x\n", ipg_r8(RECEIVE_MODE)); -} - -static int ipg_io_config(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = ipg_ioaddr(dev); - u32 origmacctrl; - u32 restoremacctrl; - - IPG_DEBUG_MSG("_io_config\n"); - - origmacctrl = ipg_r32(MAC_CTRL); - - restoremacctrl = origmacctrl | IPG_MC_STATISTICS_ENABLE; - - /* Based on compilation option, determine if FCS is to be - * stripped on receive frames by IPG. - */ - if (!IPG_STRIP_FCS_ON_RX) - restoremacctrl |= IPG_MC_RCV_FCS; - - /* Determine if transmitter and/or receiver are - * enabled so we may restore MACCTRL correctly. - */ - if (origmacctrl & IPG_MC_TX_ENABLED) - restoremacctrl |= IPG_MC_TX_ENABLE; - - if (origmacctrl & IPG_MC_RX_ENABLED) - restoremacctrl |= IPG_MC_RX_ENABLE; - - /* Transmitter and receiver must be disabled before setting - * IFSSelect. - */ - ipg_w32((origmacctrl & (IPG_MC_RX_DISABLE | IPG_MC_TX_DISABLE)) & - IPG_MC_RSVD_MASK, MAC_CTRL); - - /* Now that transmitter and receiver are disabled, write - * to IFSSelect. - */ - ipg_w32((origmacctrl & IPG_MC_IFS_96BIT) & IPG_MC_RSVD_MASK, MAC_CTRL); - - /* Set RECEIVEMODE register. */ - ipg_nic_set_multicast_list(dev); - - ipg_w16(sp->max_rxframe_size, MAX_FRAME_SIZE); - - ipg_w8(IPG_RXDMAPOLLPERIOD_VALUE, RX_DMA_POLL_PERIOD); - ipg_w8(IPG_RXDMAURGENTTHRESH_VALUE, RX_DMA_URGENT_THRESH); - ipg_w8(IPG_RXDMABURSTTHRESH_VALUE, RX_DMA_BURST_THRESH); - ipg_w8(IPG_TXDMAPOLLPERIOD_VALUE, TX_DMA_POLL_PERIOD); - ipg_w8(IPG_TXDMAURGENTTHRESH_VALUE, TX_DMA_URGENT_THRESH); - ipg_w8(IPG_TXDMABURSTTHRESH_VALUE, TX_DMA_BURST_THRESH); - ipg_w16((IPG_IE_HOST_ERROR | IPG_IE_TX_DMA_COMPLETE | - IPG_IE_TX_COMPLETE | IPG_IE_INT_REQUESTED | - IPG_IE_UPDATE_STATS | IPG_IE_LINK_EVENT | - IPG_IE_RX_DMA_COMPLETE | IPG_IE_RX_DMA_PRIORITY), INT_ENABLE); - ipg_w16(IPG_FLOWONTHRESH_VALUE, FLOW_ON_THRESH); - ipg_w16(IPG_FLOWOFFTHRESH_VALUE, FLOW_OFF_THRESH); - - /* IPG multi-frag frame bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0200, DEBUG_CTRL); - - /* IPG TX poll now bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0010, DEBUG_CTRL); - - /* IPG RX poll now bug workaround. - * Per silicon revision B3 eratta. - */ - ipg_w16(ipg_r16(DEBUG_CTRL) | 0x0020, DEBUG_CTRL); - - /* Now restore MACCTRL to original setting. */ - ipg_w32(IPG_MC_RSVD_MASK & restoremacctrl, MAC_CTRL); - - /* Disable unused RMON statistics. */ - ipg_w32(IPG_RZ_ALL, RMON_STATISTICS_MASK); - - /* Disable unused MIB statistics. */ - ipg_w32(IPG_SM_MACCONTROLFRAMESXMTD | IPG_SM_MACCONTROLFRAMESRCVD | - IPG_SM_BCSTOCTETXMTOK_BCSTFRAMESXMTDOK | IPG_SM_TXJUMBOFRAMES | - IPG_SM_MCSTOCTETXMTOK_MCSTFRAMESXMTDOK | IPG_SM_RXJUMBOFRAMES | - IPG_SM_BCSTOCTETRCVDOK_BCSTFRAMESRCVDOK | - IPG_SM_UDPCHECKSUMERRORS | IPG_SM_TCPCHECKSUMERRORS | - IPG_SM_IPCHECKSUMERRORS, STATISTICS_MASK); - - return 0; -} - -/* - * Create a receive buffer within system memory and update - * NIC private structure appropriately. - */ -static int ipg_get_rxbuff(struct net_device *dev, int entry) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct ipg_rx *rxfd = sp->rxd + entry; - struct sk_buff *skb; - u64 rxfragsize; - - IPG_DEBUG_MSG("_get_rxbuff\n"); - - skb = netdev_alloc_skb_ip_align(dev, sp->rxsupport_size); - if (!skb) { - sp->rx_buff[entry] = NULL; - return -ENOMEM; - } - - /* Save the address of the sk_buff structure. */ - sp->rx_buff[entry] = skb; - - rxfd->frag_info = cpu_to_le64(pci_map_single(sp->pdev, skb->data, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE)); - - /* Set the RFD fragment length. */ - rxfragsize = sp->rxfrag_size; - rxfd->frag_info |= cpu_to_le64((rxfragsize << 48) & IPG_RFI_FRAGLEN); - - return 0; -} - -static int init_rfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_init_rfdlist\n"); - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - struct ipg_rx *rxfd = sp->rxd + i; - - if (sp->rx_buff[i]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[i]); - sp->rx_buff[i] = NULL; - } - - /* Clear out the RFS field. */ - rxfd->rfs = 0x0000000000000000; - - if (ipg_get_rxbuff(dev, i) < 0) { - /* - * A receive buffer was not ready, break the - * RFD list here. - */ - IPG_DEBUG_MSG("Cannot allocate Rx buffer\n"); - - /* Just in case we cannot allocate a single RFD. - * Should not occur. - */ - if (i == 0) { - netdev_err(dev, "No memory available for RFD list\n"); - return -ENOMEM; - } - } - - rxfd->next_desc = cpu_to_le64(sp->rxd_map + - sizeof(struct ipg_rx)*(i + 1)); - } - sp->rxd[i - 1].next_desc = cpu_to_le64(sp->rxd_map); - - sp->rx_current = 0; - sp->rx_dirty = 0; - - /* Write the location of the RFDList to the IPG. */ - ipg_w32((u32) sp->rxd_map, RFD_LIST_PTR_0); - ipg_w32(0x00000000, RFD_LIST_PTR_1); - - return 0; -} - -static void init_tfdlist(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_init_tfdlist\n"); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - struct ipg_tx *txfd = sp->txd + i; - - txfd->tfc = cpu_to_le64(IPG_TFC_TFDDONE); - - if (sp->tx_buff[i]) { - dev_kfree_skb_irq(sp->tx_buff[i]); - sp->tx_buff[i] = NULL; - } - - txfd->next_desc = cpu_to_le64(sp->txd_map + - sizeof(struct ipg_tx)*(i + 1)); - } - sp->txd[i - 1].next_desc = cpu_to_le64(sp->txd_map); - - sp->tx_current = 0; - sp->tx_dirty = 0; - - /* Write the location of the TFDList to the IPG. */ - IPG_DDEBUG_MSG("Starting TFDListPtr = %08x\n", - (u32) sp->txd_map); - ipg_w32((u32) sp->txd_map, TFD_LIST_PTR_0); - ipg_w32(0x00000000, TFD_LIST_PTR_1); - - sp->reset_current_tfd = 1; -} - -/* - * Free all transmit buffers which have already been transferred - * via DMA to the IPG. - */ -static void ipg_nic_txfree(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int released, pending, dirty; - - IPG_DEBUG_MSG("_nic_txfree\n"); - - pending = sp->tx_current - sp->tx_dirty; - dirty = sp->tx_dirty % IPG_TFDLIST_LENGTH; - - for (released = 0; released < pending; released++) { - struct sk_buff *skb = sp->tx_buff[dirty]; - struct ipg_tx *txfd = sp->txd + dirty; - - IPG_DEBUG_MSG("TFC = %016lx\n", (unsigned long) txfd->tfc); - - /* Look at each TFD's TFC field beginning - * at the last freed TFD up to the current TFD. - * If the TFDDone bit is set, free the associated - * buffer. - */ - if (!(txfd->tfc & cpu_to_le64(IPG_TFC_TFDDONE))) - break; - - /* Free the transmit buffer. */ - if (skb) { - pci_unmap_single(sp->pdev, - le64_to_cpu(txfd->frag_info) & ~IPG_TFI_FRAGLEN, - skb->len, PCI_DMA_TODEVICE); - - dev_kfree_skb_irq(skb); - - sp->tx_buff[dirty] = NULL; - } - dirty = (dirty + 1) % IPG_TFDLIST_LENGTH; - } - - sp->tx_dirty += released; - - if (netif_queue_stopped(dev) && - (sp->tx_current != (sp->tx_dirty + IPG_TFDLIST_LENGTH))) { - netif_wake_queue(dev); - } -} - -static void ipg_tx_timeout(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - - ipg_reset(dev, IPG_AC_TX_RESET | IPG_AC_DMA | IPG_AC_NETWORK | - IPG_AC_FIFO); - - spin_lock_irq(&sp->lock); - - /* Re-configure after DMA reset. */ - if (ipg_io_config(dev) < 0) - netdev_info(dev, "Error during re-configuration\n"); - - init_tfdlist(dev); - - spin_unlock_irq(&sp->lock); - - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & IPG_MC_RSVD_MASK, - MAC_CTRL); -} - -/* - * For TxComplete interrupts, free all transmit - * buffers which have already been transferred via DMA - * to the IPG. - */ -static void ipg_nic_txcleanup(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_nic_txcleanup\n"); - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - /* Reading the TXSTATUS register clears the - * TX_COMPLETE interrupt. - */ - u32 txstatusdword = ipg_r32(TX_STATUS); - - IPG_DEBUG_MSG("TxStatus = %08x\n", txstatusdword); - - /* Check for Transmit errors. Error bits only valid if - * TX_COMPLETE bit in the TXSTATUS register is a 1. - */ - if (!(txstatusdword & IPG_TS_TX_COMPLETE)) - break; - - /* If in 10Mbps mode, indicate transmit is ready. */ - if (sp->tenmbpsmode) { - netif_wake_queue(dev); - } - - /* Transmit error, increment stat counters. */ - if (txstatusdword & IPG_TS_TX_ERROR) { - IPG_DEBUG_MSG("Transmit error\n"); - sp->stats.tx_errors++; - } - - /* Late collision, re-enable transmitter. */ - if (txstatusdword & IPG_TS_LATE_COLLISION) { - IPG_DEBUG_MSG("Late collision on transmit\n"); - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - - /* Maximum collisions, re-enable transmitter. */ - if (txstatusdword & IPG_TS_TX_MAX_COLL) { - IPG_DEBUG_MSG("Maximum collisions on transmit\n"); - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - - /* Transmit underrun, reset and re-enable - * transmitter. - */ - if (txstatusdword & IPG_TS_TX_UNDERRUN) { - IPG_DEBUG_MSG("Transmitter underrun\n"); - sp->stats.tx_fifo_errors++; - ipg_reset(dev, IPG_AC_TX_RESET | IPG_AC_DMA | - IPG_AC_NETWORK | IPG_AC_FIFO); - - /* Re-configure after DMA reset. */ - if (ipg_io_config(dev) < 0) { - netdev_info(dev, "Error during re-configuration\n"); - } - init_tfdlist(dev); - - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - } - } - - ipg_nic_txfree(dev); -} - -/* Provides statistical information about the IPG NIC. */ -static struct net_device_stats *ipg_nic_get_stats(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - u16 temp1; - u16 temp2; - - IPG_DEBUG_MSG("_nic_get_stats\n"); - - /* Check to see if the NIC has been initialized via nic_open, - * before trying to read statistic registers. - */ - if (!netif_running(dev)) - return &sp->stats; - - sp->stats.rx_packets += ipg_r32(IPG_FRAMESRCVDOK); - sp->stats.tx_packets += ipg_r32(IPG_FRAMESXMTDOK); - sp->stats.rx_bytes += ipg_r32(IPG_OCTETRCVOK); - sp->stats.tx_bytes += ipg_r32(IPG_OCTETXMTOK); - temp1 = ipg_r16(IPG_FRAMESLOSTRXERRORS); - sp->stats.rx_errors += temp1; - sp->stats.rx_missed_errors += temp1; - temp1 = ipg_r32(IPG_SINGLECOLFRAMES) + ipg_r32(IPG_MULTICOLFRAMES) + - ipg_r32(IPG_LATECOLLISIONS); - temp2 = ipg_r16(IPG_CARRIERSENSEERRORS); - sp->stats.collisions += temp1; - sp->stats.tx_dropped += ipg_r16(IPG_FRAMESABORTXSCOLLS); - sp->stats.tx_errors += ipg_r16(IPG_FRAMESWEXDEFERRAL) + - ipg_r32(IPG_FRAMESWDEFERREDXMT) + temp1 + temp2; - sp->stats.multicast += ipg_r32(IPG_MCSTOCTETRCVDOK); - - /* detailed tx_errors */ - sp->stats.tx_carrier_errors += temp2; - - /* detailed rx_errors */ - sp->stats.rx_length_errors += ipg_r16(IPG_INRANGELENGTHERRORS) + - ipg_r16(IPG_FRAMETOOLONGERRORS); - sp->stats.rx_crc_errors += ipg_r16(IPG_FRAMECHECKSEQERRORS); - - /* Unutilized IPG statistic registers. */ - ipg_r32(IPG_MCSTFRAMESRCVDOK); - - return &sp->stats; -} - -/* Restore used receive buffers. */ -static int ipg_nic_rxrestore(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - const unsigned int curr = sp->rx_current; - unsigned int dirty = sp->rx_dirty; - - IPG_DEBUG_MSG("_nic_rxrestore\n"); - - for (dirty = sp->rx_dirty; curr - dirty > 0; dirty++) { - unsigned int entry = dirty % IPG_RFDLIST_LENGTH; - - /* rx_copybreak may poke hole here and there. */ - if (sp->rx_buff[entry]) - continue; - - /* Generate a new receive buffer to replace the - * current buffer (which will be released by the - * Linux system). - */ - if (ipg_get_rxbuff(dev, entry) < 0) { - IPG_DEBUG_MSG("Cannot allocate new Rx buffer\n"); - - break; - } - - /* Reset the RFS field. */ - sp->rxd[entry].rfs = 0x0000000000000000; - } - sp->rx_dirty = dirty; - - return 0; -} - -/* use jumboindex and jumbosize to control jumbo frame status - * initial status is jumboindex=-1 and jumbosize=0 - * 1. jumboindex = -1 and jumbosize=0 : previous jumbo frame has been done. - * 2. jumboindex != -1 and jumbosize != 0 : jumbo frame is not over size and receiving - * 3. jumboindex = -1 and jumbosize != 0 : jumbo frame is over size, already dump - * previous receiving and need to continue dumping the current one - */ -enum { - NORMAL_PACKET, - ERROR_PACKET -}; - -enum { - FRAME_NO_START_NO_END = 0, - FRAME_WITH_START = 1, - FRAME_WITH_END = 10, - FRAME_WITH_START_WITH_END = 11 -}; - -static void ipg_nic_rx_free_skb(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; - - if (sp->rx_buff[entry]) { - struct ipg_rx *rxfd = sp->rxd + entry; - - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[entry]); - sp->rx_buff[entry] = NULL; - } -} - -static int ipg_nic_rx_check_frame_type(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct ipg_rx *rxfd = sp->rxd + (sp->rx_current % IPG_RFDLIST_LENGTH); - int type = FRAME_NO_START_NO_END; - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMESTART) - type += FRAME_WITH_START; - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMEEND) - type += FRAME_WITH_END; - return type; -} - -static int ipg_nic_rx_check_error(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; - struct ipg_rx *rxfd = sp->rxd + entry; - - if (IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & - (IPG_RFS_RXFIFOOVERRUN | IPG_RFS_RXRUNTFRAME | - IPG_RFS_RXALIGNMENTERROR | IPG_RFS_RXFCSERROR | - IPG_RFS_RXOVERSIZEDFRAME | IPG_RFS_RXLENGTHERROR))) { - IPG_DEBUG_MSG("Rx error, RFS = %016lx\n", - (unsigned long) rxfd->rfs); - - /* Increment general receive error statistic. */ - sp->stats.rx_errors++; - - /* Increment detailed receive error statistics. */ - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFIFOOVERRUN) { - IPG_DEBUG_MSG("RX FIFO overrun occurred\n"); - - sp->stats.rx_fifo_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXRUNTFRAME) { - IPG_DEBUG_MSG("RX runt occurred\n"); - sp->stats.rx_length_errors++; - } - - /* Do nothing for IPG_RFS_RXOVERSIZEDFRAME, - * error count handled by a IPG statistic register. - */ - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXALIGNMENTERROR) { - IPG_DEBUG_MSG("RX alignment error occurred\n"); - sp->stats.rx_frame_errors++; - } - - /* Do nothing for IPG_RFS_RXFCSERROR, error count - * handled by a IPG statistic register. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (sp->rx_buff[entry]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - dev_kfree_skb_irq(sp->rx_buff[entry]); - sp->rx_buff[entry] = NULL; - } - return ERROR_PACKET; - } - return NORMAL_PACKET; -} - -static void ipg_nic_rx_with_start_and_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - struct sk_buff *skb; - int framelen; - - if (jumbo->found_start) { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) != NORMAL_PACKET) - return; - - skb = sp->rx_buff[entry]; - if (!skb) - return; - - /* accept this frame and send to upper layer */ - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - if (framelen > sp->rxfrag_size) - framelen = sp->rxfrag_size; - - skb_put(skb, framelen); - skb->protocol = eth_type_trans(skb, dev); - skb_checksum_none_assert(skb); - netif_rx(skb); - sp->rx_buff[entry] = NULL; -} - -static void ipg_nic_rx_with_start(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - struct pci_dev *pdev = sp->pdev; - struct sk_buff *skb; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) != NORMAL_PACKET) - return; - - /* accept this frame and send to upper layer */ - skb = sp->rx_buff[entry]; - if (!skb) - return; - - if (jumbo->found_start) - dev_kfree_skb_irq(jumbo->skb); - - pci_unmap_single(pdev, le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - skb_put(skb, sp->rxfrag_size); - - jumbo->found_start = 1; - jumbo->current_size = sp->rxfrag_size; - jumbo->skb = skb; - - sp->rx_buff[entry] = NULL; -} - -static void ipg_nic_rx_with_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) == NORMAL_PACKET) { - struct sk_buff *skb = sp->rx_buff[entry]; - - if (!skb) - return; - - if (jumbo->found_start) { - int framelen, endframelen; - - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - - endframelen = framelen - jumbo->current_size; - if (framelen > sp->rxsupport_size) - dev_kfree_skb_irq(jumbo->skb); - else { - memcpy(skb_put(jumbo->skb, endframelen), - skb->data, endframelen); - - jumbo->skb->protocol = - eth_type_trans(jumbo->skb, dev); - - skb_checksum_none_assert(jumbo->skb); - netif_rx(jumbo->skb); - } - } - - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - - ipg_nic_rx_free_skb(dev); - } else { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } -} - -static void ipg_nic_rx_no_start_no_end(struct net_device *dev, - struct ipg_nic_private *sp, - struct ipg_rx *rxfd, unsigned entry) -{ - struct ipg_jumbo *jumbo = &sp->jumbo; - - /* 1: found error, 0 no error */ - if (ipg_nic_rx_check_error(dev) == NORMAL_PACKET) { - struct sk_buff *skb = sp->rx_buff[entry]; - - if (skb) { - if (jumbo->found_start) { - jumbo->current_size += sp->rxfrag_size; - if (jumbo->current_size <= sp->rxsupport_size) { - memcpy(skb_put(jumbo->skb, - sp->rxfrag_size), - skb->data, sp->rxfrag_size); - } - } - ipg_nic_rx_free_skb(dev); - } - } else { - dev_kfree_skb_irq(jumbo->skb); - jumbo->found_start = 0; - jumbo->current_size = 0; - jumbo->skb = NULL; - } -} - -static int ipg_nic_rx_jumbo(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int curr = sp->rx_current; - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - - IPG_DEBUG_MSG("_nic_rx\n"); - - for (i = 0; i < IPG_MAXRFDPROCESS_COUNT; i++, curr++) { - unsigned int entry = curr % IPG_RFDLIST_LENGTH; - struct ipg_rx *rxfd = sp->rxd + entry; - - if (!(rxfd->rfs & cpu_to_le64(IPG_RFS_RFDDONE))) - break; - - switch (ipg_nic_rx_check_frame_type(dev)) { - case FRAME_WITH_START_WITH_END: - ipg_nic_rx_with_start_and_end(dev, sp, rxfd, entry); - break; - case FRAME_WITH_START: - ipg_nic_rx_with_start(dev, sp, rxfd, entry); - break; - case FRAME_WITH_END: - ipg_nic_rx_with_end(dev, sp, rxfd, entry); - break; - case FRAME_NO_START_NO_END: - ipg_nic_rx_no_start_no_end(dev, sp, rxfd, entry); - break; - } - } - - sp->rx_current = curr; - - if (i == IPG_MAXRFDPROCESS_COUNT) { - /* There are more RFDs to process, however the - * allocated amount of RFD processing time has - * expired. Assert Interrupt Requested to make - * sure we come back to process the remaining RFDs. - */ - ipg_w32(ipg_r32(ASIC_CTRL) | IPG_AC_INT_REQUEST, ASIC_CTRL); - } - - ipg_nic_rxrestore(dev); - - return 0; -} - -static int ipg_nic_rx(struct net_device *dev) -{ - /* Transfer received Ethernet frames to higher network layers. */ - struct ipg_nic_private *sp = netdev_priv(dev); - unsigned int curr = sp->rx_current; - void __iomem *ioaddr = sp->ioaddr; - struct ipg_rx *rxfd; - unsigned int i; - - IPG_DEBUG_MSG("_nic_rx\n"); - -#define __RFS_MASK \ - cpu_to_le64(IPG_RFS_RFDDONE | IPG_RFS_FRAMESTART | IPG_RFS_FRAMEEND) - - for (i = 0; i < IPG_MAXRFDPROCESS_COUNT; i++, curr++) { - unsigned int entry = curr % IPG_RFDLIST_LENGTH; - struct sk_buff *skb = sp->rx_buff[entry]; - unsigned int framelen; - - rxfd = sp->rxd + entry; - - if (((rxfd->rfs & __RFS_MASK) != __RFS_MASK) || !skb) - break; - - /* Get received frame length. */ - framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - - /* Check for jumbo frame arrival with too small - * RXFRAG_SIZE. - */ - if (framelen > sp->rxfrag_size) { - IPG_DEBUG_MSG - ("RFS FrameLen > allocated fragment size\n"); - - framelen = sp->rxfrag_size; - } - - if ((IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & - (IPG_RFS_RXFIFOOVERRUN | IPG_RFS_RXRUNTFRAME | - IPG_RFS_RXALIGNMENTERROR | IPG_RFS_RXFCSERROR | - IPG_RFS_RXOVERSIZEDFRAME | IPG_RFS_RXLENGTHERROR)))) { - - IPG_DEBUG_MSG("Rx error, RFS = %016lx\n", - (unsigned long int) rxfd->rfs); - - /* Increment general receive error statistic. */ - sp->stats.rx_errors++; - - /* Increment detailed receive error statistics. */ - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFIFOOVERRUN) { - IPG_DEBUG_MSG("RX FIFO overrun occurred\n"); - sp->stats.rx_fifo_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXRUNTFRAME) { - IPG_DEBUG_MSG("RX runt occurred\n"); - sp->stats.rx_length_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXOVERSIZEDFRAME) ; - /* Do nothing, error count handled by a IPG - * statistic register. - */ - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXALIGNMENTERROR) { - IPG_DEBUG_MSG("RX alignment error occurred\n"); - sp->stats.rx_frame_errors++; - } - - if (le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFCSERROR) ; - /* Do nothing, error count handled by a IPG - * statistic register. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (skb) { - __le64 info = rxfd->frag_info; - - pci_unmap_single(sp->pdev, - le64_to_cpu(info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - - dev_kfree_skb_irq(skb); - } - } else { - - /* Adjust the new buffer length to accommodate the size - * of the received frame. - */ - skb_put(skb, framelen); - - /* Set the buffer's protocol field to Ethernet. */ - skb->protocol = eth_type_trans(skb, dev); - - /* The IPG encountered an error with (or - * there were no) IP/TCP/UDP checksums. - * This may or may not indicate an invalid - * IP/TCP/UDP frame was received. Let the - * upper layer decide. - */ - skb_checksum_none_assert(skb); - - /* Hand off frame for higher layer processing. - * The function netif_rx() releases the sk_buff - * when processing completes. - */ - netif_rx(skb); - } - - /* Assure RX buffer is not reused by IPG. */ - sp->rx_buff[entry] = NULL; - } - - /* - * If there are more RFDs to process and the allocated amount of RFD - * processing time has expired, assert Interrupt Requested to make - * sure we come back to process the remaining RFDs. - */ - if (i == IPG_MAXRFDPROCESS_COUNT) - ipg_w32(ipg_r32(ASIC_CTRL) | IPG_AC_INT_REQUEST, ASIC_CTRL); - -#ifdef IPG_DEBUG - /* Check if the RFD list contained no receive frame data. */ - if (!i) - sp->EmptyRFDListCount++; -#endif - while ((le64_to_cpu(rxfd->rfs) & IPG_RFS_RFDDONE) && - !((le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMESTART) && - (le64_to_cpu(rxfd->rfs) & IPG_RFS_FRAMEEND))) { - unsigned int entry = curr++ % IPG_RFDLIST_LENGTH; - - rxfd = sp->rxd + entry; - - IPG_DEBUG_MSG("Frame requires multiple RFDs\n"); - - /* An unexpected event, additional code needed to handle - * properly. So for the time being, just disregard the - * frame. - */ - - /* Free the memory associated with the RX - * buffer since it is erroneous and we will - * not pass it to higher layer processes. - */ - if (sp->rx_buff[entry]) { - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb_irq(sp->rx_buff[entry]); - } - - /* Assure RX buffer is not reused by IPG. */ - sp->rx_buff[entry] = NULL; - } - - sp->rx_current = curr; - - /* Check to see if there are a minimum number of used - * RFDs before restoring any (should improve performance.) - */ - if ((curr - sp->rx_dirty) >= IPG_MINUSEDRFDSTOFREE) - ipg_nic_rxrestore(dev); - - return 0; -} - -static void ipg_reset_after_host_error(struct work_struct *work) -{ - struct ipg_nic_private *sp = - container_of(work, struct ipg_nic_private, task.work); - struct net_device *dev = sp->dev; - - /* - * Acknowledge HostError interrupt by resetting - * IPG DMA and HOST. - */ - ipg_reset(dev, IPG_AC_GLOBAL_RESET | IPG_AC_HOST | IPG_AC_DMA); - - init_rfdlist(dev); - init_tfdlist(dev); - - if (ipg_io_config(dev) < 0) { - netdev_info(dev, "Cannot recover from PCI error\n"); - schedule_delayed_work(&sp->task, HZ); - } -} - -static irqreturn_t ipg_interrupt_handler(int irq, void *dev_inst) -{ - struct net_device *dev = dev_inst; - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int handled = 0; - u16 status; - - IPG_DEBUG_MSG("_interrupt_handler\n"); - - if (sp->is_jumbo) - ipg_nic_rxrestore(dev); - - spin_lock(&sp->lock); - - /* Get interrupt source information, and acknowledge - * some (i.e. TxDMAComplete, RxDMAComplete, RxEarly, - * IntRequested, MacControlFrame, LinkEvent) interrupts - * if issued. Also, all IPG interrupts are disabled by - * reading IntStatusAck. - */ - status = ipg_r16(INT_STATUS_ACK); - - IPG_DEBUG_MSG("IntStatusAck = %04x\n", status); - - /* Shared IRQ of remove event. */ - if (!(status & IPG_IS_RSVD_MASK)) - goto out_enable; - - handled = 1; - - if (unlikely(!netif_running(dev))) - goto out_unlock; - - /* If RFDListEnd interrupt, restore all used RFDs. */ - if (status & IPG_IS_RFD_LIST_END) { - IPG_DEBUG_MSG("RFDListEnd Interrupt\n"); - - /* The RFD list end indicates an RFD was encountered - * with a 0 NextPtr, or with an RFDDone bit set to 1 - * (indicating the RFD is not read for use by the - * IPG.) Try to restore all RFDs. - */ - ipg_nic_rxrestore(dev); - -#ifdef IPG_DEBUG - /* Increment the RFDlistendCount counter. */ - sp->RFDlistendCount++; -#endif - } - - /* If RFDListEnd, RxDMAPriority, RxDMAComplete, or - * IntRequested interrupt, process received frames. */ - if ((status & IPG_IS_RX_DMA_PRIORITY) || - (status & IPG_IS_RFD_LIST_END) || - (status & IPG_IS_RX_DMA_COMPLETE) || - (status & IPG_IS_INT_REQUESTED)) { -#ifdef IPG_DEBUG - /* Increment the RFD list checked counter if interrupted - * only to check the RFD list. */ - if (status & (~(IPG_IS_RX_DMA_PRIORITY | IPG_IS_RFD_LIST_END | - IPG_IS_RX_DMA_COMPLETE | IPG_IS_INT_REQUESTED) & - (IPG_IS_HOST_ERROR | IPG_IS_TX_DMA_COMPLETE | - IPG_IS_LINK_EVENT | IPG_IS_TX_COMPLETE | - IPG_IS_UPDATE_STATS))) - sp->RFDListCheckedCount++; -#endif - - if (sp->is_jumbo) - ipg_nic_rx_jumbo(dev); - else - ipg_nic_rx(dev); - } - - /* If TxDMAComplete interrupt, free used TFDs. */ - if (status & IPG_IS_TX_DMA_COMPLETE) - ipg_nic_txfree(dev); - - /* TxComplete interrupts indicate one of numerous actions. - * Determine what action to take based on TXSTATUS register. - */ - if (status & IPG_IS_TX_COMPLETE) - ipg_nic_txcleanup(dev); - - /* If UpdateStats interrupt, update Linux Ethernet statistics */ - if (status & IPG_IS_UPDATE_STATS) - ipg_nic_get_stats(dev); - - /* If HostError interrupt, reset IPG. */ - if (status & IPG_IS_HOST_ERROR) { - IPG_DDEBUG_MSG("HostError Interrupt\n"); - - schedule_delayed_work(&sp->task, 0); - } - - /* If LinkEvent interrupt, resolve autonegotiation. */ - if (status & IPG_IS_LINK_EVENT) { - if (ipg_config_autoneg(dev) < 0) - netdev_info(dev, "Auto-negotiation error\n"); - } - - /* If MACCtrlFrame interrupt, do nothing. */ - if (status & IPG_IS_MAC_CTRL_FRAME) - IPG_DEBUG_MSG("MACCtrlFrame interrupt\n"); - - /* If RxComplete interrupt, do nothing. */ - if (status & IPG_IS_RX_COMPLETE) - IPG_DEBUG_MSG("RxComplete interrupt\n"); - - /* If RxEarly interrupt, do nothing. */ - if (status & IPG_IS_RX_EARLY) - IPG_DEBUG_MSG("RxEarly interrupt\n"); - -out_enable: - /* Re-enable IPG interrupts. */ - ipg_w16(IPG_IE_TX_DMA_COMPLETE | IPG_IE_RX_DMA_COMPLETE | - IPG_IE_HOST_ERROR | IPG_IE_INT_REQUESTED | IPG_IE_TX_COMPLETE | - IPG_IE_LINK_EVENT | IPG_IE_UPDATE_STATS, INT_ENABLE); -out_unlock: - spin_unlock(&sp->lock); - - return IRQ_RETVAL(handled); -} - -static void ipg_rx_clear(struct ipg_nic_private *sp) -{ - unsigned int i; - - for (i = 0; i < IPG_RFDLIST_LENGTH; i++) { - if (sp->rx_buff[i]) { - struct ipg_rx *rxfd = sp->rxd + i; - - dev_kfree_skb_irq(sp->rx_buff[i]); - sp->rx_buff[i] = NULL; - pci_unmap_single(sp->pdev, - le64_to_cpu(rxfd->frag_info) & ~IPG_RFI_FRAGLEN, - sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - } - } -} - -static void ipg_tx_clear(struct ipg_nic_private *sp) -{ - unsigned int i; - - for (i = 0; i < IPG_TFDLIST_LENGTH; i++) { - if (sp->tx_buff[i]) { - struct ipg_tx *txfd = sp->txd + i; - - pci_unmap_single(sp->pdev, - le64_to_cpu(txfd->frag_info) & ~IPG_TFI_FRAGLEN, - sp->tx_buff[i]->len, PCI_DMA_TODEVICE); - - dev_kfree_skb_irq(sp->tx_buff[i]); - - sp->tx_buff[i] = NULL; - } - } -} - -static int ipg_nic_open(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - struct pci_dev *pdev = sp->pdev; - int rc; - - IPG_DEBUG_MSG("_nic_open\n"); - - sp->rx_buf_sz = sp->rxsupport_size; - - /* Check for interrupt line conflicts, and request interrupt - * line for IPG. - * - * IMPORTANT: Disable IPG interrupts prior to registering - * IRQ. - */ - ipg_w16(0x0000, INT_ENABLE); - - /* Register the interrupt line to be used by the IPG within - * the Linux system. - */ - rc = request_irq(pdev->irq, ipg_interrupt_handler, IRQF_SHARED, - dev->name, dev); - if (rc < 0) { - netdev_info(dev, "Error when requesting interrupt\n"); - goto out; - } - - dev->irq = pdev->irq; - - rc = -ENOMEM; - - sp->rxd = dma_alloc_coherent(&pdev->dev, IPG_RX_RING_BYTES, - &sp->rxd_map, GFP_KERNEL); - if (!sp->rxd) - goto err_free_irq_0; - - sp->txd = dma_alloc_coherent(&pdev->dev, IPG_TX_RING_BYTES, - &sp->txd_map, GFP_KERNEL); - if (!sp->txd) - goto err_free_rx_1; - - rc = init_rfdlist(dev); - if (rc < 0) { - netdev_info(dev, "Error during configuration\n"); - goto err_free_tx_2; - } - - init_tfdlist(dev); - - rc = ipg_io_config(dev); - if (rc < 0) { - netdev_info(dev, "Error during configuration\n"); - goto err_release_tfdlist_3; - } - - /* Resolve autonegotiation. */ - if (ipg_config_autoneg(dev) < 0) - netdev_info(dev, "Auto-negotiation error\n"); - - /* initialize JUMBO Frame control variable */ - sp->jumbo.found_start = 0; - sp->jumbo.current_size = 0; - sp->jumbo.skb = NULL; - - /* Enable transmit and receive operation of the IPG. */ - ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_RX_ENABLE | IPG_MC_TX_ENABLE) & - IPG_MC_RSVD_MASK, MAC_CTRL); - - netif_start_queue(dev); -out: - return rc; - -err_release_tfdlist_3: - ipg_tx_clear(sp); - ipg_rx_clear(sp); -err_free_tx_2: - dma_free_coherent(&pdev->dev, IPG_TX_RING_BYTES, sp->txd, sp->txd_map); -err_free_rx_1: - dma_free_coherent(&pdev->dev, IPG_RX_RING_BYTES, sp->rxd, sp->rxd_map); -err_free_irq_0: - free_irq(pdev->irq, dev); - goto out; -} - -static int ipg_nic_stop(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - struct pci_dev *pdev = sp->pdev; - - IPG_DEBUG_MSG("_nic_stop\n"); - - netif_stop_queue(dev); - - IPG_DUMPTFDLIST(dev); - - do { - (void) ipg_r16(INT_STATUS_ACK); - - ipg_reset(dev, IPG_AC_GLOBAL_RESET | IPG_AC_HOST | IPG_AC_DMA); - - synchronize_irq(pdev->irq); - } while (ipg_r16(INT_ENABLE) & IPG_IE_RSVD_MASK); - - ipg_rx_clear(sp); - - ipg_tx_clear(sp); - - pci_free_consistent(pdev, IPG_RX_RING_BYTES, sp->rxd, sp->rxd_map); - pci_free_consistent(pdev, IPG_TX_RING_BYTES, sp->txd, sp->txd_map); - - free_irq(pdev->irq, dev); - - return 0; -} - -static netdev_tx_t ipg_nic_hard_start_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int entry = sp->tx_current % IPG_TFDLIST_LENGTH; - unsigned long flags; - struct ipg_tx *txfd; - - IPG_DDEBUG_MSG("_nic_hard_start_xmit\n"); - - /* If in 10Mbps mode, stop the transmit queue so - * no more transmit frames are accepted. - */ - if (sp->tenmbpsmode) - netif_stop_queue(dev); - - if (sp->reset_current_tfd) { - sp->reset_current_tfd = 0; - entry = 0; - } - - txfd = sp->txd + entry; - - sp->tx_buff[entry] = skb; - - /* Clear all TFC fields, except TFDDONE. */ - txfd->tfc = cpu_to_le64(IPG_TFC_TFDDONE); - - /* Specify the TFC field within the TFD. */ - txfd->tfc |= cpu_to_le64(IPG_TFC_WORDALIGNDISABLED | - (IPG_TFC_FRAMEID & sp->tx_current) | - (IPG_TFC_FRAGCOUNT & (1 << 24))); - /* - * 16--17 (WordAlign) <- 3 (disable), - * 0--15 (FrameId) <- sp->tx_current, - * 24--27 (FragCount) <- 1 - */ - - /* Request TxComplete interrupts at an interval defined - * by the constant IPG_FRAMESBETWEENTXCOMPLETES. - * Request TxComplete interrupt for every frame - * if in 10Mbps mode to accommodate problem with 10Mbps - * processing. - */ - if (sp->tenmbpsmode) - txfd->tfc |= cpu_to_le64(IPG_TFC_TXINDICATE); - txfd->tfc |= cpu_to_le64(IPG_TFC_TXDMAINDICATE); - /* Based on compilation option, determine if FCS is to be - * appended to transmit frame by IPG. - */ - if (!(IPG_APPEND_FCS_ON_TX)) - txfd->tfc |= cpu_to_le64(IPG_TFC_FCSAPPENDDISABLE); - - /* Based on compilation option, determine if IP, TCP and/or - * UDP checksums are to be added to transmit frame by IPG. - */ - if (IPG_ADD_IPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_IPCHECKSUMENABLE); - - if (IPG_ADD_TCPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_TCPCHECKSUMENABLE); - - if (IPG_ADD_UDPCHECKSUM_ON_TX) - txfd->tfc |= cpu_to_le64(IPG_TFC_UDPCHECKSUMENABLE); - - /* Based on compilation option, determine if VLAN tag info is to be - * inserted into transmit frame by IPG. - */ - if (IPG_INSERT_MANUAL_VLAN_TAG) { - txfd->tfc |= cpu_to_le64(IPG_TFC_VLANTAGINSERT | - ((u64) IPG_MANUAL_VLAN_VID << 32) | - ((u64) IPG_MANUAL_VLAN_CFI << 44) | - ((u64) IPG_MANUAL_VLAN_USERPRIORITY << 45)); - } - - /* The fragment start location within system memory is defined - * by the sk_buff structure's data field. The physical address - * of this location within the system's virtual memory space - * is determined using the IPG_HOST2BUS_MAP function. - */ - txfd->frag_info = cpu_to_le64(pci_map_single(sp->pdev, skb->data, - skb->len, PCI_DMA_TODEVICE)); - - /* The length of the fragment within system memory is defined by - * the sk_buff structure's len field. - */ - txfd->frag_info |= cpu_to_le64(IPG_TFI_FRAGLEN & - ((u64) (skb->len & 0xffff) << 48)); - - /* Clear the TFDDone bit last to indicate the TFD is ready - * for transfer to the IPG. - */ - txfd->tfc &= cpu_to_le64(~IPG_TFC_TFDDONE); - - spin_lock_irqsave(&sp->lock, flags); - - sp->tx_current++; - - mmiowb(); - - ipg_w32(IPG_DC_TX_DMA_POLL_NOW, DMA_CTRL); - - if (sp->tx_current == (sp->tx_dirty + IPG_TFDLIST_LENGTH)) - netif_stop_queue(dev); - - spin_unlock_irqrestore(&sp->lock, flags); - - return NETDEV_TX_OK; -} - -static void ipg_set_phy_default_param(unsigned char rev, - struct net_device *dev, int phy_address) -{ - unsigned short length; - unsigned char revision; - const unsigned short *phy_param; - unsigned short address, value; - - phy_param = &DefaultPhyParam[0]; - length = *phy_param & 0x00FF; - revision = (unsigned char)((*phy_param) >> 8); - phy_param++; - while (length != 0) { - if (rev == revision) { - while (length > 1) { - address = *phy_param; - value = *(phy_param + 1); - phy_param += 2; - mdio_write(dev, phy_address, address, value); - length -= 4; - } - break; - } else { - phy_param += length / 2; - length = *phy_param & 0x00FF; - revision = (unsigned char)((*phy_param) >> 8); - phy_param++; - } - } -} - -static int read_eeprom(struct net_device *dev, int eep_addr) -{ - void __iomem *ioaddr = ipg_ioaddr(dev); - unsigned int i; - int ret = 0; - u16 value; - - value = IPG_EC_EEPROM_READOPCODE | (eep_addr & 0xff); - ipg_w16(value, EEPROM_CTRL); - - for (i = 0; i < 1000; i++) { - u16 data; - - mdelay(10); - data = ipg_r16(EEPROM_CTRL); - if (!(data & IPG_EC_EEPROM_BUSY)) { - ret = ipg_r16(EEPROM_DATA); - break; - } - } - return ret; -} - -static void ipg_init_mii(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - struct mii_if_info *mii_if = &sp->mii_if; - int phyaddr; - - mii_if->dev = dev; - mii_if->mdio_read = mdio_read; - mii_if->mdio_write = mdio_write; - mii_if->phy_id_mask = 0x1f; - mii_if->reg_num_mask = 0x1f; - - mii_if->phy_id = phyaddr = ipg_find_phyaddr(dev); - - if (phyaddr != 0x1f) { - u16 mii_phyctrl, mii_1000cr; - - mii_1000cr = mdio_read(dev, phyaddr, MII_CTRL1000); - mii_1000cr |= ADVERTISE_1000FULL | ADVERTISE_1000HALF | - GMII_PHY_1000BASETCONTROL_PreferMaster; - mdio_write(dev, phyaddr, MII_CTRL1000, mii_1000cr); - - mii_phyctrl = mdio_read(dev, phyaddr, MII_BMCR); - - /* Set default phyparam */ - ipg_set_phy_default_param(sp->pdev->revision, dev, phyaddr); - - /* Reset PHY */ - mii_phyctrl |= BMCR_RESET | BMCR_ANRESTART; - mdio_write(dev, phyaddr, MII_BMCR, mii_phyctrl); - - } -} - -static int ipg_hw_init(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->ioaddr; - unsigned int i; - int rc; - - /* Read/Write and Reset EEPROM Value */ - /* Read LED Mode Configuration from EEPROM */ - sp->led_mode = read_eeprom(dev, 6); - - /* Reset all functions within the IPG. Do not assert - * RST_OUT as not compatible with some PHYs. - */ - rc = ipg_reset(dev, IPG_RESET_MASK); - if (rc < 0) - goto out; - - ipg_init_mii(dev); - - /* Read MAC Address from EEPROM */ - for (i = 0; i < 3; i++) - sp->station_addr[i] = read_eeprom(dev, 16 + i); - - for (i = 0; i < 3; i++) - ipg_w16(sp->station_addr[i], STATION_ADDRESS_0 + 2*i); - - /* Set station address in ethernet_device structure. */ - dev->dev_addr[0] = ipg_r16(STATION_ADDRESS_0) & 0x00ff; - dev->dev_addr[1] = (ipg_r16(STATION_ADDRESS_0) & 0xff00) >> 8; - dev->dev_addr[2] = ipg_r16(STATION_ADDRESS_1) & 0x00ff; - dev->dev_addr[3] = (ipg_r16(STATION_ADDRESS_1) & 0xff00) >> 8; - dev->dev_addr[4] = ipg_r16(STATION_ADDRESS_2) & 0x00ff; - dev->dev_addr[5] = (ipg_r16(STATION_ADDRESS_2) & 0xff00) >> 8; -out: - return rc; -} - -static int ipg_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = generic_mii_ioctl(&sp->mii_if, if_mii(ifr), cmd, NULL); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_nic_change_mtu(struct net_device *dev, int new_mtu) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int err; - - /* Function to accommodate changes to Maximum Transfer Unit - * (or MTU) of IPG NIC. Cannot use default function since - * the default will not allow for MTU > 1500 bytes. - */ - - IPG_DEBUG_MSG("_nic_change_mtu\n"); - - /* - * Check that the new MTU value is between 68 (14 byte header, 46 byte - * payload, 4 byte FCS) and 10 KB, which is the largest supported MTU. - */ - if (new_mtu < 68 || new_mtu > 10240) - return -EINVAL; - - err = ipg_nic_stop(dev); - if (err) - return err; - - dev->mtu = new_mtu; - - sp->max_rxframe_size = new_mtu; - - sp->rxfrag_size = new_mtu; - if (sp->rxfrag_size > 4088) - sp->rxfrag_size = 4088; - - sp->rxsupport_size = sp->max_rxframe_size; - - if (new_mtu > 0x0600) - sp->is_jumbo = true; - else - sp->is_jumbo = false; - - return ipg_nic_open(dev); -} - -static int ipg_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_ethtool_gset(&sp->mii_if, cmd); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_ethtool_sset(&sp->mii_if, cmd); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static int ipg_nway_reset(struct net_device *dev) -{ - struct ipg_nic_private *sp = netdev_priv(dev); - int rc; - - mutex_lock(&sp->mii_mutex); - rc = mii_nway_restart(&sp->mii_if); - mutex_unlock(&sp->mii_mutex); - - return rc; -} - -static const struct ethtool_ops ipg_ethtool_ops = { - .get_settings = ipg_get_settings, - .set_settings = ipg_set_settings, - .nway_reset = ipg_nway_reset, -}; - -static void ipg_remove(struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata(pdev); - struct ipg_nic_private *sp = netdev_priv(dev); - - IPG_DEBUG_MSG("_remove\n"); - - /* Un-register Ethernet device. */ - unregister_netdev(dev); - - pci_iounmap(pdev, sp->ioaddr); - - pci_release_regions(pdev); - - free_netdev(dev); - pci_disable_device(pdev); -} - -static const struct net_device_ops ipg_netdev_ops = { - .ndo_open = ipg_nic_open, - .ndo_stop = ipg_nic_stop, - .ndo_start_xmit = ipg_nic_hard_start_xmit, - .ndo_get_stats = ipg_nic_get_stats, - .ndo_set_rx_mode = ipg_nic_set_multicast_list, - .ndo_do_ioctl = ipg_ioctl, - .ndo_tx_timeout = ipg_tx_timeout, - .ndo_change_mtu = ipg_nic_change_mtu, - .ndo_set_mac_address = eth_mac_addr, - .ndo_validate_addr = eth_validate_addr, -}; - -static int ipg_probe(struct pci_dev *pdev, const struct pci_device_id *id) -{ - unsigned int i = id->driver_data; - struct ipg_nic_private *sp; - struct net_device *dev; - void __iomem *ioaddr; - int rc; - - rc = pci_enable_device(pdev); - if (rc < 0) - goto out; - - pr_info("%s: %s\n", pci_name(pdev), ipg_brand_name[i]); - - pci_set_master(pdev); - - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(40)); - if (rc < 0) { - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc < 0) { - pr_err("%s: DMA config failed\n", pci_name(pdev)); - goto err_disable_0; - } - } - - /* - * Initialize net device. - */ - dev = alloc_etherdev(sizeof(struct ipg_nic_private)); - if (!dev) { - rc = -ENOMEM; - goto err_disable_0; - } - - sp = netdev_priv(dev); - spin_lock_init(&sp->lock); - mutex_init(&sp->mii_mutex); - - sp->is_jumbo = IPG_IS_JUMBO; - sp->rxfrag_size = IPG_RXFRAG_SIZE; - sp->rxsupport_size = IPG_RXSUPPORT_SIZE; - sp->max_rxframe_size = IPG_MAX_RXFRAME_SIZE; - - /* Declare IPG NIC functions for Ethernet device methods. - */ - dev->netdev_ops = &ipg_netdev_ops; - SET_NETDEV_DEV(dev, &pdev->dev); - dev->ethtool_ops = &ipg_ethtool_ops; - - rc = pci_request_regions(pdev, DRV_NAME); - if (rc) - goto err_free_dev_1; - - ioaddr = pci_iomap(pdev, 1, pci_resource_len(pdev, 1)); - if (!ioaddr) { - pr_err("%s: cannot map MMIO\n", pci_name(pdev)); - rc = -EIO; - goto err_release_regions_2; - } - - /* Save the pointer to the PCI device information. */ - sp->ioaddr = ioaddr; - sp->pdev = pdev; - sp->dev = dev; - - INIT_DELAYED_WORK(&sp->task, ipg_reset_after_host_error); - - pci_set_drvdata(pdev, dev); - - rc = ipg_hw_init(dev); - if (rc < 0) - goto err_unmap_3; - - rc = register_netdev(dev); - if (rc < 0) - goto err_unmap_3; - - netdev_info(dev, "Ethernet device registered\n"); -out: - return rc; - -err_unmap_3: - pci_iounmap(pdev, ioaddr); -err_release_regions_2: - pci_release_regions(pdev); -err_free_dev_1: - free_netdev(dev); -err_disable_0: - pci_disable_device(pdev); - goto out; -} - -static struct pci_driver ipg_pci_driver = { - .name = IPG_DRIVER_NAME, - .id_table = ipg_pci_tbl, - .probe = ipg_probe, - .remove = ipg_remove, -}; - -module_pci_driver(ipg_pci_driver); diff --git a/drivers/net/ethernet/icplus/ipg.h b/drivers/net/ethernet/icplus/ipg.h deleted file mode 100644 index de60628..0000000 --- a/drivers/net/ethernet/icplus/ipg.h +++ /dev/null @@ -1,748 +0,0 @@ -/* - * Include file for Gigabit Ethernet device driver for Network - * Interface Cards (NICs) utilizing the Tamarack Microelectronics - * Inc. IPG Gigabit or Triple Speed Ethernet Media Access - * Controller. - */ -#ifndef __LINUX_IPG_H -#define __LINUX_IPG_H - -#include <linux/module.h> - -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/ioport.h> -#include <linux/errno.h> -#include <asm/io.h> -#include <linux/delay.h> -#include <linux/types.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <asm/bitops.h> - -/* - * Constants - */ - -/* GMII based PHY IDs */ -#define NS 0x2000 -#define MARVELL 0x0141 -#define ICPLUS_PHY 0x243 - -/* NIC Physical Layer Device MII register fields. */ -#define MII_PHY_SELECTOR_IEEE8023 0x0001 -#define MII_PHY_TECHABILITYFIELD 0x1FE0 - -/* GMII_PHY_1000 need to set to prefer master */ -#define GMII_PHY_1000BASETCONTROL_PreferMaster 0x0400 - -/* NIC Physical Layer Device GMII constants. */ -#define GMII_PREAMBLE 0xFFFFFFFF -#define GMII_ST 0x1 -#define GMII_READ 0x2 -#define GMII_WRITE 0x1 -#define GMII_TA_READ_MASK 0x1 -#define GMII_TA_WRITE 0x2 - -/* I/O register offsets. */ -enum ipg_regs { - DMA_CTRL = 0x00, - RX_DMA_STATUS = 0x08, /* Unused + reserved */ - TFD_LIST_PTR_0 = 0x10, - TFD_LIST_PTR_1 = 0x14, - TX_DMA_BURST_THRESH = 0x18, - TX_DMA_URGENT_THRESH = 0x19, - TX_DMA_POLL_PERIOD = 0x1a, - RFD_LIST_PTR_0 = 0x1c, - RFD_LIST_PTR_1 = 0x20, - RX_DMA_BURST_THRESH = 0x24, - RX_DMA_URGENT_THRESH = 0x25, - RX_DMA_POLL_PERIOD = 0x26, - DEBUG_CTRL = 0x2c, - ASIC_CTRL = 0x30, - FIFO_CTRL = 0x38, /* Unused */ - FLOW_OFF_THRESH = 0x3c, - FLOW_ON_THRESH = 0x3e, - EEPROM_DATA = 0x48, - EEPROM_CTRL = 0x4a, - EXPROM_ADDR = 0x4c, /* Unused */ - EXPROM_DATA = 0x50, /* Unused */ - WAKE_EVENT = 0x51, /* Unused */ - COUNTDOWN = 0x54, /* Unused */ - INT_STATUS_ACK = 0x5a, - INT_ENABLE = 0x5c, - INT_STATUS = 0x5e, /* Unused */ - TX_STATUS = 0x60, - MAC_CTRL = 0x6c, - VLAN_TAG = 0x70, /* Unused */ - PHY_SET = 0x75, - PHY_CTRL = 0x76, - STATION_ADDRESS_0 = 0x78, - STATION_ADDRESS_1 = 0x7a, - STATION_ADDRESS_2 = 0x7c, - MAX_FRAME_SIZE = 0x86, - RECEIVE_MODE = 0x88, - HASHTABLE_0 = 0x8c, - HASHTABLE_1 = 0x90, - RMON_STATISTICS_MASK = 0x98, - STATISTICS_MASK = 0x9c, - RX_JUMBO_FRAMES = 0xbc, /* Unused */ - TCP_CHECKSUM_ERRORS = 0xc0, /* Unused */ - IP_CHECKSUM_ERRORS = 0xc2, /* Unused */ - UDP_CHECKSUM_ERRORS = 0xc4, /* Unused */ - TX_JUMBO_FRAMES = 0xf4 /* Unused */ -}; - -/* Ethernet MIB statistic register offsets. */ -#define IPG_OCTETRCVOK 0xA8 -#define IPG_MCSTOCTETRCVDOK 0xAC -#define IPG_BCSTOCTETRCVOK 0xB0 -#define IPG_FRAMESRCVDOK 0xB4 -#define IPG_MCSTFRAMESRCVDOK 0xB8 -#define IPG_BCSTFRAMESRCVDOK 0xBE -#define IPG_MACCONTROLFRAMESRCVD 0xC6 -#define IPG_FRAMETOOLONGERRORS 0xC8 -#define IPG_INRANGELENGTHERRORS 0xCA -#define IPG_FRAMECHECKSEQERRORS 0xCC -#define IPG_FRAMESLOSTRXERRORS 0xCE -#define IPG_OCTETXMTOK 0xD0 -#define IPG_MCSTOCTETXMTOK 0xD4 -#define IPG_BCSTOCTETXMTOK 0xD8 -#define IPG_FRAMESXMTDOK 0xDC -#define IPG_MCSTFRAMESXMTDOK 0xE0 -#define IPG_FRAMESWDEFERREDXMT 0xE4 -#define IPG_LATECOLLISIONS 0xE8 -#define IPG_MULTICOLFRAMES 0xEC -#define IPG_SINGLECOLFRAMES 0xF0 -#define IPG_BCSTFRAMESXMTDOK 0xF6 -#define IPG_CARRIERSENSEERRORS 0xF8 -#define IPG_MACCONTROLFRAMESXMTDOK 0xFA -#define IPG_FRAMESABORTXSCOLLS 0xFC -#define IPG_FRAMESWEXDEFERRAL 0xFE - -/* RMON statistic register offsets. */ -#define IPG_ETHERSTATSCOLLISIONS 0x100 -#define IPG_ETHERSTATSOCTETSTRANSMIT 0x104 -#define IPG_ETHERSTATSPKTSTRANSMIT 0x108 -#define IPG_ETHERSTATSPKTS64OCTESTSTRANSMIT 0x10C -#define IPG_ETHERSTATSPKTS65TO127OCTESTSTRANSMIT 0x110 -#define IPG_ETHERSTATSPKTS128TO255OCTESTSTRANSMIT 0x114 -#define IPG_ETHERSTATSPKTS256TO511OCTESTSTRANSMIT 0x118 -#define IPG_ETHERSTATSPKTS512TO1023OCTESTSTRANSMIT 0x11C -#define IPG_ETHERSTATSPKTS1024TO1518OCTESTSTRANSMIT 0x120 -#define IPG_ETHERSTATSCRCALIGNERRORS 0x124 -#define IPG_ETHERSTATSUNDERSIZEPKTS 0x128 -#define IPG_ETHERSTATSFRAGMENTS 0x12C -#define IPG_ETHERSTATSJABBERS 0x130 -#define IPG_ETHERSTATSOCTETS 0x134 -#define IPG_ETHERSTATSPKTS 0x138 -#define IPG_ETHERSTATSPKTS64OCTESTS 0x13C -#define IPG_ETHERSTATSPKTS65TO127OCTESTS 0x140 -#define IPG_ETHERSTATSPKTS128TO255OCTESTS 0x144 -#define IPG_ETHERSTATSPKTS256TO511OCTESTS 0x148 -#define IPG_ETHERSTATSPKTS512TO1023OCTESTS 0x14C -#define IPG_ETHERSTATSPKTS1024TO1518OCTESTS 0x150 - -/* RMON statistic register equivalents. */ -#define IPG_ETHERSTATSMULTICASTPKTSTRANSMIT 0xE0 -#define IPG_ETHERSTATSBROADCASTPKTSTRANSMIT 0xF6 -#define IPG_ETHERSTATSMULTICASTPKTS 0xB8 -#define IPG_ETHERSTATSBROADCASTPKTS 0xBE -#define IPG_ETHERSTATSOVERSIZEPKTS 0xC8 -#define IPG_ETHERSTATSDROPEVENTS 0xCE - -/* Serial EEPROM offsets */ -#define IPG_EEPROM_CONFIGPARAM 0x00 -#define IPG_EEPROM_ASICCTRL 0x01 -#define IPG_EEPROM_SUBSYSTEMVENDORID 0x02 -#define IPG_EEPROM_SUBSYSTEMID 0x03 -#define IPG_EEPROM_STATIONADDRESS0 0x10 -#define IPG_EEPROM_STATIONADDRESS1 0x11 -#define IPG_EEPROM_STATIONADDRESS2 0x12 - -/* Register & data structure bit masks */ - -/* PCI register masks. */ - -/* IOBaseAddress */ -#define IPG_PIB_RSVD_MASK 0xFFFFFE01 -#define IPG_PIB_IOBASEADDRESS 0xFFFFFF00 -#define IPG_PIB_IOBASEADDRIND 0x00000001 - -/* MemBaseAddress */ -#define IPG_PMB_RSVD_MASK 0xFFFFFE07 -#define IPG_PMB_MEMBASEADDRIND 0x00000001 -#define IPG_PMB_MEMMAPTYPE 0x00000006 -#define IPG_PMB_MEMMAPTYPE0 0x00000002 -#define IPG_PMB_MEMMAPTYPE1 0x00000004 -#define IPG_PMB_MEMBASEADDRESS 0xFFFFFE00 - -/* ConfigStatus */ -#define IPG_CS_RSVD_MASK 0xFFB0 -#define IPG_CS_CAPABILITIES 0x0010 -#define IPG_CS_66MHZCAPABLE 0x0020 -#define IPG_CS_FASTBACK2BACK 0x0080 -#define IPG_CS_DATAPARITYREPORTED 0x0100 -#define IPG_CS_DEVSELTIMING 0x0600 -#define IPG_CS_SIGNALEDTARGETABORT 0x0800 -#define IPG_CS_RECEIVEDTARGETABORT 0x1000 -#define IPG_CS_RECEIVEDMASTERABORT 0x2000 -#define IPG_CS_SIGNALEDSYSTEMERROR 0x4000 -#define IPG_CS_DETECTEDPARITYERROR 0x8000 - -/* TFD data structure masks. */ - -/* TFDList, TFC */ -#define IPG_TFC_RSVD_MASK 0x0000FFFF9FFFFFFFULL -#define IPG_TFC_FRAMEID 0x000000000000FFFFULL -#define IPG_TFC_WORDALIGN 0x0000000000030000ULL -#define IPG_TFC_WORDALIGNTODWORD 0x0000000000000000ULL -#define IPG_TFC_WORDALIGNTOWORD 0x0000000000020000ULL -#define IPG_TFC_WORDALIGNDISABLED 0x0000000000030000ULL -#define IPG_TFC_TCPCHECKSUMENABLE 0x0000000000040000ULL -#define IPG_TFC_UDPCHECKSUMENABLE 0x0000000000080000ULL -#define IPG_TFC_IPCHECKSUMENABLE 0x0000000000100000ULL -#define IPG_TFC_FCSAPPENDDISABLE 0x0000000000200000ULL -#define IPG_TFC_TXINDICATE 0x0000000000400000ULL -#define IPG_TFC_TXDMAINDICATE 0x0000000000800000ULL -#define IPG_TFC_FRAGCOUNT 0x000000000F000000ULL -#define IPG_TFC_VLANTAGINSERT 0x0000000010000000ULL -#define IPG_TFC_TFDDONE 0x0000000080000000ULL -#define IPG_TFC_VID 0x00000FFF00000000ULL -#define IPG_TFC_CFI 0x0000100000000000ULL -#define IPG_TFC_USERPRIORITY 0x0000E00000000000ULL - -/* TFDList, FragInfo */ -#define IPG_TFI_RSVD_MASK 0xFFFF00FFFFFFFFFFULL -#define IPG_TFI_FRAGADDR 0x000000FFFFFFFFFFULL -#define IPG_TFI_FRAGLEN 0xFFFF000000000000ULL - -/* RFD data structure masks. */ - -/* RFDList, RFS */ -#define IPG_RFS_RSVD_MASK 0x0000FFFFFFFFFFFFULL -#define IPG_RFS_RXFRAMELEN 0x000000000000FFFFULL -#define IPG_RFS_RXFIFOOVERRUN 0x0000000000010000ULL -#define IPG_RFS_RXRUNTFRAME 0x0000000000020000ULL -#define IPG_RFS_RXALIGNMENTERROR 0x0000000000040000ULL -#define IPG_RFS_RXFCSERROR 0x0000000000080000ULL -#define IPG_RFS_RXOVERSIZEDFRAME 0x0000000000100000ULL -#define IPG_RFS_RXLENGTHERROR 0x0000000000200000ULL -#define IPG_RFS_VLANDETECTED 0x0000000000400000ULL -#define IPG_RFS_TCPDETECTED 0x0000000000800000ULL -#define IPG_RFS_TCPERROR 0x0000000001000000ULL -#define IPG_RFS_UDPDETECTED 0x0000000002000000ULL -#define IPG_RFS_UDPERROR 0x0000000004000000ULL -#define IPG_RFS_IPDETECTED 0x0000000008000000ULL -#define IPG_RFS_IPERROR 0x0000000010000000ULL -#define IPG_RFS_FRAMESTART 0x0000000020000000ULL -#define IPG_RFS_FRAMEEND 0x0000000040000000ULL -#define IPG_RFS_RFDDONE 0x0000000080000000ULL -#define IPG_RFS_TCI 0x0000FFFF00000000ULL - -/* RFDList, FragInfo */ -#define IPG_RFI_RSVD_MASK 0xFFFF00FFFFFFFFFFULL -#define IPG_RFI_FRAGADDR 0x000000FFFFFFFFFFULL -#define IPG_RFI_FRAGLEN 0xFFFF000000000000ULL - -/* I/O Register masks. */ - -/* RMON Statistics Mask */ -#define IPG_RZ_ALL 0x0FFFFFFF - -/* Statistics Mask */ -#define IPG_SM_ALL 0x0FFFFFFF -#define IPG_SM_OCTETRCVOK_FRAMESRCVDOK 0x00000001 -#define IPG_SM_MCSTOCTETRCVDOK_MCSTFRAMESRCVDOK 0x00000002 -#define IPG_SM_BCSTOCTETRCVDOK_BCSTFRAMESRCVDOK 0x00000004 -#define IPG_SM_RXJUMBOFRAMES 0x00000008 -#define IPG_SM_TCPCHECKSUMERRORS 0x00000010 -#define IPG_SM_IPCHECKSUMERRORS 0x00000020 -#define IPG_SM_UDPCHECKSUMERRORS 0x00000040 -#define IPG_SM_MACCONTROLFRAMESRCVD 0x00000080 -#define IPG_SM_FRAMESTOOLONGERRORS 0x00000100 -#define IPG_SM_INRANGELENGTHERRORS 0x00000200 -#define IPG_SM_FRAMECHECKSEQERRORS 0x00000400 -#define IPG_SM_FRAMESLOSTRXERRORS 0x00000800 -#define IPG_SM_OCTETXMTOK_FRAMESXMTOK 0x00001000 -#define IPG_SM_MCSTOCTETXMTOK_MCSTFRAMESXMTDOK 0x00002000 -#define IPG_SM_BCSTOCTETXMTOK_BCSTFRAMESXMTDOK 0x00004000 -#define IPG_SM_FRAMESWDEFERREDXMT 0x00008000 -#define IPG_SM_LATECOLLISIONS 0x00010000 -#define IPG_SM_MULTICOLFRAMES 0x00020000 -#define IPG_SM_SINGLECOLFRAMES 0x00040000 -#define IPG_SM_TXJUMBOFRAMES 0x00080000 -#define IPG_SM_CARRIERSENSEERRORS 0x00100000 -#define IPG_SM_MACCONTROLFRAMESXMTD 0x00200000 -#define IPG_SM_FRAMESABORTXSCOLLS 0x00400000 -#define IPG_SM_FRAMESWEXDEFERAL 0x00800000 - -/* Countdown */ -#define IPG_CD_RSVD_MASK 0x0700FFFF -#define IPG_CD_COUNT 0x0000FFFF -#define IPG_CD_COUNTDOWNSPEED 0x01000000 -#define IPG_CD_COUNTDOWNMODE 0x02000000 -#define IPG_CD_COUNTINTENABLED 0x04000000 - -/* TxDMABurstThresh */ -#define IPG_TB_RSVD_MASK 0xFF - -/* TxDMAUrgentThresh */ -#define IPG_TU_RSVD_MASK 0xFF - -/* TxDMAPollPeriod */ -#define IPG_TP_RSVD_MASK 0xFF - -/* RxDMAUrgentThresh */ -#define IPG_RU_RSVD_MASK 0xFF - -/* RxDMAPollPeriod */ -#define IPG_RP_RSVD_MASK 0xFF - -/* ReceiveMode */ -#define IPG_RM_RSVD_MASK 0x3F -#define IPG_RM_RECEIVEUNICAST 0x01 -#define IPG_RM_RECEIVEMULTICAST 0x02 -#define IPG_RM_RECEIVEBROADCAST 0x04 -#define IPG_RM_RECEIVEALLFRAMES 0x08 -#define IPG_RM_RECEIVEMULTICASTHASH 0x10 -#define IPG_RM_RECEIVEIPMULTICAST 0x20 - -/* PhySet */ -#define IPG_PS_MEM_LENB9B 0x01 -#define IPG_PS_MEM_LEN9 0x02 -#define IPG_PS_NON_COMPDET 0x04 - -/* PhyCtrl */ -#define IPG_PC_RSVD_MASK 0xFF -#define IPG_PC_MGMTCLK_LO 0x00 -#define IPG_PC_MGMTCLK_HI 0x01 -#define IPG_PC_MGMTCLK 0x01 -#define IPG_PC_MGMTDATA 0x02 -#define IPG_PC_MGMTDIR 0x04 -#define IPG_PC_DUPLEX_POLARITY 0x08 -#define IPG_PC_DUPLEX_STATUS 0x10 -#define IPG_PC_LINK_POLARITY 0x20 -#define IPG_PC_LINK_SPEED 0xC0 -#define IPG_PC_LINK_SPEED_10MBPS 0x40 -#define IPG_PC_LINK_SPEED_100MBPS 0x80 -#define IPG_PC_LINK_SPEED_1000MBPS 0xC0 - -/* DMACtrl */ -#define IPG_DC_RSVD_MASK 0xC07D9818 -#define IPG_DC_RX_DMA_COMPLETE 0x00000008 -#define IPG_DC_RX_DMA_POLL_NOW 0x00000010 -#define IPG_DC_TX_DMA_COMPLETE 0x00000800 -#define IPG_DC_TX_DMA_POLL_NOW 0x00001000 -#define IPG_DC_TX_DMA_IN_PROG 0x00008000 -#define IPG_DC_RX_EARLY_DISABLE 0x00010000 -#define IPG_DC_MWI_DISABLE 0x00040000 -#define IPG_DC_TX_WRITE_BACK_DISABLE 0x00080000 -#define IPG_DC_TX_BURST_LIMIT 0x00700000 -#define IPG_DC_TARGET_ABORT 0x40000000 -#define IPG_DC_MASTER_ABORT 0x80000000 - -/* ASICCtrl */ -#define IPG_AC_RSVD_MASK 0x07FFEFF2 -#define IPG_AC_EXP_ROM_SIZE 0x00000002 -#define IPG_AC_PHY_SPEED10 0x00000010 -#define IPG_AC_PHY_SPEED100 0x00000020 -#define IPG_AC_PHY_SPEED1000 0x00000040 -#define IPG_AC_PHY_MEDIA 0x00000080 -#define IPG_AC_FORCED_CFG 0x00000700 -#define IPG_AC_D3RESETDISABLE 0x00000800 -#define IPG_AC_SPEED_UP_MODE 0x00002000 -#define IPG_AC_LED_MODE 0x00004000 -#define IPG_AC_RST_OUT_POLARITY 0x00008000 -#define IPG_AC_GLOBAL_RESET 0x00010000 -#define IPG_AC_RX_RESET 0x00020000 -#define IPG_AC_TX_RESET 0x00040000 -#define IPG_AC_DMA 0x00080000 -#define IPG_AC_FIFO 0x00100000 -#define IPG_AC_NETWORK 0x00200000 -#define IPG_AC_HOST 0x00400000 -#define IPG_AC_AUTO_INIT 0x00800000 -#define IPG_AC_RST_OUT 0x01000000 -#define IPG_AC_INT_REQUEST 0x02000000 -#define IPG_AC_RESET_BUSY 0x04000000 -#define IPG_AC_LED_SPEED 0x08000000 -#define IPG_AC_LED_MODE_BIT_1 0x20000000 - -/* EepromCtrl */ -#define IPG_EC_RSVD_MASK 0x83FF -#define IPG_EC_EEPROM_ADDR 0x00FF -#define IPG_EC_EEPROM_OPCODE 0x0300 -#define IPG_EC_EEPROM_SUBCOMMAD 0x0000 -#define IPG_EC_EEPROM_WRITEOPCODE 0x0100 -#define IPG_EC_EEPROM_READOPCODE 0x0200 -#define IPG_EC_EEPROM_ERASEOPCODE 0x0300 -#define IPG_EC_EEPROM_BUSY 0x8000 - -/* FIFOCtrl */ -#define IPG_FC_RSVD_MASK 0xC001 -#define IPG_FC_RAM_TEST_MODE 0x0001 -#define IPG_FC_TRANSMITTING 0x4000 -#define IPG_FC_RECEIVING 0x8000 - -/* TxStatus */ -#define IPG_TS_RSVD_MASK 0xFFFF00DD -#define IPG_TS_TX_ERROR 0x00000001 -#define IPG_TS_LATE_COLLISION 0x00000004 -#define IPG_TS_TX_MAX_COLL 0x00000008 -#define IPG_TS_TX_UNDERRUN 0x00000010 -#define IPG_TS_TX_IND_REQD 0x00000040 -#define IPG_TS_TX_COMPLETE 0x00000080 -#define IPG_TS_TX_FRAMEID 0xFFFF0000 - -/* WakeEvent */ -#define IPG_WE_WAKE_PKT_ENABLE 0x01 -#define IPG_WE_MAGIC_PKT_ENABLE 0x02 -#define IPG_WE_LINK_EVT_ENABLE 0x04 -#define IPG_WE_WAKE_POLARITY 0x08 -#define IPG_WE_WAKE_PKT_EVT 0x10 -#define IPG_WE_MAGIC_PKT_EVT 0x20 -#define IPG_WE_LINK_EVT 0x40 -#define IPG_WE_WOL_ENABLE 0x80 - -/* IntEnable */ -#define IPG_IE_RSVD_MASK 0x1FFE -#define IPG_IE_HOST_ERROR 0x0002 -#define IPG_IE_TX_COMPLETE 0x0004 -#define IPG_IE_MAC_CTRL_FRAME 0x0008 -#define IPG_IE_RX_COMPLETE 0x0010 -#define IPG_IE_RX_EARLY 0x0020 -#define IPG_IE_INT_REQUESTED 0x0040 -#define IPG_IE_UPDATE_STATS 0x0080 -#define IPG_IE_LINK_EVENT 0x0100 -#define IPG_IE_TX_DMA_COMPLETE 0x0200 -#define IPG_IE_RX_DMA_COMPLETE 0x0400 -#define IPG_IE_RFD_LIST_END 0x0800 -#define IPG_IE_RX_DMA_PRIORITY 0x1000 - -/* IntStatus */ -#define IPG_IS_RSVD_MASK 0x1FFF -#define IPG_IS_INTERRUPT_STATUS 0x0001 -#define IPG_IS_HOST_ERROR 0x0002 -#define IPG_IS_TX_COMPLETE 0x0004 -#define IPG_IS_MAC_CTRL_FRAME 0x0008 -#define IPG_IS_RX_COMPLETE 0x0010 -#define IPG_IS_RX_EARLY 0x0020 -#define IPG_IS_INT_REQUESTED 0x0040 -#define IPG_IS_UPDATE_STATS 0x0080 -#define IPG_IS_LINK_EVENT 0x0100 -#define IPG_IS_TX_DMA_COMPLETE 0x0200 -#define IPG_IS_RX_DMA_COMPLETE 0x0400 -#define IPG_IS_RFD_LIST_END 0x0800 -#define IPG_IS_RX_DMA_PRIORITY 0x1000 - -/* MACCtrl */ -#define IPG_MC_RSVD_MASK 0x7FE33FA3 -#define IPG_MC_IFS_SELECT 0x00000003 -#define IPG_MC_IFS_4352BIT 0x00000003 -#define IPG_MC_IFS_1792BIT 0x00000002 -#define IPG_MC_IFS_1024BIT 0x00000001 -#define IPG_MC_IFS_96BIT 0x00000000 -#define IPG_MC_DUPLEX_SELECT 0x00000020 -#define IPG_MC_DUPLEX_SELECT_FD 0x00000020 -#define IPG_MC_DUPLEX_SELECT_HD 0x00000000 -#define IPG_MC_TX_FLOW_CONTROL_ENABLE 0x00000080 -#define IPG_MC_RX_FLOW_CONTROL_ENABLE 0x00000100 -#define IPG_MC_RCV_FCS 0x00000200 -#define IPG_MC_FIFO_LOOPBACK 0x00000400 -#define IPG_MC_MAC_LOOPBACK 0x00000800 -#define IPG_MC_AUTO_VLAN_TAGGING 0x00001000 -#define IPG_MC_AUTO_VLAN_UNTAGGING 0x00002000 -#define IPG_MC_COLLISION_DETECT 0x00010000 -#define IPG_MC_CARRIER_SENSE 0x00020000 -#define IPG_MC_STATISTICS_ENABLE 0x00200000 -#define IPG_MC_STATISTICS_DISABLE 0x00400000 -#define IPG_MC_STATISTICS_ENABLED 0x00800000 -#define IPG_MC_TX_ENABLE 0x01000000 -#define IPG_MC_TX_DISABLE 0x02000000 -#define IPG_MC_TX_ENABLED 0x04000000 -#define IPG_MC_RX_ENABLE 0x08000000 -#define IPG_MC_RX_DISABLE 0x10000000 -#define IPG_MC_RX_ENABLED 0x20000000 -#define IPG_MC_PAUSED 0x40000000 - -/* - * Tune - */ - -/* Assign IPG_APPEND_FCS_ON_TX > 0 for auto FCS append on TX. */ -#define IPG_APPEND_FCS_ON_TX 1 - -/* Assign IPG_APPEND_FCS_ON_TX > 0 for auto FCS strip on RX. */ -#define IPG_STRIP_FCS_ON_RX 1 - -/* Assign IPG_DROP_ON_RX_ETH_ERRORS > 0 to drop RX frames with - * Ethernet errors. - */ -#define IPG_DROP_ON_RX_ETH_ERRORS 1 - -/* Assign IPG_INSERT_MANUAL_VLAN_TAG > 0 to insert VLAN tags manually - * (via TFC). - */ -#define IPG_INSERT_MANUAL_VLAN_TAG 0 - -/* Assign IPG_ADD_IPCHECKSUM_ON_TX > 0 for auto IP checksum on TX. */ -#define IPG_ADD_IPCHECKSUM_ON_TX 0 - -/* Assign IPG_ADD_TCPCHECKSUM_ON_TX > 0 for auto TCP checksum on TX. - * DO NOT USE FOR SILICON REVISIONS B3 AND EARLIER. - */ -#define IPG_ADD_TCPCHECKSUM_ON_TX 0 - -/* Assign IPG_ADD_UDPCHECKSUM_ON_TX > 0 for auto UDP checksum on TX. - * DO NOT USE FOR SILICON REVISIONS B3 AND EARLIER. - */ -#define IPG_ADD_UDPCHECKSUM_ON_TX 0 - -/* If inserting VLAN tags manually, assign the IPG_MANUAL_VLAN_xx - * constants as desired. - */ -#define IPG_MANUAL_VLAN_VID 0xABC -#define IPG_MANUAL_VLAN_CFI 0x1 -#define IPG_MANUAL_VLAN_USERPRIORITY 0x5 - -#define IPG_IO_REG_RANGE 0xFF -#define IPG_MEM_REG_RANGE 0x154 -#define IPG_DRIVER_NAME "Sundance Technology IPG Triple-Speed Ethernet" -#define IPG_NIC_PHY_ADDRESS 0x01 -#define IPG_DMALIST_ALIGN_PAD 0x07 -#define IPG_MULTICAST_HASHTABLE_SIZE 0x40 - -/* Number of milliseconds to wait after issuing a software reset. - * 0x05 <= IPG_AC_RESETWAIT to account for proper 10Mbps operation. - */ -#define IPG_AC_RESETWAIT 0x05 - -/* Number of IPG_AC_RESETWAIT timeperiods before declaring timeout. */ -#define IPG_AC_RESET_TIMEOUT 0x0A - -/* Minimum number of nanoseconds used to toggle MDC clock during - * MII/GMII register access. - */ -#define IPG_PC_PHYCTRLWAIT_NS 200 - -#define IPG_TFDLIST_LENGTH 0x100 - -/* Number of frames between TxDMAComplete interrupt. - * 0 < IPG_FRAMESBETWEENTXDMACOMPLETES <= IPG_TFDLIST_LENGTH - */ -#define IPG_FRAMESBETWEENTXDMACOMPLETES 0x1 - -#define IPG_RFDLIST_LENGTH 0x100 - -/* Maximum number of RFDs to process per interrupt. - * 1 < IPG_MAXRFDPROCESS_COUNT < IPG_RFDLIST_LENGTH - */ -#define IPG_MAXRFDPROCESS_COUNT 0x80 - -/* Minimum margin between last freed RFD, and current RFD. - * 1 < IPG_MINUSEDRFDSTOFREE < IPG_RFDLIST_LENGTH - */ -#define IPG_MINUSEDRFDSTOFREE 0x80 - -/* specify the jumbo frame maximum size - * per unit is 0x600 (the rx_buffer size that one RFD can carry) - */ -#define MAX_JUMBOSIZE 0x8 /* max is 12K */ - -/* Key register values loaded at driver start up. */ - -/* TXDMAPollPeriod is specified in 320ns increments. - * - * Value Time - * --------------------- - * 0x00-0x01 320ns - * 0x03 ~1us - * 0x1F ~10us - * 0xFF ~82us - */ -#define IPG_TXDMAPOLLPERIOD_VALUE 0x26 - -/* TxDMAUrgentThresh specifies the minimum amount of - * data in the transmit FIFO before asserting an - * urgent transmit DMA request. - * - * Value Min TxFIFO occupied space before urgent TX request - * --------------------------------------------------------------- - * 0x00-0x04 128 bytes (1024 bits) - * 0x27 1248 bytes (~10000 bits) - * 0x30 1536 bytes (12288 bits) - * 0xFF 8192 bytes (65535 bits) - */ -#define IPG_TXDMAURGENTTHRESH_VALUE 0x04 - -/* TxDMABurstThresh specifies the minimum amount of - * free space in the transmit FIFO before asserting an - * transmit DMA request. - * - * Value Min TxFIFO free space before TX request - * ---------------------------------------------------- - * 0x00-0x08 256 bytes - * 0x30 1536 bytes - * 0xFF 8192 bytes - */ -#define IPG_TXDMABURSTTHRESH_VALUE 0x30 - -/* RXDMAPollPeriod is specified in 320ns increments. - * - * Value Time - * --------------------- - * 0x00-0x01 320ns - * 0x03 ~1us - * 0x1F ~10us - * 0xFF ~82us - */ -#define IPG_RXDMAPOLLPERIOD_VALUE 0x01 - -/* RxDMAUrgentThresh specifies the minimum amount of - * free space within the receive FIFO before asserting - * a urgent receive DMA request. - * - * Value Min RxFIFO free space before urgent RX request - * --------------------------------------------------------------- - * 0x00-0x04 128 bytes (1024 bits) - * 0x27 1248 bytes (~10000 bits) - * 0x30 1536 bytes (12288 bits) - * 0xFF 8192 bytes (65535 bits) - */ -#define IPG_RXDMAURGENTTHRESH_VALUE 0x30 - -/* RxDMABurstThresh specifies the minimum amount of - * occupied space within the receive FIFO before asserting - * a receive DMA request. - * - * Value Min TxFIFO free space before TX request - * ---------------------------------------------------- - * 0x00-0x08 256 bytes - * 0x30 1536 bytes - * 0xFF 8192 bytes - */ -#define IPG_RXDMABURSTTHRESH_VALUE 0x30 - -/* FlowOnThresh specifies the maximum amount of occupied - * space in the receive FIFO before a PAUSE frame with - * maximum pause time transmitted. - * - * Value Max RxFIFO occupied space before PAUSE - * --------------------------------------------------- - * 0x0000 0 bytes - * 0x0740 29,696 bytes - * 0x07FF 32,752 bytes - */ -#define IPG_FLOWONTHRESH_VALUE 0x0740 - -/* FlowOffThresh specifies the minimum amount of occupied - * space in the receive FIFO before a PAUSE frame with - * zero pause time is transmitted. - * - * Value Max RxFIFO occupied space before PAUSE - * --------------------------------------------------- - * 0x0000 0 bytes - * 0x00BF 3056 bytes - * 0x07FF 32,752 bytes - */ -#define IPG_FLOWOFFTHRESH_VALUE 0x00BF - -/* - * Miscellaneous macros. - */ - -/* Macros for printing debug statements. */ -#ifdef IPG_DEBUG -# define IPG_DEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DDEBUG_MSG(fmt, args...) \ - printk(KERN_DEBUG "IPG: " fmt, ##args) -# define IPG_DUMPRFDLIST(args) ipg_dump_rfdlist(args) -# define IPG_DUMPTFDLIST(args) ipg_dump_tfdlist(args) -#else -# define IPG_DEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DDEBUG_MSG(fmt, args...) \ -do { \ - if (0) \ - printk(KERN_DEBUG "IPG: " fmt, ##args); \ -} while (0) -# define IPG_DUMPRFDLIST(args) -# define IPG_DUMPTFDLIST(args) -#endif - -/* - * End miscellaneous macros. - */ - -/* Transmit Frame Descriptor. The IPG supports 15 fragments, - * however Linux requires only a single fragment. Note, each - * TFD field is 64 bits wide. - */ -struct ipg_tx { - __le64 next_desc; - __le64 tfc; - __le64 frag_info; -}; - -/* Receive Frame Descriptor. Note, each RFD field is 64 bits wide. - */ -struct ipg_rx { - __le64 next_desc; - __le64 rfs; - __le64 frag_info; -}; - -struct ipg_jumbo { - int found_start; - int current_size; - struct sk_buff *skb; -}; - -/* Structure of IPG NIC specific data. */ -struct ipg_nic_private { - void __iomem *ioaddr; - struct ipg_tx *txd; - struct ipg_rx *rxd; - dma_addr_t txd_map; - dma_addr_t rxd_map; - struct sk_buff *tx_buff[IPG_TFDLIST_LENGTH]; - struct sk_buff *rx_buff[IPG_RFDLIST_LENGTH]; - unsigned int tx_current; - unsigned int tx_dirty; - unsigned int rx_current; - unsigned int rx_dirty; - bool is_jumbo; - struct ipg_jumbo jumbo; - unsigned long rxfrag_size; - unsigned long rxsupport_size; - unsigned long max_rxframe_size; - unsigned int rx_buf_sz; - struct pci_dev *pdev; - struct net_device *dev; - struct net_device_stats stats; - spinlock_t lock; - int tenmbpsmode; - - u16 led_mode; - u16 station_addr[3]; /* Station Address in EEPROM Reg 0x10..0x12 */ - - struct mutex mii_mutex; - struct mii_if_info mii_if; - int reset_current_tfd; -#ifdef IPG_DEBUG - int RFDlistendCount; - int RFDListCheckedCount; - int EmptyRFDListCount; -#endif - struct delayed_work task; -}; - -#endif /* __LINUX_IPG_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 85f1b1e..31c491e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -892,9 +892,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn; dev->caps.port_mask[i] = dev->caps.port_type[i]; dev->caps.phys_port_id[i] = func_cap.phys_port_id; - if (mlx4_get_slave_pkey_gid_tbl_len(dev, i, - &dev->caps.gid_table_len[i], - &dev->caps.pkey_table_len[i])) + err = mlx4_get_slave_pkey_gid_tbl_len(dev, i, + &dev->caps.gid_table_len[i], + &dev->caps.pkey_table_len[i]); + if (err) goto err_mem; } @@ -906,6 +907,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.uar_page_size * dev->caps.num_uars, (unsigned long long) pci_resource_len(dev->persist->pdev, 2)); + err = -ENOMEM; goto err_mem; } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 9813d34..6fec3e9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -4952,26 +4952,41 @@ static void rem_slave_counters(struct mlx4_dev *dev, int slave) struct res_counter *counter; struct res_counter *tmp; int err; - int index; + int *counters_arr = NULL; + int i, j; err = move_all_busy(dev, slave, RES_COUNTER); if (err) mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n", slave); - spin_lock_irq(mlx4_tlock(dev)); - list_for_each_entry_safe(counter, tmp, counter_list, com.list) { - if (counter->com.owner == slave) { - index = counter->com.res_id; - rb_erase(&counter->com.node, - &tracker->res_tree[RES_COUNTER]); - list_del(&counter->com.list); - kfree(counter); - __mlx4_counter_free(dev, index); + counters_arr = kmalloc_array(dev->caps.max_counters, + sizeof(*counters_arr), GFP_KERNEL); + if (!counters_arr) + return; + + do { + i = 0; + j = 0; + spin_lock_irq(mlx4_tlock(dev)); + list_for_each_entry_safe(counter, tmp, counter_list, com.list) { + if (counter->com.owner == slave) { + counters_arr[i++] = counter->com.res_id; + rb_erase(&counter->com.node, + &tracker->res_tree[RES_COUNTER]); + list_del(&counter->com.list); + kfree(counter); + } + } + spin_unlock_irq(mlx4_tlock(dev)); + + while (j < i) { + __mlx4_counter_free(dev, counters_arr[j++]); mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0); } - } - spin_unlock_irq(mlx4_tlock(dev)); + } while (i); + + kfree(counters_arr); } static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f2ae62d..22e72bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -334,9 +334,15 @@ struct mlx5e_tx_skb_cb { #define MLX5E_TX_SKB_CB(__skb) ((struct mlx5e_tx_skb_cb *)__skb->cb) +enum mlx5e_dma_map_type { + MLX5E_DMA_MAP_SINGLE, + MLX5E_DMA_MAP_PAGE +}; + struct mlx5e_sq_dma { - dma_addr_t addr; - u32 size; + dma_addr_t addr; + u32 size; + enum mlx5e_dma_map_type type; }; enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5fc4d2d..1e52db3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1332,6 +1332,42 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) return err; } +static int mlx5e_refresh_tir_self_loopback_enable(struct mlx5_core_dev *mdev, + u32 tirn) +{ + void *in; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); + + err = mlx5_core_modify_tir(mdev, tirn, in, inlen); + + kvfree(in); + + return err; +} + +static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv) +{ + int err; + int i; + + for (i = 0; i < MLX5E_NUM_TT; i++) { + err = mlx5e_refresh_tir_self_loopback_enable(priv->mdev, + priv->tirn[i]); + if (err) + return err; + } + + return 0; +} + static int mlx5e_set_dev_port_mtu(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -1376,6 +1412,13 @@ int mlx5e_open_locked(struct net_device *netdev) goto err_clear_state_opened_flag; } + err = mlx5e_refresh_tirs_self_loopback_enable(priv); + if (err) { + netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n", + __func__, err); + goto err_close_channels; + } + mlx5e_update_carrier(priv); mlx5e_redirect_rqts(priv); @@ -1383,6 +1426,8 @@ int mlx5e_open_locked(struct net_device *netdev) return 0; +err_close_channels: + mlx5e_close_channels(priv); err_clear_state_opened_flag: clear_bit(MLX5E_STATE_OPENED, &priv->state); return err; @@ -1856,6 +1901,8 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + max_mtu = MLX5E_HW2SW_MTU(max_mtu); + if (new_mtu > max_mtu) { netdev_err(netdev, "%s: Bad MTU (%d) > (%d) Max\n", @@ -1909,6 +1956,9 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) "Not creating net device, some required device capabilities are missing\n"); return -ENOTSUPP; } + if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) + mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index cd8f85a..1341b1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -61,39 +61,47 @@ void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw) } } -static void mlx5e_dma_pop_last_pushed(struct mlx5e_sq *sq, dma_addr_t *addr, - u32 *size) +static inline void mlx5e_tx_dma_unmap(struct device *pdev, + struct mlx5e_sq_dma *dma) { - sq->dma_fifo_pc--; - *addr = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr; - *size = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size; -} - -static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) -{ - dma_addr_t addr; - u32 size; - int i; - - for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { - mlx5e_dma_pop_last_pushed(sq, &addr, &size); - dma_unmap_single(sq->pdev, addr, size, DMA_TO_DEVICE); + switch (dma->type) { + case MLX5E_DMA_MAP_SINGLE: + dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + break; + case MLX5E_DMA_MAP_PAGE: + dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE); + break; + default: + WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n"); } } -static inline void mlx5e_dma_push(struct mlx5e_sq *sq, dma_addr_t addr, - u32 size) +static inline void mlx5e_dma_push(struct mlx5e_sq *sq, + dma_addr_t addr, + u32 size, + enum mlx5e_dma_map_type map_type) { sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr = addr; sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size = size; + sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].type = map_type; sq->dma_fifo_pc++; } -static inline void mlx5e_dma_get(struct mlx5e_sq *sq, u32 i, dma_addr_t *addr, - u32 *size) +static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_sq *sq, u32 i) { - *addr = sq->dma_fifo[i & sq->dma_fifo_mask].addr; - *size = sq->dma_fifo[i & sq->dma_fifo_mask].size; + return &sq->dma_fifo[i & sq->dma_fifo_mask]; +} + +static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb) +{ + int i; + + for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) { + struct mlx5e_sq_dma *last_pushed_dma = + mlx5e_dma_get(sq, --sq->dma_fifo_pc); + + mlx5e_tx_dma_unmap(sq->pdev, last_pushed_dma); + } } u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, @@ -118,8 +126,15 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, */ #define MLX5E_MIN_INLINE ETH_HLEN - if (bf && (skb_headlen(skb) <= sq->max_inline)) - return skb_headlen(skb); + if (bf) { + u16 ihs = skb_headlen(skb); + + if (skb_vlan_tag_present(skb)) + ihs += VLAN_HLEN; + + if (ihs <= sq->max_inline) + return skb_headlen(skb); + } return MLX5E_MIN_INLINE; } @@ -218,7 +233,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(headlen); - mlx5e_dma_push(sq, dma_addr, headlen); + mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE); MLX5E_TX_SKB_CB(skb)->num_dma++; dseg++; @@ -237,7 +252,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(fsz); - mlx5e_dma_push(sq, dma_addr, fsz); + mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); MLX5E_TX_SKB_CB(skb)->num_dma++; dseg++; @@ -353,13 +368,10 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) } for (j = 0; j < MLX5E_TX_SKB_CB(skb)->num_dma; j++) { - dma_addr_t addr; - u32 size; + struct mlx5e_sq_dma *dma = + mlx5e_dma_get(sq, dma_fifo_cc++); - mlx5e_dma_get(sq, dma_fifo_cc, &addr, &size); - dma_fifo_cc++; - dma_unmap_single(sq->pdev, addr, size, - DMA_TO_DEVICE); + mlx5e_tx_dma_unmap(sq->pdev, dma); } npkts++; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b4f2123..79ef799 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7429,15 +7429,15 @@ process_pkt: rtl8169_rx_vlan_tag(desc, skb); + if (skb->pkt_type == PACKET_MULTICAST) + dev->stats.multicast++; + napi_gro_receive(&tp->napi, skb); u64_stats_update_begin(&tp->rx_stats.syncp); tp->rx_stats.packets++; tp->rx_stats.bytes += pkt_size; u64_stats_update_end(&tp->rx_stats.syncp); - - if (skb->pkt_type == PACKET_MULTICAST) - dev->stats.multicast++; } release_descriptor: desc->opts2 = 0; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index aa7b208..ee8d1ec 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -408,8 +408,6 @@ static int ravb_dmac_init(struct net_device *ndev) /* Interrupt enable: */ /* Frame receive */ ravb_write(ndev, RIC0_FRE0 | RIC0_FRE1, RIC0); - /* Receive FIFO full warning */ - ravb_write(ndev, RIC1_RFWE, RIC1); /* Receive FIFO full error, descriptor empty */ ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2); /* Frame transmitted, timestamp FIFO updated */ @@ -733,8 +731,10 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id) ((tis & tic) & BIT(q))) { if (napi_schedule_prep(&priv->napi[q])) { /* Mask RX and TX interrupts */ - ravb_write(ndev, ric0 & ~BIT(q), RIC0); - ravb_write(ndev, tic & ~BIT(q), TIC); + ric0 &= ~BIT(q); + tic &= ~BIT(q); + ravb_write(ndev, ric0, RIC0); + ravb_write(ndev, tic, TIC); __napi_schedule(&priv->napi[q]); } else { netdev_warn(ndev, diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index d288f1c..a3c42a3 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -3422,7 +3422,7 @@ out: * with our request for slot reset the mmio_enabled callback will never be * called, and the link_reset callback is not used by AER or EEH mechanisms. */ -static struct pci_error_handlers efx_err_handlers = { +static const struct pci_error_handlers efx_err_handlers = { .error_detected = efx_io_error_detected, .slot_reset = efx_io_slot_reset, .resume = efx_io_resume, diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index c860c90..219a99b 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -809,22 +809,17 @@ static int smsc911x_phy_check_loopbackpkt(struct smsc911x_data *pdata) static int smsc911x_phy_reset(struct smsc911x_data *pdata) { - struct phy_device *phy_dev = pdata->phy_dev; unsigned int temp; unsigned int i = 100000; - BUG_ON(!phy_dev); - BUG_ON(!phy_dev->bus); - - SMSC_TRACE(pdata, hw, "Performing PHY BCR Reset"); - smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, BMCR_RESET); + temp = smsc911x_reg_read(pdata, PMT_CTRL); + smsc911x_reg_write(pdata, PMT_CTRL, temp | PMT_CTRL_PHY_RST_); do { msleep(1); - temp = smsc911x_mii_read(phy_dev->bus, phy_dev->addr, - MII_BMCR); - } while ((i--) && (temp & BMCR_RESET)); + temp = smsc911x_reg_read(pdata, PMT_CTRL); + } while ((i--) && (temp & PMT_CTRL_PHY_RST_)); - if (temp & BMCR_RESET) { + if (unlikely(temp & PMT_CTRL_PHY_RST_)) { SMSC_WARN(pdata, hw, "PHY reset failed to complete"); return -EIO; } @@ -2296,7 +2291,7 @@ static int smsc911x_init(struct net_device *dev) } /* Reset the LAN911x */ - if (smsc911x_soft_reset(pdata)) + if (smsc911x_phy_reset(pdata) || smsc911x_soft_reset(pdata)) return -ENODEV; dev->flags |= IFF_MULTICAST; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 9d89bdb..82de68b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -337,11 +337,11 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) QSGMII_PHY_RX_SIGNAL_DETECT_EN | QSGMII_PHY_TX_DRIVER_EN | QSGMII_PHY_QSGMII_EN | - 0x4 << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | - 0x3 << QSGMII_PHY_RX_DC_BIAS_OFFSET | - 0x1 << QSGMII_PHY_RX_INPUT_EQU_OFFSET | - 0x2 << QSGMII_PHY_CDR_PI_SLEW_OFFSET | - 0xC << QSGMII_PHY_TX_DRV_AMP_OFFSET); + 0x4ul << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | + 0x3ul << QSGMII_PHY_RX_DC_BIAS_OFFSET | + 0x1ul << QSGMII_PHY_RX_INPUT_EQU_OFFSET | + 0x2ul << QSGMII_PHY_CDR_PI_SLEW_OFFSET | + 0xCul << QSGMII_PHY_TX_DRV_AMP_OFFSET); } plat_dat->has_gmac = true; diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index ae68afd..f38696c 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -345,13 +345,6 @@ VELOCITY_PARAM(flow_control, "Enable flow control ability"); */ VELOCITY_PARAM(speed_duplex, "Setting the speed and duplex mode"); -#define VAL_PKT_LEN_DEF 0 -/* ValPktLen[] is used for setting the checksum offload ability of NIC. - 0: Receive frame with invalid layer 2 length (Default) - 1: Drop frame with invalid layer 2 length -*/ -VELOCITY_PARAM(ValPktLen, "Receiving or Drop invalid 802.3 frame"); - #define WOL_OPT_DEF 0 #define WOL_OPT_MIN 0 #define WOL_OPT_MAX 7 @@ -494,7 +487,6 @@ static void velocity_get_options(struct velocity_opt *opts, int index, velocity_set_int_opt(&opts->flow_cntl, flow_control[index], FLOW_CNTL_MIN, FLOW_CNTL_MAX, FLOW_CNTL_DEF, "flow_control", devname); velocity_set_bool_opt(&opts->flags, IP_byte_align[index], IP_ALIG_DEF, VELOCITY_FLAGS_IP_ALIGN, "IP_byte_align", devname); - velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname); velocity_set_int_opt((int *) &opts->spd_dpx, speed_duplex[index], MED_LNK_MIN, MED_LNK_MAX, MED_LNK_DEF, "Media link mode", devname); velocity_set_int_opt(&opts->wol_opts, wol_opts[index], WOL_OPT_MIN, WOL_OPT_MAX, WOL_OPT_DEF, "Wake On Lan options", devname); opts->numrx = (opts->numrx & ~3); @@ -2055,8 +2047,9 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) int pkt_len = le16_to_cpu(rd->rdesc0.len) & 0x3fff; struct sk_buff *skb; - if (rd->rdesc0.RSR & (RSR_STP | RSR_EDP)) { - VELOCITY_PRT(MSG_LEVEL_VERBOSE, KERN_ERR " %s : the received frame spans multiple RDs.\n", vptr->netdev->name); + if (unlikely(rd->rdesc0.RSR & (RSR_STP | RSR_EDP | RSR_RL))) { + if (rd->rdesc0.RSR & (RSR_STP | RSR_EDP)) + VELOCITY_PRT(MSG_LEVEL_VERBOSE, KERN_ERR " %s : the received frame spans multiple RDs.\n", vptr->netdev->name); stats->rx_length_errors++; return -EINVAL; } @@ -2069,17 +2062,6 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) dma_sync_single_for_cpu(vptr->dev, rd_info->skb_dma, vptr->rx.buf_sz, DMA_FROM_DEVICE); - /* - * Drop frame not meeting IEEE 802.3 - */ - - if (vptr->flags & VELOCITY_FLAGS_VAL_PKT_LEN) { - if (rd->rdesc0.RSR & RSR_RL) { - stats->rx_length_errors++; - return -EINVAL; - } - } - velocity_rx_csum(rd, skb); if (velocity_rx_copy(&skb, pkt_len, vptr) < 0) { diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index bb8b530..b103adb 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -599,7 +599,7 @@ int fjes_hw_unregister_buff_addr(struct fjes_hw *hw, int dest_epid) FJES_CMD_REQ_RES_CODE_BUSY) && (timeout > 0)) { msleep(200 + hw->my_epid * 20); - timeout -= (200 + hw->my_epid * 20); + timeout -= (200 + hw->my_epid * 20); res_buf->unshare_buffer.length = 0; res_buf->unshare_buffer.code = 0; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index d50887e..8c48bb2 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -254,7 +254,7 @@ acct: } } -static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, +static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb, bool local) { struct ipvl_dev *ipvlan = addr->master; @@ -262,6 +262,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, unsigned int len; rx_handler_result_t ret = RX_HANDLER_CONSUMED; bool success = false; + struct sk_buff *skb = *pskb; len = skb->len + ETH_HLEN; if (unlikely(!(dev->flags & IFF_UP))) { @@ -273,6 +274,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff *skb, if (!skb) goto out; + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; @@ -486,7 +488,7 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) - return ipvlan_rcv_frame(addr, skb, true); + return ipvlan_rcv_frame(addr, &skb, true); out: skb->dev = ipvlan->phy_dev; @@ -506,7 +508,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); if (addr) - return ipvlan_rcv_frame(addr, skb, true); + return ipvlan_rcv_frame(addr, &skb, true); } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) @@ -589,7 +591,7 @@ static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb, addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) - ret = ipvlan_rcv_frame(addr, skb, false); + ret = ipvlan_rcv_frame(addr, pskb, false); out: return ret; @@ -626,7 +628,7 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); if (addr) - ret = ipvlan_rcv_frame(addr, skb, false); + ret = ipvlan_rcv_frame(addr, pskb, false); } return ret; @@ -651,5 +653,5 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) WARN_ONCE(true, "ipvlan_handle_frame() called for mode = [%hx]\n", port->mode); kfree_skb(skb); - return NET_RX_DROP; + return RX_HANDLER_CONSUMED; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 86f6c62..06c8bfe 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -415,6 +415,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; + *pskb = skb; eth = eth_hdr(skb); macvlan_forward_source(skb, port, eth->h_source); src = macvlan_hash_lookup(port, eth->h_source); @@ -456,6 +457,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) goto out; } + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index fabf11d..2d020a3 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -308,6 +308,8 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_HAS_INTERRUPT, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, .driver = { .owner = THIS_MODULE, }, @@ -327,6 +329,8 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_HAS_INTERRUPT, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, + .ack_interrupt = at803x_ack_interrupt, + .config_intr = at803x_config_intr, .driver = { .owner = THIS_MODULE, }, diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 5de8d58..0240552 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1154,6 +1154,21 @@ static struct phy_driver marvell_drivers[] = { .driver = { .owner = THIS_MODULE }, }, { + .phy_id = MARVELL_PHY_ID_88E1540, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "Marvell 88E1540", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_aneg = &m88e1510_config_aneg, + .read_status = &marvell_read_status, + .ack_interrupt = &marvell_ack_interrupt, + .config_intr = &marvell_config_intr, + .did_interrupt = &m88e1121_did_interrupt, + .resume = &genphy_resume, + .suspend = &genphy_suspend, + .driver = { .owner = THIS_MODULE }, + }, + { .phy_id = MARVELL_PHY_ID_88E3016, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E3016", @@ -1186,6 +1201,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1318S, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1116R, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1510, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1540, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index adb48ab..48ce6ef 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -863,6 +863,9 @@ void phy_state_machine(struct work_struct *work) needs_aneg = true; break; case PHY_NOLINK: + if (phy_interrupt_is_valid(phydev)) + break; + err = phy_read_status(phydev); if (err) break; diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 76cad71..dd295db 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -66,6 +66,7 @@ #define PHY_ID_VSC8244 0x000fc6c0 #define PHY_ID_VSC8514 0x00070670 #define PHY_ID_VSC8574 0x000704a0 +#define PHY_ID_VSC8601 0x00070420 #define PHY_ID_VSC8662 0x00070660 #define PHY_ID_VSC8221 0x000fc550 #define PHY_ID_VSC8211 0x000fc4b0 @@ -133,7 +134,8 @@ static int vsc82xx_config_intr(struct phy_device *phydev) (phydev->drv->phy_id == PHY_ID_VSC8234 || phydev->drv->phy_id == PHY_ID_VSC8244 || phydev->drv->phy_id == PHY_ID_VSC8514 || - phydev->drv->phy_id == PHY_ID_VSC8574) ? + phydev->drv->phy_id == PHY_ID_VSC8574 || + phydev->drv->phy_id == PHY_ID_VSC8601) ? MII_VSC8244_IMASK_MASK : MII_VSC8221_IMASK_MASK); else { @@ -272,6 +274,18 @@ static struct phy_driver vsc82xx_driver[] = { .config_intr = &vsc82xx_config_intr, .driver = { .owner = THIS_MODULE,}, }, { + .phy_id = PHY_ID_VSC8601, + .name = "Vitesse VSC8601", + .phy_id_mask = 0x000ffff0, + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = &genphy_config_init, + .config_aneg = &genphy_config_aneg, + .read_status = &genphy_read_status, + .ack_interrupt = &vsc824x_ack_interrupt, + .config_intr = &vsc82xx_config_intr, + .driver = { .owner = THIS_MODULE,}, +}, { .phy_id = PHY_ID_VSC8662, .name = "Vitesse VSC8662", .phy_id_mask = 0x000ffff0, diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c78d3cb..3da70bf 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -696,6 +696,11 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (kernel_ulong_t) &wwan_info, }, { + /* Dell DW5580 modules */ + USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, 0x81ba, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = (kernel_ulong_t)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 46f4cad..899ea42 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2157,12 +2157,13 @@ vmxnet3_set_mc(struct net_device *netdev) if (!netdev_mc_empty(netdev)) { new_table = vmxnet3_copy_mc(netdev); if (new_table) { - rxConf->mfTableLen = cpu_to_le16( - netdev_mc_count(netdev) * ETH_ALEN); + size_t sz = netdev_mc_count(netdev) * ETH_ALEN; + + rxConf->mfTableLen = cpu_to_le16(sz); new_table_pa = dma_map_single( &adapter->pdev->dev, new_table, - rxConf->mfTableLen, + sz, PCI_DMA_TODEVICE); } diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 3f859a5..4c58c83 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.3.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.4.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040300 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040400 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index e735c72..edb1984 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1685,8 +1685,8 @@ static void pci_dma_configure(struct pci_dev *dev) { struct device *bridge = pci_get_host_bridge_device(dev); - if (IS_ENABLED(CONFIG_OF) && dev->dev.of_node) { - if (bridge->parent) + if (IS_ENABLED(CONFIG_OF) && + bridge->parent && bridge->parent->of_node) { of_dma_configure(&dev->dev, bridge->parent->of_node); } else if (has_acpi_companion(bridge)) { struct acpi_device *adev = to_acpi_device_node(bridge->fwnode); diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 548a189..a831d18 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -1080,28 +1080,10 @@ void __init chsc_init_cleanup(void) free_page((unsigned long)sei_page); } -int chsc_enable_facility(int operation_code) +int __chsc_enable_facility(struct chsc_sda_area *sda_area, int operation_code) { - unsigned long flags; int ret; - struct { - struct chsc_header request; - u8 reserved1:4; - u8 format:4; - u8 reserved2; - u16 operation_code; - u32 reserved3; - u32 reserved4; - u32 operation_data_area[252]; - struct chsc_header response; - u32 reserved5:4; - u32 format2:4; - u32 reserved6:24; - } __attribute__ ((packed)) *sda_area; - spin_lock_irqsave(&chsc_page_lock, flags); - memset(chsc_page, 0, PAGE_SIZE); - sda_area = chsc_page; sda_area->request.length = 0x0400; sda_area->request.code = 0x0031; sda_area->operation_code = operation_code; @@ -1119,10 +1101,25 @@ int chsc_enable_facility(int operation_code) default: ret = chsc_error_from_response(sda_area->response.code); } +out: + return ret; +} + +int chsc_enable_facility(int operation_code) +{ + struct chsc_sda_area *sda_area; + unsigned long flags; + int ret; + + spin_lock_irqsave(&chsc_page_lock, flags); + memset(chsc_page, 0, PAGE_SIZE); + sda_area = chsc_page; + + ret = __chsc_enable_facility(sda_area, operation_code); if (ret != 0) CIO_CRW_EVENT(2, "chsc: sda (oc=%x) failed (rc=%04x)\n", operation_code, sda_area->response.code); -out: + spin_unlock_irqrestore(&chsc_page_lock, flags); return ret; } diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h index 76c9b50..0de134c 100644 --- a/drivers/s390/cio/chsc.h +++ b/drivers/s390/cio/chsc.h @@ -115,6 +115,20 @@ struct chsc_scpd { u8 data[PAGE_SIZE - 20]; } __attribute__ ((packed)); +struct chsc_sda_area { + struct chsc_header request; + u8 :4; + u8 format:4; + u8 :8; + u16 operation_code; + u32 :32; + u32 :32; + u32 operation_data_area[252]; + struct chsc_header response; + u32 :4; + u32 format2:4; + u32 :24; +} __packed __aligned(PAGE_SIZE); extern int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd); @@ -122,6 +136,7 @@ extern int chsc_determine_css_characteristics(void); extern int chsc_init(void); extern void chsc_init_cleanup(void); +int __chsc_enable_facility(struct chsc_sda_area *sda_area, int operation_code); extern int chsc_enable_facility(int); struct channel_subsystem; extern int chsc_secm(struct channel_subsystem *, int); diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index b5620e8..690b854 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -925,18 +925,32 @@ void reipl_ccw_dev(struct ccw_dev_id *devid) int __init cio_get_iplinfo(struct cio_iplinfo *iplinfo) { + static struct chsc_sda_area sda_area __initdata; struct subchannel_id schid; struct schib schib; schid = *(struct subchannel_id *)&S390_lowcore.subchannel_id; if (!schid.one) return -ENODEV; + + if (schid.ssid) { + /* + * Firmware should have already enabled MSS but whoever started + * the kernel might have initiated a channel subsystem reset. + * Ensure that MSS is enabled. + */ + memset(&sda_area, 0, sizeof(sda_area)); + if (__chsc_enable_facility(&sda_area, CHSC_SDA_OC_MSS)) + return -ENODEV; + } if (stsch_err(schid, &schib)) return -ENODEV; if (schib.pmcw.st != SUBCHANNEL_TYPE_IO) return -ENODEV; if (!schib.pmcw.dnv) return -ENODEV; + + iplinfo->ssid = schid.ssid; iplinfo->devno = schib.pmcw.dev; iplinfo->is_qdio = schib.pmcw.qf; return 0; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 2ee3053..489e703 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -702,17 +702,12 @@ css_generate_pgid(struct channel_subsystem *css, u32 tod_high) css->global_pgid.pgid_high.ext_cssid.version = 0x80; css->global_pgid.pgid_high.ext_cssid.cssid = css->cssid; } else { -#ifdef CONFIG_SMP css->global_pgid.pgid_high.cpu_addr = stap(); -#else - css->global_pgid.pgid_high.cpu_addr = 0; -#endif } get_cpu_id(&cpu_id); css->global_pgid.cpu_id = cpu_id.ident; css->global_pgid.cpu_model = cpu_id.machine; css->global_pgid.tod_high = tod_high; - } static void diff --git a/drivers/s390/crypto/Makefile b/drivers/s390/crypto/Makefile index 57f710b..b8ab186 100644 --- a/drivers/s390/crypto/Makefile +++ b/drivers/s390/crypto/Makefile @@ -3,6 +3,9 @@ # ap-objs := ap_bus.o -obj-$(CONFIG_ZCRYPT) += ap.o zcrypt_api.o zcrypt_pcixcc.o -obj-$(CONFIG_ZCRYPT) += zcrypt_cex2a.o zcrypt_cex4.o +# zcrypt_api depends on ap +obj-$(CONFIG_ZCRYPT) += ap.o zcrypt_api.o +# msgtype* depend on zcrypt_api obj-$(CONFIG_ZCRYPT) += zcrypt_msgtype6.o zcrypt_msgtype50.o +# adapter drivers depend on ap, zcrypt_api and msgtype* +obj-$(CONFIG_ZCRYPT) += zcrypt_pcixcc.o zcrypt_cex2a.o zcrypt_cex4.o diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 9cb3dfb..61f7685 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -74,6 +74,7 @@ static struct device *ap_root_device = NULL; static struct ap_config_info *ap_configuration; static DEFINE_SPINLOCK(ap_device_list_lock); static LIST_HEAD(ap_device_list); +static bool initialised; /* * Workqueue timer for bus rescan. @@ -1384,6 +1385,9 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner, { struct device_driver *drv = &ap_drv->driver; + if (!initialised) + return -ENODEV; + drv->bus = &ap_bus_type; drv->probe = ap_device_probe; drv->remove = ap_device_remove; @@ -1808,6 +1812,7 @@ int __init ap_module_init(void) goto out_pm; queue_work(system_long_wq, &ap_scan_work); + initialised = true; return 0; @@ -1837,6 +1842,7 @@ void ap_module_exit(void) { int i; + initialised = false; ap_reset_domain(); ap_poll_thread_stop(); del_timer_sync(&ap_config_timer); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index a9603eb..9f8fa42 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -317,11 +317,9 @@ EXPORT_SYMBOL(zcrypt_device_unregister); void zcrypt_msgtype_register(struct zcrypt_ops *zops) { - if (zops->owner) { - spin_lock_bh(&zcrypt_ops_list_lock); - list_add_tail(&zops->list, &zcrypt_ops_list); - spin_unlock_bh(&zcrypt_ops_list_lock); - } + spin_lock_bh(&zcrypt_ops_list_lock); + list_add_tail(&zops->list, &zcrypt_ops_list); + spin_unlock_bh(&zcrypt_ops_list_lock); } EXPORT_SYMBOL(zcrypt_msgtype_register); @@ -342,7 +340,7 @@ struct zcrypt_ops *__ops_lookup(unsigned char *name, int variant) spin_lock_bh(&zcrypt_ops_list_lock); list_for_each_entry(zops, &zcrypt_ops_list, list) { if ((zops->variant == variant) && - (!strncmp(zops->owner->name, name, MODULE_NAME_LEN))) { + (!strncmp(zops->name, name, sizeof(zops->name)))) { found = 1; break; } diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index 7508768..38618f0 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -96,6 +96,7 @@ struct zcrypt_ops { struct list_head list; /* zcrypt ops list. */ struct module *owner; int variant; + char name[128]; }; struct zcrypt_device { diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 71ceee9..74edf29 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -513,6 +513,7 @@ static struct zcrypt_ops zcrypt_msgtype50_ops = { .rsa_modexpo = zcrypt_cex2a_modexpo, .rsa_modexpo_crt = zcrypt_cex2a_modexpo_crt, .owner = THIS_MODULE, + .name = MSGTYPE50_NAME, .variant = MSGTYPE50_VARIANT_DEFAULT, }; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 7476221..9a2dd47 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1119,6 +1119,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_device *zdev, */ static struct zcrypt_ops zcrypt_msgtype6_norng_ops = { .owner = THIS_MODULE, + .name = MSGTYPE06_NAME, .variant = MSGTYPE06_VARIANT_NORNG, .rsa_modexpo = zcrypt_msgtype6_modexpo, .rsa_modexpo_crt = zcrypt_msgtype6_modexpo_crt, @@ -1127,6 +1128,7 @@ static struct zcrypt_ops zcrypt_msgtype6_norng_ops = { static struct zcrypt_ops zcrypt_msgtype6_ops = { .owner = THIS_MODULE, + .name = MSGTYPE06_NAME, .variant = MSGTYPE06_VARIANT_DEFAULT, .rsa_modexpo = zcrypt_msgtype6_modexpo, .rsa_modexpo_crt = zcrypt_msgtype6_modexpo_crt, @@ -1136,6 +1138,7 @@ static struct zcrypt_ops zcrypt_msgtype6_ops = { static struct zcrypt_ops zcrypt_msgtype6_ep11_ops = { .owner = THIS_MODULE, + .name = MSGTYPE06_NAME, .variant = MSGTYPE06_VARIANT_EP11, .rsa_modexpo = NULL, .rsa_modexpo_crt = NULL, diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c index 25abd4e..91a00301 100644 --- a/drivers/sh/pm_runtime.c +++ b/drivers/sh/pm_runtime.c @@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = { static int __init sh_pm_runtime_init(void) { - if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) { + if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { if (!of_find_compatible_node(NULL, NULL, "renesas,cpg-mstp-clocks")) return 0; @@ -46,6 +46,12 @@ config FS_DAX or if unsure, say N. Saying Y will increase the size of the kernel by about 5kB. +config FS_DAX_PMD + bool + default FS_DAX + depends on FS_DAX + depends on BROKEN + endif # BLOCK # Posix ACL utility routines diff --git a/fs/block_dev.c b/fs/block_dev.c index bb0dfb1..c25639e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -390,9 +390,17 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, struct page *page) { const struct block_device_operations *ops = bdev->bd_disk->fops; + int result = -EOPNOTSUPP; + if (!ops->rw_page || bdev_get_integrity(bdev)) - return -EOPNOTSUPP; - return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + return result; + + result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + if (result) + return result; + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); + blk_queue_exit(bdev->bd_queue); + return result; } EXPORT_SYMBOL_GPL(bdev_read_page); @@ -421,14 +429,20 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, int result; int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE; const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; + result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL); + if (result) + return result; + set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw); if (result) end_page_writeback(page); else unlock_page(page); + blk_queue_exit(bdev->bd_queue); return result; } EXPORT_SYMBOL_GPL(bdev_write_page); diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 7a6b02f..c0f3da3 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -879,7 +879,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) loff_t pos, eof; size_t len; void *data; - int ret; + int ret = -ENOBUFS; ASSERT(op != NULL); ASSERT(page != NULL); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index c81ce7f..a7a1b21 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1636,6 +1636,116 @@ const struct file_operations configfs_dir_operations = { .iterate = configfs_readdir, }; +/** + * configfs_register_group - creates a parent-child relation between two groups + * @parent_group: parent group + * @group: child group + * + * link groups, creates dentry for the child and attaches it to the + * parent dentry. + * + * Return: 0 on success, negative errno code on error + */ +int configfs_register_group(struct config_group *parent_group, + struct config_group *group) +{ + struct configfs_subsystem *subsys = parent_group->cg_subsys; + struct dentry *parent; + int ret; + + mutex_lock(&subsys->su_mutex); + link_group(parent_group, group); + mutex_unlock(&subsys->su_mutex); + + parent = parent_group->cg_item.ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + ret = create_default_group(parent_group, group); + if (!ret) { + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + } + mutex_unlock(&d_inode(parent)->i_mutex); + return ret; +} +EXPORT_SYMBOL(configfs_register_group); + +/** + * configfs_unregister_group() - unregisters a child group from its parent + * @group: parent group to be unregistered + * + * Undoes configfs_register_group() + */ +void configfs_unregister_group(struct config_group *group) +{ + struct configfs_subsystem *subsys = group->cg_subsys; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + spin_lock(&configfs_dirent_lock); + configfs_detach_prep(dentry, NULL); + spin_unlock(&configfs_dirent_lock); + + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + d_delete(dentry); + mutex_unlock(&d_inode(parent)->i_mutex); + + dput(dentry); + + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); +} +EXPORT_SYMBOL(configfs_unregister_group); + +/** + * configfs_register_default_group() - allocates and registers a child group + * @parent_group: parent group + * @name: child group name + * @item_type: child item type description + * + * boilerplate to allocate and register a child group with its parent. We need + * kzalloc'ed memory because child's default_group is initially empty. + * + * Return: allocated config group or ERR_PTR() on error + */ +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type) +{ + int ret; + struct config_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + config_group_init_type_name(group, name, item_type); + + ret = configfs_register_group(parent_group, group); + if (ret) { + kfree(group); + return ERR_PTR(ret); + } + return group; +} +EXPORT_SYMBOL(configfs_register_default_group); + +/** + * configfs_unregister_default_group() - unregisters and frees a child group + * @group: the group to act on + */ +void configfs_unregister_default_group(struct config_group *group) +{ + configfs_unregister_group(group); + kfree(group); +} +EXPORT_SYMBOL(configfs_unregister_default_group); + int configfs_register_subsystem(struct configfs_subsystem *subsys) { int err; @@ -541,6 +541,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, unsigned long pfn; int result = 0; + /* dax pmd mappings are broken wrt gup and fork */ + if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) + return VM_FAULT_FALLBACK; + /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) return VM_FAULT_FALLBACK; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 3a71cea..748d35a 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -569,6 +569,8 @@ static int parse_options(char *options, struct super_block *sb) /* Fall through */ case Opt_dax: #ifdef CONFIG_FS_DAX + ext2_msg(sb, KERN_WARNING, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); set_opt(sbi->s_mount_opt, DAX); #else ext2_msg(sb, KERN_INFO, "dax option not supported"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 753f4e6..c9ab67d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1664,8 +1664,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } sbi->s_jquota_fmt = m->mount_opt; #endif -#ifndef CONFIG_FS_DAX } else if (token == Opt_dax) { +#ifdef CONFIG_FS_DAX + ext4_msg(sb, KERN_WARNING, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + sbi->s_mount_opt |= m->mount_opt; +#else ext4_msg(sb, KERN_INFO, "dax option not supported"); return -1; #endif diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 4afc4d9..8b2127f 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -610,9 +610,9 @@ parse_record: int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); if (status < 0) { - ctx->pos = cpos; + bh = NULL; ret = status; - goto out; + goto end_of_dir; } else if (status == PARSE_INVALID) goto record_end; else if (status == PARSE_NOT_LONGNAME) @@ -654,8 +654,9 @@ parse_record: fill_len = short_len; start_filldir: - if (!fake_offset) - ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + if (fake_offset && ctx->pos < 2) + ctx->pos = 2; if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) { if (!dir_emit_dot(file, ctx)) @@ -681,14 +682,19 @@ record_end: fake_offset = 0; ctx->pos = cpos; goto get_new; + end_of_dir: - ctx->pos = cpos; + if (fake_offset && cpos < 2) + ctx->pos = 2; + else + ctx->pos = cpos; fill_failed: brelse(bh); if (unicode) __putname(unicode); out: mutex_unlock(&sbi->s_lock); + return ret; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316adb9..de4bdfa 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -332,12 +332,17 @@ static void remove_huge_page(struct page *page) * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. + * maps and global counts. Page faults can not race with truncation + * in this routine. hugetlb_no_page() prevents page faults in the + * truncated range. It checks i_size before allocation, and again after + * with the page table lock for the page held. The same lock must be + * acquired to unmap a page. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. + * pages are not modified. Page faults can race with hole punch. + * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -361,46 +366,37 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Make sure to never grab more pages that we - * might possibly need. + * Don't grab more pages than the number left in the range. */ if (end - next < lookup_nr) lookup_nr = end - next; /* - * This pagevec_lookup() may return pages past 'end', - * so we must check for page->index > end. + * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) { - if (next == start) - break; - next = start; - continue; - } + if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; + /* + * The page (index) could be beyond end. This is + * only possible in the punch hole case as end is + * max page offset in the truncate case. + */ + next = page->index; + if (next >= end) + break; + hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); lock_page(page); - if (page->index >= end) { - unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - next = end; /* we are done */ - break; - } - - /* - * If page is mapped, it was faulted in after being - * unmapped. Do nothing in this race case. In the - * normal case page is not mapped. - */ - if (!page_mapped(page)) { + if (likely(!page_mapped(page))) { bool rsv_on_error = !PagePrivate(page); /* * We must free the huge page and remove @@ -421,17 +417,23 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, hugetlb_fix_reserve_counts( inode, rsv_on_error); } + } else { + /* + * If page is mapped, it was faulted in after + * being unmapped. It indicates a race between + * hole punch and page fault. Do nothing in + * this case. Getting here in a truncate + * operation is a bug. + */ + BUG_ON(truncate_op); } - if (page->index > next) - next = page->index; - - ++next; unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); } + ++next; huge_pagevec_release(&pvec); + cond_resched(); } if (truncate_op) @@ -647,9 +649,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = CURRENT_TIME; - spin_lock(&inode->i_lock); - inode->i_private = NULL; - spin_unlock(&inode->i_lock); out: mutex_unlock(&inode->i_mutex); return error; diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 79b1130..0a3f9b5 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -525,6 +525,8 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg switch (rqdata.cmd) { case NCP_LOCK_EX: case NCP_LOCK_SH: + if (rqdata.timeout < 0) + return -EINVAL; if (rqdata.timeout == 0) rqdata.timeout = NCP_LOCK_DEFAULT_TIMEOUT; else if (rqdata.timeout > NCP_LOCK_MAX_TIMEOUT) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3b48ac2..a03f6f4 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -372,6 +372,8 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } + /* update inode->i_mode after mask with "umask". */ + inode->i_mode = mode; handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index e67aeac..4b74c97 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -136,6 +136,9 @@ drm_atomic_connectors_for_crtc(struct drm_atomic_state *state, void drm_atomic_legacy_backoff(struct drm_atomic_state *state); +void +drm_atomic_clean_old_fb(struct drm_device *dev, unsigned plane_mask, int ret); + int __must_check drm_atomic_check_only(struct drm_atomic_state *state); int __must_check drm_atomic_commit(struct drm_atomic_state *state); int __must_check drm_atomic_async_commit(struct drm_atomic_state *state); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3fe27f8..c0d2b79 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -794,6 +794,8 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); +extern int blk_queue_enter(struct request_queue *q, gfp_t gfp); +extern void blk_queue_exit(struct request_queue *q); extern void blk_start_queue(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); diff --git a/include/linux/configfs.h b/include/linux/configfs.h index a8a335b..758a029 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -197,6 +197,16 @@ static inline struct configfs_subsystem *to_configfs_subsystem(struct config_gro int configfs_register_subsystem(struct configfs_subsystem *subsys); void configfs_unregister_subsystem(struct configfs_subsystem *subsys); +int configfs_register_group(struct config_group *parent_group, + struct config_group *group); +void configfs_unregister_group(struct config_group *group); + +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type); +void configfs_unregister_default_group(struct config_group *group); + /* These functions can sleep and can alloc with GFP_KERNEL */ /* WARNING: These cannot be called underneath configfs callbacks!! */ int configfs_depend_item(struct configfs_subsystem *subsys, struct config_item *target); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6523109..8942af0 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -271,7 +271,7 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { - return gfp_flags & __GFP_DIRECT_RECLAIM; + return (bool __force)(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index e6982ac..a57f0df 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -16,6 +16,7 @@ #define MARVELL_PHY_ID_88E1318S 0x01410e90 #define MARVELL_PHY_ID_88E1116R 0x01410e40 #define MARVELL_PHY_ID_88E1510 0x01410dd0 +#define MARVELL_PHY_ID_88E1540 0x01410eb0 #define MARVELL_PHY_ID_88E3016 0x01410e60 /* struct phy_device dev_flags definitions */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dd20974..1565324 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -453,26 +453,28 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 lro_cap[0x1]; u8 lro_psh_flag[0x1]; u8 lro_time_stamp[0x1]; - u8 reserved_0[0x6]; + u8 reserved_0[0x3]; + u8 self_lb_en_modifiable[0x1]; + u8 reserved_1[0x2]; u8 max_lso_cap[0x5]; - u8 reserved_1[0x4]; + u8 reserved_2[0x4]; u8 rss_ind_tbl_cap[0x4]; - u8 reserved_2[0x3]; + u8 reserved_3[0x3]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_3[0x2]; + u8 reserved_4[0x2]; u8 tunnel_statless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; - u8 reserved_4[0x20]; + u8 reserved_5[0x20]; - u8 reserved_5[0x10]; + u8 reserved_6[0x10]; u8 lro_min_mss_size[0x10]; - u8 reserved_6[0x120]; + u8 reserved_7[0x120]; u8 lro_timer_supported_periods[4][0x20]; - u8 reserved_7[0x600]; + u8 reserved_8[0x600]; }; struct mlx5_ifc_roce_cap_bits { @@ -4051,9 +4053,11 @@ struct mlx5_ifc_modify_tis_in_bits { }; struct mlx5_ifc_modify_tir_bitmask_bits { - u8 reserved[0x20]; + u8 reserved_0[0x20]; - u8 reserved1[0x1f]; + u8 reserved_1[0x1b]; + u8 self_lb_en[0x1]; + u8 reserved_2[0x3]; u8 lro[0x1]; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d208914..67bfac1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2068,20 +2068,23 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; -#define netdev_alloc_pcpu_stats(type) \ -({ \ - typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ - if (pcpu_stats) { \ - int __cpu; \ - for_each_possible_cpu(__cpu) { \ - typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, __cpu); \ - u64_stats_init(&stat->syncp); \ - } \ - } \ - pcpu_stats; \ +#define __netdev_alloc_pcpu_stats(type, gfp) \ +({ \ + typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ + if (pcpu_stats) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ }) +#define netdev_alloc_pcpu_stats(type) \ + __netdev_alloc_pcpu_stats(type, GFP_KERNEL); + #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update the rtnetlink @@ -3854,6 +3857,11 @@ static inline bool netif_is_bridge_master(const struct net_device *dev) return dev->priv_flags & IFF_EBRIDGE; } +static inline bool netif_is_bridge_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_BRIDGE_PORT; +} + static inline bool netif_is_ovs_master(const struct net_device *dev) { return dev->priv_flags & IFF_OPENVSWITCH; diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 48bb01e..0e1f433 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -421,7 +421,7 @@ extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], - size_t len); + size_t len, size_t align); extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], struct ip_set_ext *ext); diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 187feab..5fcd375 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -5,10 +5,13 @@ #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS -static inline int nf_hook_ingress_active(struct sk_buff *skb) +static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { - return nf_hook_list_active(&skb->dev->nf_hooks_ingress, - NFPROTO_NETDEV, NF_NETDEV_INGRESS); +#ifdef HAVE_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) + return false; +#endif + return !list_empty(&skb->dev->nf_hooks_ingress); } static inline int nf_hook_ingress(struct sk_buff *skb) @@ -16,8 +19,8 @@ static inline int nf_hook_ingress(struct sk_buff *skb) struct nf_hook_state state; nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, - NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL, - skb->dev, NULL, dev_net(skb->dev), NULL); + NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, + skb->dev, NULL, NULL, dev_net(skb->dev), NULL); return nf_hook_slow(skb, &state); } diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index 36112cd..b90d8ec 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -80,7 +80,7 @@ static inline int of_dma_router_register(struct device_node *np, static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, diff --git a/include/linux/signal.h b/include/linux/signal.h index ab1e039..92557bb 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -239,7 +239,6 @@ extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -extern int sigsuspend(sigset_t *); struct sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION diff --git a/include/linux/slab.h b/include/linux/slab.h index 7c82e3b..9694077 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -158,6 +158,24 @@ size_t ksize(const void *); #endif /* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + +/* + * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned + * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN + * aligned pointers. + */ +#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) +#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) +#define __assume_page_alignment __assume_aligned(PAGE_SIZE) + +/* * Kmalloc array related definitions */ @@ -286,8 +304,8 @@ static __always_inline int kmalloc_index(size_t size) } #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags); -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags); +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment; +void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment; void kmem_cache_free(struct kmem_cache *, void *); /* @@ -301,8 +319,8 @@ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); bool kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node); -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment; +void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -316,12 +334,12 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t); +extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size); + int node, size_t size) __assume_slab_alignment; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, @@ -354,10 +372,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) @@ -482,15 +500,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) return __kmalloc_node(size, flags, node); } -/* - * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. - * Intended for arches that get misalignment faults even for 64 bit integer - * aligned buffers. - */ -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - struct memcg_cache_array { struct rcu_head rcu; struct kmem_cache *entries[0]; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index aaf9700..fb961a5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -167,7 +167,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) static inline u32 rt6_get_cookie(const struct rt6_info *rt) { - if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE)) + if (rt->rt6i_flags & RTF_PCPU || + (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index aaee6fa..ff788b6 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else { stats->tx_errors++; stats->tx_aborted_errors++; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index f6dafec..62a750a 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err, struct pcpu_sw_netstats __percpu *stats) { if (err > 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += err; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else if (err < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c9149cc..4bd7508 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -618,6 +618,8 @@ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); + int (*clone)(struct nft_expr *dst, + const struct nft_expr *src); unsigned int size; int (*init)(const struct nft_ctx *ctx, @@ -660,10 +662,20 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); -static inline void nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { + int err; + __module_get(src->ops->type->owner); - memcpy(dst, src, src->ops->size); + if (src->ops->clone) { + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; + } else { + memcpy(dst, src, src->ops->size); + } + return 0; } /** diff --git a/include/net/sock.h b/include/net/sock.h index bbf7c2c..7f89e4b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2226,6 +2226,31 @@ static inline bool sk_listener(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } +/** + * sk_state_load - read sk->sk_state for lockless contexts + * @sk: socket pointer + * + * Paired with sk_state_store(). Used in places we do not hold socket lock : + * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... + */ +static inline int sk_state_load(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_state); +} + +/** + * sk_state_store - update sk->sk_state + * @sk: socket pointer + * @newstate: new state + * + * Paired with sk_state_load(). Should be used in contexts where + * state change might impact lockless readers. + */ +static inline void sk_state_store(struct sock *sk, int newstate) +{ + smp_store_release(&sk->sk_state, newstate); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index bc865e2..1d22ce9 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -323,7 +323,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb, struct net_device *filter_dev, int idx) { - return -EOPNOTSUPP; + return idx; } static inline void switchdev_port_fwd_mark_set(struct net_device *dev, diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 6e53441..db545cb 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -294,6 +294,12 @@ static int klp_write_object_relocations(struct module *pmod, for (reloc = obj->relocs; reloc->name; reloc++) { if (!klp_is_module(obj)) { + +#if defined(CONFIG_RANDOMIZE_BASE) + /* If KASLR has been enabled, adjust old value accordingly */ + if (kaslr_enabled()) + reloc->val += kaslr_offset(); +#endif ret = klp_verify_vmlinux_symbol(reloc->name, reloc->val); if (ret) diff --git a/kernel/panic.c b/kernel/panic.c index 4579dbb..4b150bc 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -152,8 +152,11 @@ void panic(const char *fmt, ...) * We may have ended up stopping the CPU holding the lock (in * smp_send_stop()) while still having some valuable data in the console * buffer. Try to acquire the lock then release it regardless of the - * result. The release will also print the buffers out. + * result. The release will also print the buffers out. Locks debug + * should be disabled to avoid reporting bad unlock balance when + * panic() is not being callled from OOPS. */ + debug_locks_off(); console_trylock(); console_unlock(); diff --git a/kernel/signal.c b/kernel/signal.c index c0b01fe..f3f1f7a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3503,7 +3503,7 @@ SYSCALL_DEFINE0(pause) #endif -int sigsuspend(sigset_t *set) +static int sigsuspend(sigset_t *set) { current->saved_sigmask = current->blocked; set_current_blocked(set); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c29ddeb..62fe06b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2009,7 +2009,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) + if (*vm_flags & VM_NO_THP) return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; @@ -2025,7 +2025,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_NOHUGEPAGE | VM_NO_THP)) + if (*vm_flags & VM_NO_THP) return -EINVAL; *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index d41b21b..bc0a8d8 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -19,6 +19,7 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/kmemleak.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/mm.h> @@ -444,6 +445,7 @@ int kasan_module_alloc(void *addr, size_t size) if (ret) { find_vm_area(addr)->flags |= VM_KASAN; + kmemleak_ignore(ret); return 0; } diff --git a/mm/memory.c b/mm/memory.c index deb679c..c387430 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3015,9 +3015,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else { /* * The fault handler has no page to lock, so it holds - * i_mmap_lock for write to protect against truncate. + * i_mmap_lock for read to protect against truncate. */ - i_mmap_unlock_write(vma->vm_file->f_mapping); + i_mmap_unlock_read(vma->vm_file->f_mapping); } goto uncharge_out; } @@ -3031,9 +3031,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else { /* * The fault handler has no page to lock, so it holds - * i_mmap_lock for write to protect against truncate. + * i_mmap_lock for read to protect against truncate. */ - i_mmap_unlock_write(vma->vm_file->f_mapping); + i_mmap_unlock_read(vma->vm_file->f_mapping); } return ret; uncharge_out: diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2c90357..3e4d654 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1542,7 +1542,9 @@ static void balance_dirty_pages(struct address_space *mapping, for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; - unsigned long m_dirty, m_thresh, m_bg_thresh; + unsigned long m_dirty = 0; /* stop bogus uninit warnings */ + unsigned long m_thresh = 0; + unsigned long m_bg_thresh = 0; /* * Unstable writes are a feature of certain networked @@ -1204,7 +1204,7 @@ unsigned long kmem_cache_flags(unsigned long object_size, return flags; } -#else +#else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} @@ -2295,23 +2295,15 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * And if we were unable to get a new slab from the partial slab lists then * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. + * + * Version of __slab_alloc to use when we know that interrupts are + * already disabled (which is the case for bulk allocation). */ -static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void *freelist; struct page *page; - unsigned long flags; - - local_irq_save(flags); -#ifdef CONFIG_PREEMPT - /* - * We may have been preempted and rescheduled on a different - * cpu before disabling interrupts. Need to reload cpu area - * pointer. - */ - c = this_cpu_ptr(s->cpu_slab); -#endif page = c->page; if (!page) @@ -2369,7 +2361,6 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); - local_irq_restore(flags); return freelist; new_slab: @@ -2386,7 +2377,6 @@ new_slab: if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); return NULL; } @@ -2402,11 +2392,35 @@ new_slab: deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); return freelist; } /* + * Another one that disabled interrupt and compensates for possible + * cpu changes by refetching the per cpu area pointer. + */ +static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) +{ + void *p; + unsigned long flags; + + local_irq_save(flags); +#ifdef CONFIG_PREEMPT + /* + * We may have been preempted and rescheduled on a different + * cpu before disabling interrupts. Need to reload cpu area + * pointer. + */ + c = this_cpu_ptr(s->cpu_slab); +#endif + + p = ___slab_alloc(s, gfpflags, node, addr, c); + local_irq_restore(flags); + return p; +} + +/* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. @@ -2804,30 +2818,23 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void *object = c->freelist; if (unlikely(!object)) { - local_irq_enable(); /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist */ - p[i] = __slab_alloc(s, flags, NUMA_NO_NODE, + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_, c); - if (unlikely(!p[i])) { - __kmem_cache_free_bulk(s, i, p); - return false; - } - local_irq_disable(); + if (unlikely(!p[i])) + goto error; + c = this_cpu_ptr(s->cpu_slab); continue; /* goto for-loop */ } /* kmem_cache debug support */ s = slab_pre_alloc_hook(s, flags); - if (unlikely(!s)) { - __kmem_cache_free_bulk(s, i, p); - c->tid = next_tid(c->tid); - local_irq_enable(); - return false; - } + if (unlikely(!s)) + goto error; c->freelist = get_freepointer(s, object); p[i] = object; @@ -2847,6 +2854,11 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, } return true; + +error: + __kmem_cache_free_bulk(s, i, p); + local_irq_enable(); + return false; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d045634..8e3c9c5 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1443,7 +1443,6 @@ struct vm_struct *remove_vm_area(const void *addr) vmap_debug_free_range(va->va_start, va->va_end); kasan_free_shadow(vm); free_unmap_vmap_area(va); - vm->size -= PAGE_SIZE; return vm; } @@ -1468,8 +1467,8 @@ static void __vunmap(const void *addr, int deallocate_pages) return; } - debug_check_no_locks_freed(addr, area->size); - debug_check_no_obj_freed(addr, area->size); + debug_check_no_locks_freed(addr, get_vm_area_size(area)); + debug_check_no_obj_freed(addr, get_vm_area_size(area)); if (deallocate_pages) { int i; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 496b275..e2ed698 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -30,7 +30,9 @@ bool vlan_do_receive(struct sk_buff **skbp) skb->pkt_type = PACKET_HOST; } - if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) { + if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR) && + !netif_is_macvlan_port(vlan_dev) && + !netif_is_bridge_port(vlan_dev)) { unsigned int offset = skb->data - skb_mac_header(skb); /* diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index f7e8dee..5f3f645 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -48,7 +48,7 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) p->state = state; err = switchdev_port_attr_set(p->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index fa53d7a..5396ff08 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -50,7 +50,7 @@ void br_init_port(struct net_bridge_port *p) p->config_pending = 0; err = switchdev_port_attr_set(p->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) netdev_err(p->dev, "failed to set HW ageing time\n"); } diff --git a/net/core/dev.c b/net/core/dev.c index ab9b8d0..ae00b89 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2403,17 +2403,20 @@ static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features = 0; struct net_device *dev = skb->dev; - const char *driver = ""; + const char *name = ""; if (!net_ratelimit()) return; - if (dev && dev->dev.parent) - driver = dev_driver_string(dev->dev.parent); - + if (dev) { + if (dev->dev.parent) + name = dev_driver_string(dev->dev.parent); + else + name = netdev_name(dev); + } WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " "gso_type=%d ip_summed=%d\n", - driver, dev ? &dev->features : &null_features, + name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features, skb->len, skb->data_len, skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type, skb->ip_summed); @@ -6426,11 +6429,16 @@ int __netdev_update_features(struct net_device *dev) if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); + else + err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); + /* return non-0 since some features might have changed and + * it's better to fire a spurious notification than miss it + */ return -1; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 1aa8437..e6af42d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -857,7 +857,7 @@ static void neigh_probe(struct neighbour *neigh) struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) - skb = skb_copy(skb, GFP_ATOMIC); + skb = skb_clone(skb, GFP_ATOMIC); write_unlock(&neigh->lock); neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 504bd17..34ba7a0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1045,15 +1045,156 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb, + struct net_device *dev) +{ + const struct rtnl_link_stats64 *stats; + struct rtnl_link_stats64 temp; + struct nlattr *attr; + + stats = dev_get_stats(dev, &temp); + + attr = nla_reserve(skb, IFLA_STATS, + sizeof(struct rtnl_link_stats)); + if (!attr) + return -EMSGSIZE; + + copy_rtnl_link_stats(nla_data(attr), stats); + + attr = nla_reserve(skb, IFLA_STATS64, + sizeof(struct rtnl_link_stats64)); + if (!attr) + return -EMSGSIZE; + + copy_rtnl_link_stats64(nla_data(attr), stats); + + return 0; +} + +static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, + struct net_device *dev, + int vfs_num, + struct nlattr *vfinfo) +{ + struct ifla_vf_rss_query_en vf_rss_query_en; + struct ifla_vf_link_state vf_linkstate; + struct ifla_vf_spoofchk vf_spoofchk; + struct ifla_vf_tx_rate vf_tx_rate; + struct ifla_vf_stats vf_stats; + struct ifla_vf_trust vf_trust; + struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; + struct nlattr *vf, *vfstats; + struct ifla_vf_mac vf_mac; + struct ifla_vf_info ivi; + + /* Not all SR-IOV capable drivers support the + * spoofcheck and "RSS query enable" query. Preset to + * -1 so the user space tool can detect that the driver + * didn't report anything. + */ + ivi.spoofchk = -1; + ivi.rss_query_en = -1; + ivi.trusted = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); + /* The default value for VF link state is "auto" + * IFLA_VF_LINK_STATE_AUTO which equals zero + */ + ivi.linkstate = 0; + if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi)) + return 0; + + vf_mac.vf = + vf_vlan.vf = + vf_rate.vf = + vf_tx_rate.vf = + vf_spoofchk.vf = + vf_linkstate.vf = + vf_rss_query_en.vf = + vf_trust.vf = ivi.vf; + + memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); + vf_vlan.vlan = ivi.vlan; + vf_vlan.qos = ivi.qos; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; + vf_spoofchk.setting = ivi.spoofchk; + vf_linkstate.link_state = ivi.linkstate; + vf_rss_query_en.setting = ivi.rss_query_en; + vf_trust.setting = ivi.trusted; + vf = nla_nest_start(skb, IFLA_VF_INFO); + if (!vf) { + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; + } + if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || + nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || + nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), + &vf_tx_rate) || + nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), + &vf_spoofchk) || + nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), + &vf_linkstate) || + nla_put(skb, IFLA_VF_RSS_QUERY_EN, + sizeof(vf_rss_query_en), + &vf_rss_query_en) || + nla_put(skb, IFLA_VF_TRUST, + sizeof(vf_trust), &vf_trust)) + return -EMSGSIZE; + memset(&vf_stats, 0, sizeof(vf_stats)); + if (dev->netdev_ops->ndo_get_vf_stats) + dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num, + &vf_stats); + vfstats = nla_nest_start(skb, IFLA_VF_STATS); + if (!vfstats) { + nla_nest_cancel(skb, vf); + nla_nest_cancel(skb, vfinfo); + return -EMSGSIZE; + } + if (nla_put_u64(skb, IFLA_VF_STATS_RX_PACKETS, + vf_stats.rx_packets) || + nla_put_u64(skb, IFLA_VF_STATS_TX_PACKETS, + vf_stats.tx_packets) || + nla_put_u64(skb, IFLA_VF_STATS_RX_BYTES, + vf_stats.rx_bytes) || + nla_put_u64(skb, IFLA_VF_STATS_TX_BYTES, + vf_stats.tx_bytes) || + nla_put_u64(skb, IFLA_VF_STATS_BROADCAST, + vf_stats.broadcast) || + nla_put_u64(skb, IFLA_VF_STATS_MULTICAST, + vf_stats.multicast)) + return -EMSGSIZE; + nla_nest_end(skb, vfstats); + nla_nest_end(skb, vf); + return 0; +} + +static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) +{ + struct rtnl_link_ifmap map = { + .mem_start = dev->mem_start, + .mem_end = dev->mem_end, + .base_addr = dev->base_addr, + .irq = dev->irq, + .dma = dev->dma, + .port = dev->if_port, + }; + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - struct rtnl_link_stats64 temp; - const struct rtnl_link_stats64 *stats; - struct nlattr *attr, *af_spec; + struct nlattr *af_spec; struct rtnl_af_ops *af_ops; struct net_device *upper_dev = netdev_master_upper_dev_get(dev); @@ -1096,18 +1237,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; - if (1) { - struct rtnl_link_ifmap map = { - .mem_start = dev->mem_start, - .mem_end = dev->mem_end, - .base_addr = dev->base_addr, - .irq = dev->irq, - .dma = dev->dma, - .port = dev->if_port, - }; - if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) - goto nla_put_failure; - } + if (rtnl_fill_link_ifmap(skb, dev)) + goto nla_put_failure; if (dev->addr_len) { if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) || @@ -1124,128 +1255,27 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_phys_switch_id_fill(skb, dev)) goto nla_put_failure; - attr = nla_reserve(skb, IFLA_STATS, - sizeof(struct rtnl_link_stats)); - if (attr == NULL) - goto nla_put_failure; - - stats = dev_get_stats(dev, &temp); - copy_rtnl_link_stats(nla_data(attr), stats); - - attr = nla_reserve(skb, IFLA_STATS64, - sizeof(struct rtnl_link_stats64)); - if (attr == NULL) + if (rtnl_fill_stats(skb, dev)) goto nla_put_failure; - copy_rtnl_link_stats64(nla_data(attr), stats); if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) goto nla_put_failure; - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent - && (ext_filter_mask & RTEXT_FILTER_VF)) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent && + ext_filter_mask & RTEXT_FILTER_VF) { int i; - - struct nlattr *vfinfo, *vf, *vfstats; + struct nlattr *vfinfo; int num_vfs = dev_num_vf(dev->dev.parent); vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); if (!vfinfo) goto nla_put_failure; for (i = 0; i < num_vfs; i++) { - struct ifla_vf_info ivi; - struct ifla_vf_mac vf_mac; - struct ifla_vf_vlan vf_vlan; - struct ifla_vf_rate vf_rate; - struct ifla_vf_tx_rate vf_tx_rate; - struct ifla_vf_spoofchk vf_spoofchk; - struct ifla_vf_link_state vf_linkstate; - struct ifla_vf_rss_query_en vf_rss_query_en; - struct ifla_vf_stats vf_stats; - struct ifla_vf_trust vf_trust; - - /* - * Not all SR-IOV capable drivers support the - * spoofcheck and "RSS query enable" query. Preset to - * -1 so the user space tool can detect that the driver - * didn't report anything. - */ - ivi.spoofchk = -1; - ivi.rss_query_en = -1; - ivi.trusted = -1; - memset(ivi.mac, 0, sizeof(ivi.mac)); - /* The default value for VF link state is "auto" - * IFLA_VF_LINK_STATE_AUTO which equals zero - */ - ivi.linkstate = 0; - if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) - break; - vf_mac.vf = - vf_vlan.vf = - vf_rate.vf = - vf_tx_rate.vf = - vf_spoofchk.vf = - vf_linkstate.vf = - vf_rss_query_en.vf = - vf_trust.vf = ivi.vf; - - memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); - vf_vlan.vlan = ivi.vlan; - vf_vlan.qos = ivi.qos; - vf_tx_rate.rate = ivi.max_tx_rate; - vf_rate.min_tx_rate = ivi.min_tx_rate; - vf_rate.max_tx_rate = ivi.max_tx_rate; - vf_spoofchk.setting = ivi.spoofchk; - vf_linkstate.link_state = ivi.linkstate; - vf_rss_query_en.setting = ivi.rss_query_en; - vf_trust.setting = ivi.trusted; - vf = nla_nest_start(skb, IFLA_VF_INFO); - if (!vf) { - nla_nest_cancel(skb, vfinfo); - goto nla_put_failure; - } - if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || - nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || - nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), - &vf_rate) || - nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), - &vf_tx_rate) || - nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), - &vf_spoofchk) || - nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), - &vf_linkstate) || - nla_put(skb, IFLA_VF_RSS_QUERY_EN, - sizeof(vf_rss_query_en), - &vf_rss_query_en) || - nla_put(skb, IFLA_VF_TRUST, - sizeof(vf_trust), &vf_trust)) + if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) goto nla_put_failure; - memset(&vf_stats, 0, sizeof(vf_stats)); - if (dev->netdev_ops->ndo_get_vf_stats) - dev->netdev_ops->ndo_get_vf_stats(dev, i, - &vf_stats); - vfstats = nla_nest_start(skb, IFLA_VF_STATS); - if (!vfstats) { - nla_nest_cancel(skb, vf); - nla_nest_cancel(skb, vfinfo); - goto nla_put_failure; - } - if (nla_put_u64(skb, IFLA_VF_STATS_RX_PACKETS, - vf_stats.rx_packets) || - nla_put_u64(skb, IFLA_VF_STATS_TX_PACKETS, - vf_stats.tx_packets) || - nla_put_u64(skb, IFLA_VF_STATS_RX_BYTES, - vf_stats.rx_bytes) || - nla_put_u64(skb, IFLA_VF_STATS_TX_BYTES, - vf_stats.tx_bytes) || - nla_put_u64(skb, IFLA_VF_STATS_BROADCAST, - vf_stats.broadcast) || - nla_put_u64(skb, IFLA_VF_STATS_MULTICAST, - vf_stats.multicast)) - goto nla_put_failure; - nla_nest_end(skb, vfstats); - nla_nest_end(skb, vf); } + nla_nest_end(skb, vfinfo); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index aa41e6d..152b9c7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4268,7 +4268,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len, + 2 * ETH_ALEN); skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 1feb15f..46b9c88 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -563,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data) int max_retries, thresh; u8 defer_accept; - if (sk_listener->sk_state != TCP_LISTEN) + if (sk_state_load(sk_listener) != TCP_LISTEN) goto drop; max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; @@ -749,7 +749,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog) * It is OK, because this socket enters to hash table only * after validation is complete. */ - sk->sk_state = TCP_LISTEN; + sk_state_store(sk, TCP_LISTEN); if (!sk->sk_prot->get_port(sk, inet->inet_num)) { inet->inet_sport = htons(inet->inet_num); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 657d230..b3ca21b 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -45,7 +45,7 @@ static void pptp_nat_expected(struct nf_conn *ct, struct net *net = nf_ct_net(ct); const struct nf_conn *master = ct->master; struct nf_conntrack_expect *other_exp; - struct nf_conntrack_tuple t; + struct nf_conntrack_tuple t = {}; const struct nf_ct_pptp_master *ct_pptp_info; const struct nf_nat_pptp *nat_pptp_info; struct nf_nat_range range; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8c0d0bd..63e5be0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -406,10 +406,12 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, ip_select_ident(net, skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + skb->transport_header += iphlen; + if (iph->protocol == IPPROTO_ICMP && + length >= iphlen + sizeof(struct icmphdr)) + icmp_out_count(net, ((struct icmphdr *) + skb_transport_header(skb))->type); } - if (iph->protocol == IPPROTO_ICMP) - icmp_out_count(net, ((struct icmphdr *) - skb_transport_header(skb))->type); err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0cfa7c0..c172877 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -451,11 +451,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + int state; sock_rps_record_flow(sk); sock_poll_wait(file, sk_sleep(sk), wait); - if (sk->sk_state == TCP_LISTEN) + + state = sk_state_load(sk); + if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -492,14 +495,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) + if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= POLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLIN | POLLRDNORM | POLLRDHUP; /* Connected or passive Fast Open socket? */ - if (sk->sk_state != TCP_SYN_SENT && - (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) { + if (state != TCP_SYN_SENT && + (state != TCP_SYN_RECV || tp->fastopen_rsk)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -507,9 +510,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) tp->urg_data) target++; - /* Potential race condition. If read of tp below will - * escape above sk->sk_state, we can be illegally awaken - * in SYN_* states. */ if (tp->rcv_nxt - tp->copied_seq >= target) mask |= POLLIN | POLLRDNORM; @@ -1934,7 +1934,7 @@ void tcp_set_state(struct sock *sk, int state) /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ - sk->sk_state = state; + sk_state_store(sk, state); #ifdef STATE_TRACE SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]); @@ -2644,7 +2644,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) if (sk->sk_type != SOCK_STREAM) return; - info->tcpi_state = sk->sk_state; + info->tcpi_state = sk_state_load(sk); + info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; @@ -2672,7 +2673,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; - if (sk->sk_state == TCP_LISTEN) { + if (info->tcpi_state == TCP_LISTEN) { info->tcpi_unacked = sk->sk_ack_backlog; info->tcpi_sacked = sk->sk_max_ack_backlog; } else { diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 479f349..b316040 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -21,7 +21,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, { struct tcp_info *info = _info; - if (sk->sk_state == TCP_LISTEN) { + if (sk_state_load(sk) == TCP_LISTEN) { r->idiag_rqueue = sk->sk_ack_backlog; r->idiag_wqueue = sk->sk_max_ack_backlog; } else if (sk->sk_type == SOCK_STREAM) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 950e28c0c..ba09016 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2158,6 +2158,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); int rx_queue; + int state; if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || @@ -2175,17 +2176,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) timer_expires = jiffies; } - if (sk->sk_state == TCP_LISTEN) + state = sk_state_load(sk); + if (state == TCP_LISTEN) rx_queue = sk->sk_ack_backlog; else - /* - * because we dont lock socket, we might find a transient negative value + /* Because we don't lock the socket, + * we might find a transient negative value. */ rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", - i, src, srcp, dest, destp, sk->sk_state, + i, src, srcp, dest, destp, state, tp->write_seq - tp->snd_una, rx_queue, timer_active, @@ -2199,8 +2201,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - sk->sk_state == TCP_LISTEN ? - (fastopenq ? fastopenq->max_qlen : 0) : + state == TCP_LISTEN ? + fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 124338a..5ee56d0 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1651,7 +1651,6 @@ out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } @@ -2015,7 +2014,6 @@ out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c8bc9b4..6f01fe1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -404,6 +404,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, } } +static bool __rt6_check_expired(const struct rt6_info *rt) +{ + if (rt->rt6i_flags & RTF_EXPIRES) + return time_after(jiffies, rt->dst.expires); + else + return false; +} + static bool rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) { @@ -1252,7 +1260,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) { - if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + if (!__rt6_check_expired(rt) && + rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && rt6_check((struct rt6_info *)(rt->dst.from), cookie)) return &rt->dst; else @@ -1272,7 +1281,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt6_dst_from_metrics_check(rt); - if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE)) + if (rt->rt6i_flags & RTF_PCPU || + (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from)) return rt6_dst_from_check(rt, cookie); else return rt6_check(rt, cookie); @@ -1322,6 +1332,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } +static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) +{ + return !(rt->rt6i_flags & RTF_CACHE) && + (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node); +} + static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu) { @@ -1335,7 +1351,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (mtu >= dst_mtu(dst)) return; - if (rt6->rt6i_flags & RTF_CACHE) { + if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); } else { const struct in6_addr *daddr, *saddr; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5baa8e7..c5429a6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1690,6 +1690,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; + int rx_queue; + int state; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; @@ -1710,6 +1712,15 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) timer_expires = jiffies; } + state = sk_state_load(sp); + if (state == TCP_LISTEN) + rx_queue = sp->sk_ack_backlog; + else + /* Because we don't lock the socket, + * we might find a transient negative value. + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", @@ -1718,9 +1729,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - tp->write_seq-tp->snd_una, - (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), + state, + tp->write_seq - tp->snd_una, + rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, @@ -1732,7 +1743,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - sp->sk_state == TCP_LISTEN ? + state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e22349e..4692782 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -869,7 +869,7 @@ config NETFILTER_XT_TARGET_TEE depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 - select NF_DUP_IPV6 if IP6_NF_IPTABLES + select NF_DUP_IPV6 if IP6_NF_IPTABLES != n ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. @@ -882,7 +882,7 @@ config NETFILTER_XT_TARGET_TPROXY depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 - select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n help This option adds a `TPROXY' target, which is somewhat similar to REDIRECT. It can only be used in the mangle table and is useful @@ -1375,7 +1375,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on IPV6 || IPV6=n depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n select NF_DEFRAG_IPV4 - select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n help This option adds a `socket' match, which can be used to match packets for which a TCP or UDP socket lookup finds a valid socket. diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index d05e759..b0bc475 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -33,7 +33,7 @@ #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype MTYPE -#define get_ext(set, map, id) ((map)->extensions + (set)->dsize * (id)) +#define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) static void mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) @@ -67,12 +67,9 @@ mtype_destroy(struct ip_set *set) del_timer_sync(&map->gc); ip_set_free(map->members); - if (set->dsize) { - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set); - ip_set_free(map->extensions); - } - kfree(map); + if (set->dsize && set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set); + ip_set_free(map); set->data = NULL; } @@ -92,16 +89,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) { const struct mtype *map = set->data; struct nlattr *nested; + size_t memsize = sizeof(*map) + map->memsize; nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (mtype_do_head(skb, map) || nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || - nla_put_net32(skb, IPSET_ATTR_MEMSIZE, - htonl(sizeof(*map) + - map->memsize + - set->dsize * map->elements))) + nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 64a5643..4783eff 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -41,7 +41,6 @@ MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ struct bitmap_ip { void *members; /* the set members */ - void *extensions; /* data extensions */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -49,6 +48,8 @@ struct bitmap_ip { size_t memsize; /* members size */ u8 netmask; /* subnet netmask */ struct timer_list gc; /* garbage collection */ + unsigned char extensions[0] /* data extensions */ + __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ @@ -224,13 +225,6 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, map->members = ip_set_alloc(map->memsize); if (!map->members) return false; - if (set->dsize) { - map->extensions = ip_set_alloc(set->dsize * elements); - if (!map->extensions) { - kfree(map->members); - return false; - } - } map->first_ip = first_ip; map->last_ip = last_ip; map->elements = elements; @@ -316,13 +310,13 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], pr_debug("hosts %u, elements %llu\n", hosts, (unsigned long long)elements); - map = kzalloc(sizeof(*map), GFP_KERNEL); + set->dsize = ip_set_elem_len(set, tb, 0, 0); + map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; map->memsize = bitmap_bytes(0, elements - 1); set->variant = &bitmap_ip; - set->dsize = ip_set_elem_len(set, tb, 0); if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { kfree(map); diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 1430535..29dde20 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -47,24 +47,26 @@ enum { /* Type structure */ struct bitmap_ipmac { void *members; /* the set members */ - void *extensions; /* MAC + data extensions */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collector */ + unsigned char extensions[0] /* MAC + data extensions */ + __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ struct bitmap_ipmac_adt_elem { + unsigned char ether[ETH_ALEN] __aligned(2); u16 id; - unsigned char *ether; + u16 add_mac; }; struct bitmap_ipmac_elem { unsigned char ether[ETH_ALEN]; unsigned char filled; -} __attribute__ ((aligned)); +} __aligned(__alignof__(u64)); static inline u32 ip_to_id(const struct bitmap_ipmac *m, u32 ip) @@ -72,11 +74,11 @@ ip_to_id(const struct bitmap_ipmac *m, u32 ip) return ip - m->first_ip; } -static inline struct bitmap_ipmac_elem * -get_elem(void *extensions, u16 id, size_t dsize) -{ - return (struct bitmap_ipmac_elem *)(extensions + id * dsize); -} +#define get_elem(extensions, id, dsize) \ + (struct bitmap_ipmac_elem *)(extensions + (id) * (dsize)) + +#define get_const_elem(extensions, id, dsize) \ + (const struct bitmap_ipmac_elem *)(extensions + (id) * (dsize)) /* Common functions */ @@ -88,10 +90,9 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e, if (!test_bit(e->id, map->members)) return 0; - elem = get_elem(map->extensions, e->id, dsize); - if (elem->filled == MAC_FILLED) - return !e->ether || - ether_addr_equal(e->ether, elem->ether); + elem = get_const_elem(map->extensions, e->id, dsize); + if (e->add_mac && elem->filled == MAC_FILLED) + return ether_addr_equal(e->ether, elem->ether); /* Trigger kernel to fill out the ethernet address */ return -EAGAIN; } @@ -103,7 +104,7 @@ bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize) if (!test_bit(id, map->members)) return 0; - elem = get_elem(map->extensions, id, dsize); + elem = get_const_elem(map->extensions, id, dsize); /* Timer not started for the incomplete elements */ return elem->filled == MAC_FILLED; } @@ -133,7 +134,7 @@ bitmap_ipmac_add_timeout(unsigned long *timeout, * and we can reuse it later when MAC is filled out, * possibly by the kernel */ - if (e->ether) + if (e->add_mac) ip_set_timeout_set(timeout, t); else *timeout = t; @@ -150,7 +151,7 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, elem = get_elem(map->extensions, e->id, dsize); if (test_bit(e->id, map->members)) { if (elem->filled == MAC_FILLED) { - if (e->ether && + if (e->add_mac && (flags & IPSET_FLAG_EXIST) && !ether_addr_equal(e->ether, elem->ether)) { /* memcpy isn't atomic */ @@ -159,7 +160,7 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, ether_addr_copy(elem->ether, e->ether); } return IPSET_ADD_FAILED; - } else if (!e->ether) + } else if (!e->add_mac) /* Already added without ethernet address */ return IPSET_ADD_FAILED; /* Fill the MAC address and trigger the timer activation */ @@ -168,7 +169,7 @@ bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e, ether_addr_copy(elem->ether, e->ether); elem->filled = MAC_FILLED; return IPSET_ADD_START_STORED_TIMEOUT; - } else if (e->ether) { + } else if (e->add_mac) { /* We can store MAC too */ ether_addr_copy(elem->ether, e->ether); elem->filled = MAC_FILLED; @@ -191,7 +192,7 @@ bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map, u32 id, size_t dsize) { const struct bitmap_ipmac_elem *elem = - get_elem(map->extensions, id, dsize); + get_const_elem(map->extensions, id, dsize); return nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip + id)) || @@ -213,7 +214,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, { struct bitmap_ipmac *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct bitmap_ipmac_adt_elem e = { .id = 0 }; + struct bitmap_ipmac_adt_elem e = { .id = 0, .add_mac = 1 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); u32 ip; @@ -231,7 +232,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, return -EINVAL; e.id = ip_to_id(map, ip); - e.ether = eth_hdr(skb)->h_source; + memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -265,11 +266,10 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_BITMAP_RANGE; e.id = ip_to_id(map, ip); - if (tb[IPSET_ATTR_ETHER]) - e.ether = nla_data(tb[IPSET_ATTR_ETHER]); - else - e.ether = NULL; - + if (tb[IPSET_ATTR_ETHER]) { + memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN); + e.add_mac = 1; + } ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; @@ -300,13 +300,6 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, map->members = ip_set_alloc(map->memsize); if (!map->members) return false; - if (set->dsize) { - map->extensions = ip_set_alloc(set->dsize * elements); - if (!map->extensions) { - kfree(map->members); - return false; - } - } map->first_ip = first_ip; map->last_ip = last_ip; map->elements = elements; @@ -361,14 +354,15 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; - map = kzalloc(sizeof(*map), GFP_KERNEL); + set->dsize = ip_set_elem_len(set, tb, + sizeof(struct bitmap_ipmac_elem), + __alignof__(struct bitmap_ipmac_elem)); + map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; map->memsize = bitmap_bytes(0, elements - 1); set->variant = &bitmap_ipmac; - set->dsize = ip_set_elem_len(set, tb, - sizeof(struct bitmap_ipmac_elem)); if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { kfree(map); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 5338ccd..7f0c733 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -35,12 +35,13 @@ MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ struct bitmap_port { void *members; /* the set members */ - void *extensions; /* data extensions */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collection */ + unsigned char extensions[0] /* data extensions */ + __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ @@ -209,13 +210,6 @@ init_map_port(struct ip_set *set, struct bitmap_port *map, map->members = ip_set_alloc(map->memsize); if (!map->members) return false; - if (set->dsize) { - map->extensions = ip_set_alloc(set->dsize * map->elements); - if (!map->extensions) { - kfree(map->members); - return false; - } - } map->first_port = first_port; map->last_port = last_port; set->timeout = IPSET_NO_TIMEOUT; @@ -232,6 +226,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], { struct bitmap_port *map; u16 first_port, last_port; + u32 elements; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) || @@ -248,14 +243,15 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], last_port = tmp; } - map = kzalloc(sizeof(*map), GFP_KERNEL); + elements = last_port - first_port + 1; + set->dsize = ip_set_elem_len(set, tb, 0, 0); + map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; - map->elements = last_port - first_port + 1; + map->elements = elements; map->memsize = bitmap_bytes(0, map->elements); set->variant = &bitmap_port; - set->dsize = ip_set_elem_len(set, tb, 0); if (!init_map_port(set, map, first_port, last_port)) { kfree(map); return -ENOMEM; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69ab9c26..54f3d7c 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -364,25 +364,27 @@ add_extension(enum ip_set_ext_id id, u32 flags, struct nlattr *tb[]) } size_t -ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) +ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, + size_t align) { enum ip_set_ext_id id; - size_t offset = len; u32 cadt_flags = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_WITH_FORCEADD) set->flags |= IPSET_CREATE_FLAG_FORCEADD; + if (!align) + align = 1; for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; - offset = ALIGN(offset, ip_set_extensions[id].align); - set->offset[id] = offset; + len = ALIGN(len, ip_set_extensions[id].align); + set->offset[id] = len; set->extensions |= ip_set_extensions[id].type; - offset += ip_set_extensions[id].len; + len += ip_set_extensions[id].len; } - return offset; + return ALIGN(len, align); } EXPORT_SYMBOL_GPL(ip_set_elem_len); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 691b54f..e5336ab 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -72,8 +72,9 @@ struct hbucket { DECLARE_BITMAP(used, AHASH_MAX_TUNED); u8 size; /* size of the array */ u8 pos; /* position of the first free entry */ - unsigned char value[0]; /* the array of the values */ -} __attribute__ ((aligned)); + unsigned char value[0] /* the array of the values */ + __aligned(__alignof__(u64)); +}; /* The hash table: the table size stored here in order to make resizing easy */ struct htable { @@ -475,7 +476,7 @@ static void mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) { struct htable *t; - struct hbucket *n; + struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; #ifdef IP_SET_HASH_WITH_NETS @@ -510,9 +511,14 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) } } if (d >= AHASH_INIT_SIZE) { - struct hbucket *tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + if (d >= n->size) { + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + continue; + } + tmp = kzalloc(sizeof(*tmp) + + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) /* Still try to delete expired elements */ continue; @@ -522,7 +528,7 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize) continue; data = ahash_data(n, j, dsize); memcpy(tmp->value + d * dsize, data, dsize); - set_bit(j, tmp->used); + set_bit(d, tmp->used); d++; } tmp->pos = d; @@ -1323,12 +1329,14 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif set->variant = &IPSET_TOKEN(HTYPE, 4_variant); set->dsize = ip_set_elem_len(set, tb, - sizeof(struct IPSET_TOKEN(HTYPE, 4_elem))); + sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)), + __alignof__(struct IPSET_TOKEN(HTYPE, 4_elem))); #ifndef IP_SET_PROTO_UNDEF } else { set->variant = &IPSET_TOKEN(HTYPE, 6_variant); set->dsize = ip_set_elem_len(set, tb, - sizeof(struct IPSET_TOKEN(HTYPE, 6_elem))); + sizeof(struct IPSET_TOKEN(HTYPE, 6_elem)), + __alignof__(struct IPSET_TOKEN(HTYPE, 6_elem))); } #endif if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a30ce6..bbede95 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -31,7 +31,7 @@ struct set_elem { struct rcu_head rcu; struct list_head list; ip_set_id_t id; -}; +} __aligned(__alignof__(u64)); struct set_adt_elem { ip_set_id_t id; @@ -618,7 +618,8 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], size = IP_SET_LIST_MIN_SIZE; set->variant = &set_variant; - set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem)); + set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), + __alignof__(struct set_elem)); if (!init_list_set(net, set, size)) return -ENOMEM; if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 1e24fff..f57b4dc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1176,6 +1176,7 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + struct sock *sk; EnterFunction(11); @@ -1183,13 +1184,12 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in if (skb->ipvs_property) return NF_ACCEPT; + sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ - if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && + if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - struct sock *sk = skb->sk; - struct inet_sock *inet = inet_sk(skb->sk); - if (inet && sk->sk_family == PF_INET && inet->nodefrag) + if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } @@ -1681,6 +1681,7 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int struct ip_vs_conn *cp; int ret, pkts; int conn_reuse_mode; + struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -1708,12 +1709,11 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ - if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && + sk = skb_to_full_sk(skb); + if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { - struct sock *sk = skb->sk; - struct inet_sock *inet = inet_sk(skb->sk); - if (inet && sk->sk_family == PF_INET && inet->nodefrag) + if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 06eb48f..740cce4 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -825,7 +825,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, struct net *net = sock_net(ctnl); struct nfnl_log_net *log = nfnl_log_pernet(net); int ret = 0; - u16 flags; + u16 flags = 0; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = nfmsg->nfgen_family; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 1067fb4..c7808fc 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -47,27 +47,34 @@ static void nft_counter_eval(const struct nft_expr *expr, local_bh_enable(); } -static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +static void nft_counter_fetch(const struct nft_counter_percpu __percpu *counter, + struct nft_counter *total) { - struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - struct nft_counter_percpu *cpu_stats; - struct nft_counter total; + const struct nft_counter_percpu *cpu_stats; u64 bytes, packets; unsigned int seq; int cpu; - memset(&total, 0, sizeof(total)); + memset(total, 0, sizeof(*total)); for_each_possible_cpu(cpu) { - cpu_stats = per_cpu_ptr(priv->counter, cpu); + cpu_stats = per_cpu_ptr(counter, cpu); do { seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); bytes = cpu_stats->counter.bytes; packets = cpu_stats->counter.packets; } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); - total.packets += packets; - total.bytes += bytes; + total->packets += packets; + total->bytes += bytes; } +} + +static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct nft_counter total; + + nft_counter_fetch(priv->counter, &total); if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes)) || nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.packets))) @@ -118,6 +125,31 @@ static void nft_counter_destroy(const struct nft_ctx *ctx, free_percpu(priv->counter); } +static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(src); + struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); + struct nft_counter_percpu __percpu *cpu_stats; + struct nft_counter_percpu *this_cpu; + struct nft_counter total; + + nft_counter_fetch(priv->counter, &total); + + cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu, + GFP_ATOMIC); + if (cpu_stats == NULL) + return ENOMEM; + + preempt_disable(); + this_cpu = this_cpu_ptr(cpu_stats); + this_cpu->counter.packets = total.packets; + this_cpu->counter.bytes = total.bytes; + preempt_enable(); + + priv_clone->counter = cpu_stats; + return 0; +} + static struct nft_expr_type nft_counter_type; static const struct nft_expr_ops nft_counter_ops = { .type = &nft_counter_type, @@ -126,6 +158,7 @@ static const struct nft_expr_ops nft_counter_ops = { .init = nft_counter_init, .destroy = nft_counter_destroy, .dump = nft_counter_dump, + .clone = nft_counter_clone, }; static struct nft_expr_type nft_counter_type __read_mostly = { diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 513a8ef..9dec3bd 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -50,8 +50,9 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, } ext = nft_set_elem_ext(set, elem); - if (priv->expr != NULL) - nft_expr_clone(nft_set_ext_expr(ext), priv->expr); + if (priv->expr != NULL && + nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0) + return NULL; return elem; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index af399ca..1cf928f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1741,6 +1741,20 @@ static void fanout_release(struct sock *sk) kfree_rcu(po->rollover, rcu); } +static bool packet_extra_vlan_len_allowed(const struct net_device *dev, + struct sk_buff *skb) +{ + /* Earlier code assumed this would be a VLAN pkt, double-check + * this now that we have the actual packet in hand. We can only + * do this check on Ethernet devices. + */ + if (unlikely(dev->type != ARPHRD_ETHER)) + return false; + + skb_reset_mac_header(skb); + return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); +} + static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; @@ -1902,18 +1916,10 @@ retry: goto retry; } - if (len > (dev->mtu + dev->hard_header_len + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_unlock; - } + if (len > (dev->mtu + dev->hard_header_len + extra_len) && + !packet_extra_vlan_len_allowed(dev, skb)) { + err = -EMSGSIZE; + goto out_unlock; } skb->protocol = proto; @@ -2332,6 +2338,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len) return false; } +static void tpacket_set_protocol(const struct net_device *dev, + struct sk_buff *skb) +{ + if (dev->type == ARPHRD_ETHER) { + skb_reset_mac_header(skb); + skb->protocol = eth_hdr(skb)->h_proto; + } +} + static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, int size_max, __be16 proto, unsigned char *addr, int hlen) @@ -2368,8 +2383,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb_reserve(skb, hlen); skb_reset_network_header(skb); - if (!packet_use_direct_xmit(po)) - skb_probe_transport_header(skb, 0); if (unlikely(po->tp_tx_has_off)) { int off_min, off_max, off; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); @@ -2415,6 +2428,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, dev->hard_header_len); if (unlikely(err)) return err; + if (!skb->protocol) + tpacket_set_protocol(dev, skb); data += dev->hard_header_len; to_write -= dev->hard_header_len; @@ -2449,6 +2464,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, len = ((to_write > len_max) ? len_max : to_write); } + skb_probe_transport_header(skb, 0); + return tp_len; } @@ -2493,12 +2510,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - reserve = dev->hard_header_len + VLAN_HLEN; + if (po->sk.sk_socket->type == SOCK_RAW) + reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); - if (size_max > dev->mtu + reserve) - size_max = dev->mtu + reserve; + if (size_max > dev->mtu + reserve + VLAN_HLEN) + size_max = dev->mtu + reserve + VLAN_HLEN; do { ph = packet_current_frame(po, &po->tx_ring, @@ -2525,18 +2543,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); if (likely(tp_len >= 0) && - tp_len > dev->mtu + dev->hard_header_len) { - struct ethhdr *ehdr; - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ + tp_len > dev->mtu + reserve && + !packet_extra_vlan_len_allowed(dev, skb)) + tp_len = -EMSGSIZE; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) - tp_len = -EMSGSIZE; - } if (unlikely(tp_len < 0)) { if (po->tp_loss) { __packet_set_status(po, ph, @@ -2765,18 +2775,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); - if (!gso_type && (len > dev->mtu + reserve + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_free; - } + if (!gso_type && (len > dev->mtu + reserve + extra_len) && + !packet_extra_vlan_len_allowed(dev, skb)) { + err = -EMSGSIZE; + goto out_free; } skb->protocol = proto; @@ -2807,8 +2809,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) len += vnet_hdr_len; } - if (!packet_use_direct_xmit(po)) - skb_probe_transport_header(skb, reserve); + skb_probe_transport_header(skb, reserve); + if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -4107,7 +4109,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; - if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) + if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; if (po->tp_version >= TPACKET_V3 && (int)(req->tp_block_size - @@ -4119,8 +4121,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; - rb->frames_per_block = req->tp_block_size/req->tp_frame_size; - if (unlikely(rb->frames_per_block <= 0)) + rb->frames_per_block = req->tp_block_size / req->tp_frame_size; + if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 4f15b7d..1543e39 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, if (!has_sha1) return -EINVAL; - memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0], - hmacs->shmac_num_idents * sizeof(__u16)); + for (i = 0; i < hmacs->shmac_num_idents; i++) + ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]); ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) + hmacs->shmac_num_idents * sizeof(__u16)); return 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index aaa0b58..955ec15 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -441,6 +441,7 @@ static void unix_release_sock(struct sock *sk, int embrion) if (state == TCP_LISTEN) unix_release_sock(skb->sk, 1); /* passed fds are erased in the kfree_skb hook */ + UNIXCB(skb).consumed = skb->len; kfree_skb(skb); } @@ -1799,6 +1800,7 @@ alloc_skb: * this - does no harm */ consume_skb(newskb); + newskb = NULL; } if (skb_append_pagefrags(skb, page, offset, size)) { @@ -1811,8 +1813,11 @@ alloc_skb: skb->truesize += size; atomic_add(size, &sk->sk_wmem_alloc); - if (newskb) + if (newskb) { + spin_lock(&other->sk_receive_queue.lock); __skb_queue_tail(&other->sk_receive_queue, newskb); + spin_unlock(&other->sk_receive_queue.lock); + } unix_state_unlock(other); mutex_unlock(&unix_sk(other)->readlock); @@ -2072,6 +2077,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) do { int chunk; + bool drop_skb; struct sk_buff *skb, *last; unix_state_lock(sk); @@ -2152,7 +2158,11 @@ unlock: } chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size); + skb_get(skb); chunk = state->recv_actor(skb, skip, chunk, state); + drop_skb = !unix_skb_len(skb); + /* skb is only safe to use if !drop_skb */ + consume_skb(skb); if (chunk < 0) { if (copied == 0) copied = -EFAULT; @@ -2161,6 +2171,18 @@ unlock: copied += chunk; size -= chunk; + if (drop_skb) { + /* the skb was touched by a concurrent reader; + * we should not expect anything from this skb + * anymore and assume it invalid - we can be + * sure it was dropped from the socket queue + * + * let's report a short read + */ + err = 0; + break; + } + /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { UNIXCB(skb).consumed += chunk; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 79b4596..edd638b 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -67,10 +67,13 @@ HOSTLOADLIBES_lathist += -lelf # point this to your LLVM backend with bpf support LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc +# asm/sysreg.h inline assmbly used by it is incompatible with llvm. +# But, ehere is not easy way to fix it, so just exclude it since it is +# useless for BPF samples. $(obj)/%.o: $(src)/%.c clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ - -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ + -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \ - -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ + -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=asm -o $@.s diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 125b906..638a38e 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -2711,7 +2711,7 @@ $kernelversion = get_kernel_version(); # generate a sequence of code that will splice in highlighting information # using the s// operator. -foreach my $k (keys @highlights) { +for (my $k = 0; $k < @highlights; $k++) { my $pattern = $highlights[$k][0]; my $result = $highlights[$k][1]; # print STDERR "scanning pattern:$pattern, highlight:($result)\n"; diff --git a/tools/Makefile b/tools/Makefile index d6f307d..7dc820a 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -32,6 +32,10 @@ help: @echo ' from the kernel command line to build and install one of' @echo ' the tools above' @echo '' + @echo ' $$ make tools/all' + @echo '' + @echo ' builds all tools.' + @echo '' @echo ' $$ make tools/install' @echo '' @echo ' installs all tools.' @@ -77,6 +81,11 @@ tmon: FORCE freefall: FORCE $(call descend,laptop/$@) +all: acpi cgroup cpupower hv firewire lguest \ + perf selftests turbostat usb \ + virtio vm net x86_energy_perf_policy \ + tmon freefall + acpi_install: $(call descend,power/$(@:_install=),install) @@ -101,7 +110,7 @@ freefall_install: install: acpi_install cgroup_install cpupower_install hv_install firewire_install lguest_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install net_install x86_energy_perf_policy_install \ - tmon freefall_install + tmon_install freefall_install acpi_clean: $(call descend,power/acpi,clean) diff --git a/tools/net/Makefile b/tools/net/Makefile index ee577ea..ddf8880 100644 --- a/tools/net/Makefile +++ b/tools/net/Makefile @@ -4,6 +4,9 @@ CC = gcc LEX = flex YACC = bison +CFLAGS += -Wall -O2 +CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include + %.yacc.c: %.y $(YACC) -o $@ -d $< @@ -12,15 +15,13 @@ YACC = bison all : bpf_jit_disasm bpf_dbg bpf_asm -bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm' +bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm' bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl bpf_jit_disasm : bpf_jit_disasm.o -bpf_dbg : CFLAGS = -Wall -O2 bpf_dbg : LDLIBS = -lreadline bpf_dbg : bpf_dbg.o -bpf_asm : CFLAGS = -Wall -O2 -I. bpf_asm : LDLIBS = bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o bpf_exp.lex.o : bpf_exp.yacc.c diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 0a945d2..99d127f 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -675,6 +675,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .fork = perf_event__repipe, .exit = perf_event__repipe, .lost = perf_event__repipe, + .lost_samples = perf_event__repipe, .aux = perf_event__repipe, .itrace_start = perf_event__repipe, .context_switch = perf_event__repipe, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2853ad2..f256fac 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -44,7 +44,7 @@ struct report { struct perf_tool tool; struct perf_session *session; - bool force, use_tui, use_gtk, use_stdio; + bool use_tui, use_gtk, use_stdio; bool hide_unresolved; bool dont_use_callchains; bool show_full_info; @@ -678,7 +678,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "file", "vmlinux pathname"), OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file", "kallsyms pathname"), - OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"), + OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, @@ -832,7 +832,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) } file.path = input_name; - file.force = report.force; + file.force = symbol_conf.force; repeat: session = perf_session__new(&file, false, &report.tool); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index e5afb89..fa9eb92 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1430,7 +1430,6 @@ close_file_and_continue: struct popup_action { struct thread *thread; - struct dso *dso; struct map_symbol ms; int socket; @@ -1565,7 +1564,6 @@ add_dso_opt(struct hist_browser *browser, struct popup_action *act, return 0; act->ms.map = map; - act->dso = map->dso; act->fn = do_zoom_dso; return 1; } @@ -1827,7 +1825,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, while (1) { struct thread *thread = NULL; - struct dso *dso = NULL; struct map *map = NULL; int choice = 0; int socked_id = -1; @@ -1839,8 +1836,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); map = browser->selection->map; - if (map) - dso = map->dso; socked_id = browser->he_selection->socket; } switch (key) { @@ -1874,7 +1869,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, hist_browser__dump(browser); continue; case 'd': - actions->dso = dso; + actions->ms.map = map; do_zoom_dso(browser, actions); continue; case 'V': diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index d909459..217b5a6 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -76,6 +76,7 @@ struct perf_tool build_id__mark_dso_hit_ops = { .exit = perf_event__exit_del_thread, .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, + .ordered_events = true, }; int build_id__sprintf(const u8 *build_id, int len, char *bf) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 7c0c083..425df5c 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -933,6 +933,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root, /* Add new node and rebalance tree */ rb_link_node(&dso->rb_node, parent, p); rb_insert_color(&dso->rb_node, root); + dso->root = root; } return NULL; } @@ -945,15 +946,30 @@ static inline struct dso *__dso__find_by_longname(struct rb_root *root, void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated) { + struct rb_root *root = dso->root; + if (name == NULL) return; if (dso->long_name_allocated) free((char *)dso->long_name); + if (root) { + rb_erase(&dso->rb_node, root); + /* + * __dso__findlink_by_longname() isn't guaranteed to add it + * back, so a clean removal is required here. + */ + RB_CLEAR_NODE(&dso->rb_node); + dso->root = NULL; + } + dso->long_name = name; dso->long_name_len = strlen(name); dso->long_name_allocated = name_allocated; + + if (root) + __dso__findlink_by_longname(root, dso, NULL); } void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated) @@ -1046,6 +1062,7 @@ struct dso *dso__new(const char *name) dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; RB_CLEAR_NODE(&dso->rb_node); + dso->root = NULL; INIT_LIST_HEAD(&dso->node); INIT_LIST_HEAD(&dso->data.open_entry); pthread_mutex_init(&dso->lock, NULL); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index fc8db9c..45ec4d0 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -135,6 +135,7 @@ struct dso { pthread_mutex_t lock; struct list_head node; struct rb_node rb_node; /* rbtree node sorted by long name */ + struct rb_root *root; /* root of rbtree that rb_node is in */ struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; struct { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 5ef90be..8b303ff 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -91,6 +91,7 @@ static void dsos__purge(struct dsos *dsos) list_for_each_entry_safe(pos, n, &dsos->head, node) { RB_CLEAR_NODE(&pos->rb_node); + pos->root = NULL; list_del_init(&pos->node); dso__put(pos); } diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index bd8f03d..05012bb 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1183,7 +1183,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) container_of(pf, struct trace_event_finder, pf); struct perf_probe_point *pp = &pf->pev->point; struct probe_trace_event *tev; - struct perf_probe_arg *args; + struct perf_probe_arg *args = NULL; int ret, i; /* Check number of tevs */ @@ -1198,19 +1198,23 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr, pp->retprobe, pp->function, &tev->point); if (ret < 0) - return ret; + goto end; tev->point.realname = strdup(dwarf_diename(sc_die)); - if (!tev->point.realname) - return -ENOMEM; + if (!tev->point.realname) { + ret = -ENOMEM; + goto end; + } pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, tev->point.offset); /* Expand special probe argument if exist */ args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS); - if (args == NULL) - return -ENOMEM; + if (args == NULL) { + ret = -ENOMEM; + goto end; + } ret = expand_probe_args(sc_die, pf, args); if (ret < 0) @@ -1234,6 +1238,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) } end: + if (ret) { + clear_probe_trace_event(tev); + tf->ntevs--; + } free(args); return ret; } @@ -1246,7 +1254,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, struct trace_event_finder tf = { .pf = {.pev = pev, .callback = add_probe_trace_event}, .max_tevs = probe_conf.max_probes, .mod = dbg->mod}; - int ret; + int ret, i; /* Allocate result tevs array */ *tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs); @@ -1258,6 +1266,8 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, ret = debuginfo__find_probes(dbg, &tf.pf); if (ret < 0) { + for (i = 0; i < tf.ntevs; i++) + clear_probe_trace_event(&tf.tevs[i]); zfree(tevs); return ret; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index b4cc766..cd08027 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -654,19 +654,24 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, struct map_groups *kmaps = map__kmaps(map); struct map *curr_map; struct symbol *pos; - int count = 0, moved = 0; + int count = 0; + struct rb_root old_root = dso->symbols[map->type]; struct rb_root *root = &dso->symbols[map->type]; struct rb_node *next = rb_first(root); if (!kmaps) return -1; + *root = RB_ROOT; + while (next) { char *module; pos = rb_entry(next, struct symbol, rb_node); next = rb_next(&pos->rb_node); + rb_erase_init(&pos->rb_node, &old_root); + module = strchr(pos->name, '\t'); if (module) *module = '\0'; @@ -674,28 +679,21 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, curr_map = map_groups__find(kmaps, map->type, pos->start); if (!curr_map || (filter && filter(curr_map, pos))) { - rb_erase_init(&pos->rb_node, root); symbol__delete(pos); - } else { - pos->start -= curr_map->start - curr_map->pgoff; - if (pos->end) - pos->end -= curr_map->start - curr_map->pgoff; - if (curr_map->dso != map->dso) { - rb_erase_init(&pos->rb_node, root); - symbols__insert( - &curr_map->dso->symbols[curr_map->type], - pos); - ++moved; - } else { - ++count; - } + continue; } + + pos->start -= curr_map->start - curr_map->pgoff; + if (pos->end) + pos->end -= curr_map->start - curr_map->pgoff; + symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + ++count; } /* Symbols have been adjusted */ dso->adjust_symbols = 1; - return count + moved; + return count; } /* @@ -1438,9 +1436,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (lstat(dso->name, &st) < 0) goto out; - if (st.st_uid && (st.st_uid != geteuid())) { + if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) { pr_warning("File %s not owned by current user or root, " - "ignoring it.\n", dso->name); + "ignoring it (use -f to override).\n", dso->name); goto out; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 40073c6..dcd786e 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -84,6 +84,7 @@ struct symbol_conf { unsigned short priv_size; unsigned short nr_events; bool try_vmlinux_path, + force, ignore_vmlinux, ignore_vmlinux_buildid, show_kernel_path, diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index d8e4b20..0dac7e0 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1173,9 +1173,9 @@ dump_nhm_platform_info(void) unsigned long long msr; unsigned int ratio; - get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); + get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); - fprintf(stderr, "cpu%d: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr); + fprintf(stderr, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr); ratio = (msr >> 40) & 0xFF; fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency frequency\n", @@ -1807,7 +1807,7 @@ void check_permissions() * * MSR_SMI_COUNT 0x00000034 * - * MSR_NHM_PLATFORM_INFO 0x000000ce + * MSR_PLATFORM_INFO 0x000000ce * MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 * * MSR_PKG_C3_RESIDENCY 0x000003f8 @@ -1876,7 +1876,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; - get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); + get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); base_ratio = (msr >> 8) & 0xFF; base_hz = base_ratio * bclk * 1000000; diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index bcf5ec7..5a60162 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -128,6 +128,7 @@ static const char * const page_flag_names[] = { [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", [KPF_ZERO_PAGE] = "z:zero_page", + [KPF_IDLE] = "i:idle_page", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", |
