diff options
395 files changed, 12642 insertions, 4200 deletions
diff --git a/Documentation/crypto/asymmetric-keys.txt b/Documentation/crypto/asymmetric-keys.txt index b82b6ad48488..5969bf42562a 100644 --- a/Documentation/crypto/asymmetric-keys.txt +++ b/Documentation/crypto/asymmetric-keys.txt @@ -10,6 +10,7 @@ Contents: - Signature verification. - Asymmetric key subtypes. - Instantiation data parsers. + - Keyring link restrictions. ======== @@ -318,7 +319,8 @@ KEYRING LINK RESTRICTIONS ========================= Keyrings created from userspace using add_key can be configured to check the -signature of the key being linked. +signature of the key being linked. Keys without a valid signature are not +allowed to link. Several restriction methods are available: @@ -327,9 +329,10 @@ Several restriction methods are available: - Option string used with KEYCTL_RESTRICT_KEYRING: - "builtin_trusted" - The kernel builtin trusted keyring will be searched for the signing - key. The ca_keys kernel parameter also affects which keys are used for - signature verification. + The kernel builtin trusted keyring will be searched for the signing key. + If the builtin trusted keyring is not configured, all links will be + rejected. The ca_keys kernel parameter also affects which keys are used + for signature verification. (2) Restrict using the kernel builtin and secondary trusted keyrings @@ -337,8 +340,10 @@ Several restriction methods are available: - "builtin_and_secondary_trusted" The kernel builtin and secondary trusted keyrings will be searched for the - signing key. The ca_keys kernel parameter also affects which keys are used - for signature verification. + signing key. If the secondary trusted keyring is not configured, this + restriction will behave like the "builtin_trusted" option. The ca_keys + kernel parameter also affects which keys are used for signature + verification. (3) Restrict using a separate key or keyring @@ -346,7 +351,7 @@ Several restriction methods are available: - "key_or_keyring:<key or keyring serial number>[:chain]" Whenever a key link is requested, the link will only succeed if the key - being linked is signed by one of the designated keys. This key may be + being linked is signed by one of the designated keys. This key may be specified directly by providing a serial number for one asymmetric key, or a group of keys may be searched for the signing key by providing the serial number for a keyring. @@ -354,7 +359,51 @@ Several restriction methods are available: When the "chain" option is provided at the end of the string, the keys within the destination keyring will also be searched for signing keys. This allows for verification of certificate chains by adding each - cert in order (starting closest to the root) to one keyring. + certificate in order (starting closest to the root) to a keyring. For + instance, one keyring can be populated with links to a set of root + certificates, with a separate, restricted keyring set up for each + certificate chain to be validated: + + # Create and populate a keyring for root certificates + root_id=`keyctl add keyring root-certs "" @s` + keyctl padd asymmetric "" $root_id < root1.cert + keyctl padd asymmetric "" $root_id < root2.cert + + # Create and restrict a keyring for the certificate chain + chain_id=`keyctl add keyring chain "" @s` + keyctl restrict_keyring $chain_id asymmetric key_or_keyring:$root_id:chain + + # Attempt to add each certificate in the chain, starting with the + # certificate closest to the root. + keyctl padd asymmetric "" $chain_id < intermediateA.cert + keyctl padd asymmetric "" $chain_id < intermediateB.cert + keyctl padd asymmetric "" $chain_id < end-entity.cert + + If the final end-entity certificate is successfully added to the "chain" + keyring, we can be certain that it has a valid signing chain going back to + one of the root certificates. + + A single keyring can be used to verify a chain of signatures by + restricting the keyring after linking the root certificate: + + # Create a keyring for the certificate chain and add the root + chain2_id=`keyctl add keyring chain2 "" @s` + keyctl padd asymmetric "" $chain2_id < root1.cert + + # Restrict the keyring that already has root1.cert linked. The cert + # will remain linked by the keyring. + keyctl restrict_keyring $chain2_id asymmetric key_or_keyring:0:chain + + # Attempt to add each certificate in the chain, starting with the + # certificate closest to the root. + keyctl padd asymmetric "" $chain2_id < intermediateA.cert + keyctl padd asymmetric "" $chain2_id < intermediateB.cert + keyctl padd asymmetric "" $chain2_id < end-entity.cert + + If the final end-entity certificate is successfully added to the "chain2" + keyring, we can be certain that there is a valid signing chain going back + to the root certificate that was added before the keyring was restricted. + In all of these cases, if the signing key is found the signature of the key to be linked will be verified using the signing key. The requested key is added diff --git a/Documentation/devicetree/bindings/clock/img,boston-clock.txt b/Documentation/devicetree/bindings/clock/img,boston-clock.txt new file mode 100644 index 000000000000..7bc5e9ffb624 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/img,boston-clock.txt @@ -0,0 +1,31 @@ +Binding for Imagination Technologies MIPS Boston clock sources. + +This binding uses the common clock binding[1]. + +[1] Documentation/devicetree/bindings/clock/clock-bindings.txt + +The device node must be a child node of the syscon node corresponding to the +Boston system's platform registers. + +Required properties: +- compatible : Should be "img,boston-clock". +- #clock-cells : Should be set to 1. + Values available for clock consumers can be found in the header file: + <dt-bindings/clock/boston-clock.h> + +Example: + + system-controller@17ffd000 { + compatible = "img,boston-platform-regs", "syscon"; + reg = <0x17ffd000 0x1000>; + + clk_boston: clock { + compatible = "img,boston-clock"; + #clock-cells = <1>; + }; + }; + + uart0: uart@17ffe000 { + /* ... */ + clocks = <&clk_boston BOSTON_CLK_SYS>; + }; diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt index 192d8cbcc5f9..918972babcd8 100644 --- a/Documentation/fault-injection/fault-injection.txt +++ b/Documentation/fault-injection/fault-injection.txt @@ -136,12 +136,13 @@ use the boot option: o proc entries -- /proc/self/task/<current-tid>/fail-nth: +- /proc/<pid>/fail-nth: +- /proc/self/task/<tid>/fail-nth: - Write to this file of integer N makes N-th call in the current task fail - (N is 0-based). Read from this file returns a single char 'Y' or 'N' - that says if the fault setup with a previous write to this file was - injected or not, and disables the fault if it wasn't yet injected. + Write to this file of integer N makes N-th call in the task fail. + Read from this file returns a integer value. A value of '0' indicates + that the fault setup with a previous write to this file was injected. + A positive integer N indicates that the fault wasn't yet injected. Note that this file enables all types of faults (slab, futex, etc). This setting takes precedence over all other generic debugfs settings like probability, interval, times, etc. But per-capability settings @@ -320,18 +321,19 @@ int main() system("echo N > /sys/kernel/debug/failslab/ignore-gfp-wait"); sprintf(buf, "/proc/self/task/%ld/fail-nth", syscall(SYS_gettid)); fail_nth = open(buf, O_RDWR); - for (i = 0;; i++) { + for (i = 1;; i++) { sprintf(buf, "%d", i); write(fail_nth, buf, strlen(buf)); res = socketpair(AF_LOCAL, SOCK_STREAM, 0, fds); err = errno; - read(fail_nth, buf, 1); + pread(fail_nth, buf, sizeof(buf), 0); if (res == 0) { close(fds[0]); close(fds[1]); } - printf("%d-th fault %c: res=%d/%d\n", i, buf[0], res, err); - if (buf[0] != 'Y') + printf("%d-th fault %c: res=%d/%d\n", i, atoi(buf) ? 'N' : 'Y', + res, err); + if (atoi(buf)) break; } return 0; @@ -339,7 +341,6 @@ int main() An example output: -0-th fault Y: res=-1/23 1-th fault Y: res=-1/23 2-th fault Y: res=-1/23 3-th fault Y: res=-1/12 diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 48c9faa73a76..73e7d91f03dc 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -1225,12 +1225,6 @@ The underlying reason for the above rules is to make sure, that a mount can be accurately replicated (e.g. umounting and mounting again) based on the information found in /proc/mounts. -A simple method of saving options at mount/remount time and showing -them is provided with the save_mount_options() and -generic_show_options() helper functions. Please note, that using -these may have drawbacks. For more info see header comments for these -functions in fs/namespace.c. - Resources ========= diff --git a/Documentation/ntb.txt b/Documentation/ntb.txt index e4771e5c2ad7..a043854d28df 100644 --- a/Documentation/ntb.txt +++ b/Documentation/ntb.txt @@ -3,14 +3,16 @@ NTB Drivers =========== NTB (Non-Transparent Bridge) is a type of PCI-Express bridge chip that connects -the separate memory systems of two computers to the same PCI-Express fabric. -Existing NTB hardware supports a common feature set, including scratchpad -registers, doorbell registers, and memory translation windows. Scratchpad -registers are read-and-writable registers that are accessible from either side -of the device, so that peers can exchange a small amount of information at a -fixed address. Doorbell registers provide a way for peers to send interrupt -events. Memory windows allow translated read and write access to the peer -memory. +the separate memory systems of two or more computers to the same PCI-Express +fabric. Existing NTB hardware supports a common feature set: doorbell +registers and memory translation windows, as well as non common features like +scratchpad and message registers. Scratchpad registers are read-and-writable +registers that are accessible from either side of the device, so that peers can +exchange a small amount of information at a fixed address. Message registers can +be utilized for the same purpose. Additionally they are provided with with +special status bits to make sure the information isn't rewritten by another +peer. Doorbell registers provide a way for peers to send interrupt events. +Memory windows allow translated read and write access to the peer memory. NTB Core Driver (ntb) ===================== @@ -30,6 +32,88 @@ as ntb hardware, or hardware drivers, are inserted and removed. The registration uses the Linux Device framework, so it should feel familiar to anyone who has written a pci driver. +NTB Typical client driver implementation +---------------------------------------- + +Primary purpose of NTB is to share some peace of memory between at least two +systems. So the NTB device features like Scratchpad/Message registers are +mainly used to perform the proper memory window initialization. Typically +there are two types of memory window interfaces supported by the NTB API: +inbound translation configured on the local ntb port and outbound translation +configured by the peer, on the peer ntb port. The first type is +depicted on the next figure + +Inbound translation: + Memory: Local NTB Port: Peer NTB Port: Peer MMIO: + ____________ + | dma-mapped |-ntb_mw_set_trans(addr) | + | memory | _v____________ | ______________ + | (addr) |<======| MW xlat addr |<====| MW base addr |<== memory-mapped IO + |------------| |--------------| | |--------------| + +So typical scenario of the first type memory window initialization looks: +1) allocate a memory region, 2) put translated address to NTB config, +3) somehow notify a peer device of performed initialization, 4) peer device +maps corresponding outbound memory window so to have access to the shared +memory region. + +The second type of interface, that implies the shared windows being +initialized by a peer device, is depicted on the figure: + +Outbound translation: + Memory: Local NTB Port: Peer NTB Port: Peer MMIO: + ____________ ______________ + | dma-mapped | | | MW base addr |<== memory-mapped IO + | memory | | |--------------| + | (addr) |<===================| MW xlat addr |<-ntb_peer_mw_set_trans(addr) + |------------| | |--------------| + +Typical scenario of the second type interface initialization would be: +1) allocate a memory region, 2) somehow deliver a translated address to a peer +device, 3) peer puts the translated address to NTB config, 4) peer device maps +outbound memory window so to have access to the shared memory region. + +As one can see the described scenarios can be combined in one portable +algorithm. + Local device: + 1) Allocate memory for a shared window + 2) Initialize memory window by translated address of the allocated region + (it may fail if local memory window initialization is unsupported) + 3) Send the translated address and memory window index to a peer device + Peer device: + 1) Initialize memory window with retrieved address of the allocated + by another device memory region (it may fail if peer memory window + initialization is unsupported) + 2) Map outbound memory window + +In accordance with this scenario, the NTB Memory Window API can be used as +follows: + Local device: + 1) ntb_mw_count(pidx) - retrieve number of memory ranges, which can + be allocated for memory windows between local device and peer device + of port with specified index. + 2) ntb_get_align(pidx, midx) - retrieve parameters restricting the + shared memory region alignment and size. Then memory can be properly + allocated. + 3) Allocate physically contiguous memory region in compliance with + restrictions retrieved in 2). + 4) ntb_mw_set_trans(pidx, midx) - try to set translation address of + the memory window with specified index for the defined peer device + (it may fail if local translated address setting is not supported) + 5) Send translated base address (usually together with memory window + number) to the peer device using, for instance, scratchpad or message + registers. + Peer device: + 1) ntb_peer_mw_set_trans(pidx, midx) - try to set received from other + device (related to pidx) translated address for specified memory + window. It may fail if retrieved address, for instance, exceeds + maximum possible address or isn't properly aligned. + 2) ntb_peer_mw_get_addr(widx) - retrieve MMIO address to map the memory + window so to have an access to the shared memory. + +Also it is worth to note, that method ntb_mw_count(pidx) should return the +same value as ntb_peer_mw_count() on the peer with port index - pidx. + NTB Transport Client (ntb\_transport) and NTB Netdev (ntb\_netdev) ------------------------------------------------------------------ diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst index 0d831a7afe4f..1648fa80b3bf 100644 --- a/Documentation/security/keys/core.rst +++ b/Documentation/security/keys/core.rst @@ -894,6 +894,12 @@ The keyctl syscall functions are: To apply a keyring restriction the process must have Set Attribute permission and the keyring must not be previously restricted. + One application of restricted keyrings is to verify X.509 certificate + chains or individual certificate signatures using the asymmetric key type. + See Documentation/crypto/asymmetric-keys.txt for specific restrictions + applicable to the asymmetric key type. + + Kernel Services =============== diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 3a9831b72945..e63a35fafef0 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4329,3 +4329,21 @@ Querying this capability returns a bitmap indicating the possible virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N (counting from the right) is set, then a virtual SMT mode of 2^N is available. + +8.11 KVM_CAP_HYPERV_SYNIC2 + +Architectures: x86 + +This capability enables a newer version of Hyper-V Synthetic interrupt +controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM +doesn't clear SynIC message and event flags pages when they are enabled by +writing to the respective MSRs. + +8.12 KVM_CAP_HYPERV_VP_INDEX + +Architectures: x86 + +This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its +value is used to denote the target vcpu for a SynIC interrupt. For +compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this +capability is absent, userspace can still query this msr's value. diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt index 0a9ea515512a..1ebecc115dc6 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virtual/kvm/msr.txt @@ -166,10 +166,11 @@ MSR_KVM_SYSTEM_TIME: 0x12 MSR_KVM_ASYNC_PF_EN: 0x4b564d02 data: Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area which must be in guest RAM and must be - zeroed. Bits 5-2 are reserved and should be zero. Bit 0 is 1 + zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1 when asynchronous page faults are enabled on the vcpu 0 when disabled. Bit 1 is 1 if asynchronous page faults can be injected - when vcpu is in cpl == 0. + when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults + are delivered to L1 as #PF vmexits. First 4 byte of 64 byte memory location will be written to by the hypervisor at the time of asynchronous page fault (APF) diff --git a/MAINTAINERS b/MAINTAINERS index 7d9bd4a041af..205d3977ac46 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2516,10 +2516,10 @@ S: Supported F: drivers/media/platform/sti/delta BEFS FILE SYSTEM -M: Luis de Bethencourt <luisbg@osg.samsung.com> +M: Luis de Bethencourt <luisbg@kernel.org> M: Salah Triki <salah.triki@gmail.com> S: Maintained -T: git git://github.com/luisbg/linux-befs.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/luisbg/linux-befs.git F: Documentation/filesystems/befs.txt F: fs/befs/ @@ -7554,6 +7554,15 @@ F: include/linux/kmemleak.h F: mm/kmemleak.c F: mm/kmemleak-test.c +KMOD MODULE USERMODE HELPER +M: "Luis R. Rodriguez" <mcgrof@kernel.org> +L: linux-kernel@vger.kernel.org +S: Maintained +F: kernel/kmod.c +F: include/linux/kmod.h +F: lib/test_kmod.c +F: tools/testing/selftests/kmod/ + KPROBES M: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> @@ -8723,6 +8732,12 @@ F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ +MIPS GENERIC PLATFORM +M: Paul Burton <paul.burton@imgtec.com> +L: linux-mips@linux-mips.org +S: Supported +F: arch/mips/generic/ + MIPS/LOONGSON1 ARCHITECTURE M: Keguang Zhang <keguang.zhang@gmail.com> L: linux-mips@linux-mips.org @@ -8732,6 +8747,16 @@ F: arch/mips/include/asm/mach-loongson32/ F: drivers/*/*loongson1* F: drivers/*/*/*loongson1* +MIPS BOSTON DEVELOPMENT BOARD +M: Paul Burton <paul.burton@imgtec.com> +L: linux-mips@linux-mips.org +S: Maintained +F: Documentation/devicetree/bindings/clock/img,boston-clock.txt +F: arch/mips/boot/dts/img/boston.dts +F: arch/mips/configs/generic/board-boston.config +F: drivers/clk/imgtec/clk-boston.c +F: include/dt-bindings/clock/boston-clock.h + MIROSOUND PCM20 FM RADIO RECEIVER DRIVER M: Hans Verkuil <hverkuil@xs4all.nl> L: linux-media@vger.kernel.org @@ -9381,6 +9406,12 @@ F: include/linux/ntb.h F: include/linux/ntb_transport.h F: tools/testing/selftests/ntb/ +NTB IDT DRIVER +M: Serge Semin <fancer.lancer@gmail.com> +L: linux-ntb@googlegroups.com +S: Supported +F: drivers/ntb/hw/idt/ + NTB INTEL DRIVER M: Jon Mason <jdmason@kudzu.us> M: Dave Jiang <dave.jiang@intel.com> diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h index acf1d14b89a6..29d3a1524bce 100644 --- a/arch/arm/include/asm/flat.h +++ b/arch/arm/include/asm/flat.h @@ -5,12 +5,31 @@ #ifndef __ARM_FLAT_H__ #define __ARM_FLAT_H__ +#include <linux/uaccess.h> + #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - ({ unsigned long __val; __get_user_unaligned(__val, rp); __val; }) -#define flat_put_addr_at_rp(rp, val, relval) __put_user_unaligned(val, rp) + +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + return copy_from_user(addr, rp, 4) ? -EFAULT : 0; +#else + return get_user(*addr, rp); +#endif +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + return copy_to_user(rp, &addr, 4) ? -EFAULT : 0; +#else + return put_user(addr, rp); +#endif +} + #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 6838abc04279..0bf2347495f1 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -17,13 +17,6 @@ #include <asm/unified.h> #include <asm/compiler.h> -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS -#include <asm-generic/uaccess-unaligned.h> -#else -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user -#endif - #include <asm/extable.h> /* diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 56dc1a3a33b4..c1809fb549dd 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -480,7 +480,7 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, ret = pcibios_init_resource(nr, sys, hw->io_optional); if (ret) { - kfree(sys); + pci_free_host_bridge(bridge); break; } diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 59f09e6a6cb8..8f0a1de11e4a 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -254,8 +254,6 @@ do { \ (void)0; \ }) -#define __get_user_unaligned __get_user - #define get_user(x, ptr) \ ({ \ __typeof__(*(ptr)) __user *__p = (ptr); \ @@ -320,8 +318,6 @@ do { \ (void)0; \ }) -#define __put_user_unaligned __put_user - #define put_user(x, ptr) \ ({ \ __typeof__(*(ptr)) __user *__p = (ptr); \ diff --git a/arch/blackfin/include/asm/flat.h b/arch/blackfin/include/asm/flat.h index c1314c56dd18..296d7f56fbfd 100644 --- a/arch/blackfin/include/asm/flat.h +++ b/arch/blackfin/include/asm/flat.h @@ -14,23 +14,28 @@ #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) -extern unsigned long bfin_get_addr_from_rp (unsigned long *ptr, - unsigned long relval, - unsigned long flags, - unsigned long *persistent); +extern unsigned long bfin_get_addr_from_rp (u32 *ptr, u32 relval, + u32 flags, u32 *persistent); -extern void bfin_put_addr_at_rp(unsigned long *ptr, unsigned long addr, - unsigned long relval); +extern void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval); /* The amount by which a relocation can exceed the program image limits without being regarded as an error. */ #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - bfin_get_addr_from_rp(rp, relval, flags, persistent) -#define flat_put_addr_at_rp(rp, val, relval) \ - bfin_put_addr_at_rp(rp, val, relval) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = bfin_get_addr_from_rp(rp, relval, flags, persistent); + return 0; +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 val, u32 relval) +{ + bfin_put_addr_at_rp(rp, val, relval); + return 0; +} /* Convert a relocation entry into an address. */ static inline unsigned long diff --git a/arch/blackfin/kernel/flat.c b/arch/blackfin/kernel/flat.c index b5b658449616..d29ab6a2e909 100644 --- a/arch/blackfin/kernel/flat.c +++ b/arch/blackfin/kernel/flat.c @@ -13,14 +13,14 @@ #define FLAT_BFIN_RELOC_TYPE_16H_BIT 1 #define FLAT_BFIN_RELOC_TYPE_32_BIT 2 -unsigned long bfin_get_addr_from_rp(unsigned long *ptr, - unsigned long relval, - unsigned long flags, - unsigned long *persistent) +unsigned long bfin_get_addr_from_rp(u32 *ptr, + u32 relval, + u32 flags, + u32 *persistent) { unsigned short *usptr = (unsigned short *)ptr; int type = (relval >> 26) & 7; - unsigned long val; + u32 val; switch (type) { case FLAT_BFIN_RELOC_TYPE_16_BIT: @@ -59,8 +59,7 @@ EXPORT_SYMBOL(bfin_get_addr_from_rp); * Insert the address ADDR into the symbol reference at RP; * RELVAL is the raw relocation-table entry from which RP is derived */ -void bfin_put_addr_at_rp(unsigned long *ptr, unsigned long addr, - unsigned long relval) +void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval) { unsigned short *usptr = (unsigned short *)ptr; int type = (relval >> 26) & 7; diff --git a/arch/c6x/include/asm/flat.h b/arch/c6x/include/asm/flat.h index a1858bd5f6c8..6f1feb00bd52 100644 --- a/arch/c6x/include/asm/flat.h +++ b/arch/c6x/include/asm/flat.h @@ -1,11 +1,22 @@ #ifndef __ASM_C6X_FLAT_H #define __ASM_C6X_FLAT_H +#include <asm/unaligned.h> + #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val, rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = get_unaligned((__force u32 *)rp); + return 0; +} +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + put_unaligned(addr, (__force u32 *)rp); + return 0; +} #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h index a4898eccf2bf..18d024251738 100644 --- a/arch/h8300/include/asm/flat.h +++ b/arch/h8300/include/asm/flat.h @@ -5,6 +5,8 @@ #ifndef __H8300_FLAT_H__ #define __H8300_FLAT_H__ +#include <asm/unaligned.h> + #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) 1 #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) @@ -18,11 +20,21 @@ */ #define flat_get_relocate_addr(rel) (rel & ~0x00000001) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - ({(void)persistent; \ - get_unaligned(rp) & (((flags) & FLAT_FLAG_GOTPIC) ? \ - 0xffffffff : 0x00ffffff); }) -#define flat_put_addr_at_rp(rp, addr, rel) \ - put_unaligned(((*(char *)(rp)) << 24) | ((addr) & 0x00ffffff), (rp)) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + u32 val = get_unaligned((__force u32 *)rp); + if (!(flags & FLAT_FLAG_GOTPIC) + val &= 0x00ffffff; + *addr = val; + return 0; +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + u32 *p = (__force u32 *)rp; + put_unaligned((addr & 0x00ffffff) | (*(char *)p << 24), p); + return 0; +} #endif /* __H8300_FLAT_H__ */ diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index b2106b01e84f..0890ded638f0 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -87,42 +87,6 @@ static inline int __access_ok(const void __user *p, unsigned long size) #define __put_user(x, ptr) __put_user_nocheck((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr))) #define __get_user(x, ptr) __get_user_nocheck((x), (ptr), sizeof(*(ptr))) -extern long __put_user_unaligned_unknown (void); - -#define __put_user_unaligned(x, ptr) \ -({ \ - long __ret; \ - switch (sizeof(*(ptr))) { \ - case 1: __ret = __put_user((x), (ptr)); break; \ - case 2: __ret = (__put_user((x), (u8 __user *)(ptr))) \ - | (__put_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break; \ - case 4: __ret = (__put_user((x), (u16 __user *)(ptr))) \ - | (__put_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break; \ - case 8: __ret = (__put_user((x), (u32 __user *)(ptr))) \ - | (__put_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break; \ - default: __ret = __put_user_unaligned_unknown(); \ - } \ - __ret; \ -}) - -extern long __get_user_unaligned_unknown (void); - -#define __get_user_unaligned(x, ptr) \ -({ \ - long __ret; \ - switch (sizeof(*(ptr))) { \ - case 1: __ret = __get_user((x), (ptr)); break; \ - case 2: __ret = (__get_user((x), (u8 __user *)(ptr))) \ - | (__get_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break; \ - case 4: __ret = (__get_user((x), (u16 __user *)(ptr))) \ - | (__get_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break; \ - case 8: __ret = (__get_user((x), (u32 __user *)(ptr))) \ - | (__get_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break; \ - default: __ret = __get_user_unaligned_unknown(); \ - } \ - __ret; \ -}) - #ifdef ASM_SUPPORTED struct __large_struct { unsigned long buf[100]; }; # define __m(x) (*(struct __large_struct __user *)(x)) diff --git a/arch/m32r/include/asm/flat.h b/arch/m32r/include/asm/flat.h index 5d711c4688fb..455ce7ddbf14 100644 --- a/arch/m32r/include/asm/flat.h +++ b/arch/m32r/include/asm/flat.h @@ -17,11 +17,6 @@ #define flat_set_persistent(relval, p) 0 #define flat_reloc_valid(reloc, size) \ (((reloc) - textlen_for_m32r_lo16_data) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - m32r_flat_get_addr_from_rp(rp, relval, (text_len) ) - -#define flat_put_addr_at_rp(rp, addr, relval) \ - m32r_flat_put_addr_at_rp(rp, addr, relval) /* Convert a relocation entry into an address. */ static inline unsigned long @@ -57,9 +52,9 @@ flat_get_relocate_addr (unsigned long relval) static unsigned long textlen_for_m32r_lo16_data = 0; -static inline unsigned long m32r_flat_get_addr_from_rp (unsigned long *rp, - unsigned long relval, - unsigned long textlen) +static inline unsigned long m32r_flat_get_addr_from_rp (u32 *rp, + u32 relval, + u32 textlen) { unsigned int reloc = flat_m32r_get_reloc_type (relval); textlen_for_m32r_lo16_data = 0; @@ -100,9 +95,7 @@ static inline unsigned long m32r_flat_get_addr_from_rp (unsigned long *rp, return ~0; /* bogus value */ } -static inline void m32r_flat_put_addr_at_rp (unsigned long *rp, - unsigned long addr, - unsigned long relval) +static inline void flat_put_addr_at_rp(u32 *rp, u32 addr, u32 relval) { unsigned int reloc = flat_m32r_get_reloc_type (relval); if (reloc & 0xf0) { @@ -142,4 +135,8 @@ static inline void m32r_flat_put_addr_at_rp (unsigned long *rp, } } +// kludge - text_len is a local variable in the only user. +#define flat_get_addr_from_rp(rp, relval, flags, addr, persistent) \ + (m32r_flat_get_addr_from_rp(rp, relval, text_len), 0) + #endif /* __ASM_M32R_FLAT_H */ diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h index 00c392b0cabd..48b62790fe70 100644 --- a/arch/m68k/include/asm/flat.h +++ b/arch/m68k/include/asm/flat.h @@ -5,12 +5,29 @@ #ifndef __M68KNOMMU_FLAT_H__ #define __M68KNOMMU_FLAT_H__ +#include <linux/uaccess.h> + #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) \ - ({ unsigned long __val; __get_user_unaligned(__val, rp); __val; }) -#define flat_put_addr_at_rp(rp, val, relval) __put_user_unaligned(val, rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ +#ifdef CONFIG_CPU_HAS_NO_UNALIGNED + return copy_from_user(addr, rp, 4) ? -EFAULT : 0; +#else + return get_user(*addr, rp); +#endif +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ +#ifdef CONFIG_CPU_HAS_NO_UNALIGNED + return copy_to_user(rp, &addr, 4) ? -EFAULT : 0; +#else + return put_user(addr, rp); +#endif +} #define flat_get_relocate_addr(rel) (rel) static inline int flat_set_persistent(unsigned long relval, diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index 67b3481d6020..63ba18e4c9a2 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -3,11 +3,4 @@ #else #include <asm/uaccess_mm.h> #endif - #include <asm/extable.h> -#ifdef CONFIG_CPU_HAS_NO_UNALIGNED -#include <asm-generic/uaccess-unaligned.h> -#else -#define __get_user_unaligned(x, ptr) __get_user((x), (ptr)) -#define __put_user_unaligned(x, ptr) __put_user((x), (ptr)) -#endif diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h index 6847c1512c7b..f23c3d266bae 100644 --- a/arch/microblaze/include/asm/flat.h +++ b/arch/microblaze/include/asm/flat.h @@ -32,29 +32,27 @@ * reference */ -static inline unsigned long -flat_get_addr_from_rp(unsigned long *rp, unsigned long relval, - unsigned long flags, unsigned long *persistent) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) { - unsigned long addr; - (void)flags; + u32 *p = (__force u32 *)rp; /* Is it a split 64/32 reference? */ if (relval & 0x80000000) { /* Grab the two halves of the reference */ - unsigned long val_hi, val_lo; + u32 val_hi, val_lo; - val_hi = get_unaligned(rp); - val_lo = get_unaligned(rp+1); + val_hi = get_unaligned(p); + val_lo = get_unaligned(p+1); /* Crack the address out */ - addr = ((val_hi & 0xffff) << 16) + (val_lo & 0xffff); + *addr = ((val_hi & 0xffff) << 16) + (val_lo & 0xffff); } else { /* Get the address straight out */ - addr = get_unaligned(rp); + *addr = get_unaligned(p); } - return addr; + return 0; } /* @@ -63,25 +61,27 @@ flat_get_addr_from_rp(unsigned long *rp, unsigned long relval, */ static inline void -flat_put_addr_at_rp(unsigned long *rp, unsigned long addr, unsigned long relval) +flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 relval) { + u32 *p = (__force u32 *)rp; /* Is this a split 64/32 reloc? */ if (relval & 0x80000000) { /* Get the two "halves" */ - unsigned long val_hi = get_unaligned(rp); - unsigned long val_lo = get_unaligned(rp + 1); + unsigned long val_hi = get_unaligned(p); + unsigned long val_lo = get_unaligned(p + 1); /* insert the address */ val_hi = (val_hi & 0xffff0000) | addr >> 16; val_lo = (val_lo & 0xffff0000) | (addr & 0xffff); /* store the two halves back into memory */ - put_unaligned(val_hi, rp); - put_unaligned(val_lo, rp+1); + put_unaligned(val_hi, p); + put_unaligned(val_lo, p+1); } else { /* Put it straight in, no messing around */ - put_unaligned(addr, rp); + put_unaligned(addr, p); } + return 0; } #define flat_get_relocate_addr(rel) (rel & 0x7fffffff) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 45bcd1cfcec0..8dd20358464f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1,75 +1,77 @@ config MIPS bool default y - select ARCH_SUPPORTS_UPROBES + select ARCH_BINFMT_ELF_STATE + select ARCH_CLOCKSOURCE_DATA + select ARCH_DISCARD_MEMBLOCK + select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP - select HAVE_CONTEXT_TRACKING - select HAVE_GENERIC_DMA_COHERENT - select HAVE_IDE - select HAVE_IRQ_EXIT_ON_IRQ_STACK - select HAVE_OPROFILE - select HAVE_PERF_EVENTS - select PERF_USE_VMALLOC + select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANT_IPC_PARSE_VERSION + select BUILDTIME_EXTABLE_SORT + select CLONE_BACKWARDS + select CPU_PM if CPU_IDLE + select GENERIC_ATOMIC64 if !64BIT + select GENERIC_CLOCKEVENTS + select GENERIC_CMOS_UPDATE + select GENERIC_CPU_AUTOPROBE + select GENERIC_IRQ_PROBE + select GENERIC_IRQ_SHOW + select GENERIC_PCI_IOMAP + select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC + select GENERIC_SMP_IDLE_THREAD + select GENERIC_TIME_VSYSCALL + select HANDLE_DOMAIN_IRQ + select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_CBPF_JIT if !CPU_MICROMIPS - select HAVE_FUNCTION_TRACER + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT + select HAVE_CBPF_JIT if (!64BIT && !CPU_MICROMIPS) + select HAVE_EBPF_JIT if (64BIT && !CPU_MICROMIPS) + select HAVE_CC_STACKPROTECTOR + select HAVE_CONTEXT_TRACKING + select HAVE_COPY_THREAD_TLS + select HAVE_C_RECORDMCOUNT + select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DMA_API_DEBUG + select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_C_RECORDMCOUNT select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER + select HAVE_GENERIC_DMA_COHERENT + select HAVE_IDE + select HAVE_IRQ_EXIT_ON_IRQ_STACK + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_SYSCALL_TRACEPOINTS - select HAVE_DEBUG_KMEMLEAK - select HAVE_SYSCALL_TRACEPOINTS - select ARCH_HAS_ELF_RANDOMIZE - select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT - select RTC_LIB if !MACH_LOONGSON64 - select GENERIC_ATOMIC64 if !64BIT - select HAVE_DMA_CONTIGUOUS - select HAVE_DMA_API_DEBUG - select GENERIC_IRQ_PROBE - select GENERIC_IRQ_SHOW - select GENERIC_PCI_IOMAP - select HAVE_ARCH_JUMP_LABEL - select ARCH_WANT_IPC_PARSE_VERSION - select IRQ_FORCED_THREADING select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select ARCH_DISCARD_MEMBLOCK - select GENERIC_SMP_IDLE_THREAD - select BUILDTIME_EXTABLE_SORT - select GENERIC_CPU_AUTOPROBE - select GENERIC_CLOCKEVENTS - select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC - select GENERIC_CMOS_UPDATE select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select VIRT_TO_BUS - select MODULES_USE_ELF_REL if MODULES + select HAVE_OPROFILE + select HAVE_PERF_EVENTS + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_VIRT_CPU_ACCOUNTING_GEN + select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if MODULES && 64BIT - select CLONE_BACKWARDS - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_CC_STACKPROTECTOR - select CPU_PM if CPU_IDLE - select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_BINFMT_ELF_STATE + select MODULES_USE_ELF_REL if MODULES + select PERF_USE_VMALLOC + select RTC_LIB if !MACH_LOONGSON64 select SYSCTL_EXCEPTION_TRACE - select HAVE_VIRT_CPU_ACCOUNTING_GEN - select HAVE_IRQ_TIME_ACCOUNTING - select GENERIC_TIME_VSYSCALL - select ARCH_CLOCKSOURCE_DATA - select HANDLE_DOMAIN_IRQ - select HAVE_EXIT_THREAD - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_COPY_THREAD_TLS + select VIRT_TO_BUS menu "Machine selection" @@ -1179,6 +1181,15 @@ config SYS_SUPPORTS_RELOCATABLE The platform must provide plat_get_fdt() if it selects CONFIG_USE_OF to allow access to command line and entropy sources. +config MIPS_CBPF_JIT + def_bool y + depends on BPF_JIT && HAVE_CBPF_JIT + +config MIPS_EBPF_JIT + def_bool y + depends on BPF_JIT && HAVE_EBPF_JIT + + # # Endianness selection. Sufficiently obscure so many users don't know what to # answer,so we try hard to limit the available choices. Also the use of a @@ -2062,7 +2073,7 @@ config CPU_SUPPORTS_UNCACHED_ACCELERATED bool config MIPS_PGD_C0_CONTEXT bool - default y if 64BIT && CPU_MIPSR2 && !CPU_XLP + default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP # # Set to y for ptrace access to watch registers. @@ -2370,6 +2381,7 @@ config MIPS_CPS select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU + select SYS_SUPPORTS_SCHED_SMT if CPU_MIPSR6 select SYS_SUPPORTS_SMP select WEAK_ORDERING help diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 02a1787c888c..04343625b929 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -160,7 +160,7 @@ cflags-$(CONFIG_CPU_MIPS32_R1) += $(call cc-option,-march=mips32,-mips32 -U_MIPS -Wa,-mips32 -Wa,--trap cflags-$(CONFIG_CPU_MIPS32_R2) += $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \ -Wa,-mips32r2 -Wa,--trap -cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap -modd-spreg cflags-$(CONFIG_CPU_MIPS64_R1) += $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ -Wa,-mips64 -Wa,--trap cflags-$(CONFIG_CPU_MIPS64_R2) += $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ diff --git a/arch/mips/boot/dts/img/Makefile b/arch/mips/boot/dts/img/Makefile index 69a65f0f82d2..3d70958d0f5a 100644 --- a/arch/mips/boot/dts/img/Makefile +++ b/arch/mips/boot/dts/img/Makefile @@ -1,6 +1,7 @@ -dtb-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb +dtb-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += boston.dtb -obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y)) +dtb-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb +obj-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb.o # Force kbuild to make empty built-in.o if necessary obj- += dummy.o diff --git a/arch/mips/boot/dts/img/boston.dts b/arch/mips/boot/dts/img/boston.dts new file mode 100644 index 000000000000..53bfa29a7093 --- /dev/null +++ b/arch/mips/boot/dts/img/boston.dts @@ -0,0 +1,224 @@ +/dts-v1/; + +#include <dt-bindings/clock/boston-clock.h> +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/interrupt-controller/mips-gic.h> + +/ { + #address-cells = <1>; + #size-cells = <1>; + compatible = "img,boston"; + + chosen { + stdout-path = "uart0:115200"; + }; + + aliases { + uart0 = &uart0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "img,mips"; + reg = <0>; + clocks = <&clk_boston BOSTON_CLK_CPU>; + }; + }; + + memory@0 { + device_type = "memory"; + reg = <0x00000000 0x10000000>; + }; + + pci0: pci@10000000 { + compatible = "xlnx,axi-pcie-host-1.00.a"; + device_type = "pci"; + reg = <0x10000000 0x2000000>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 2 IRQ_TYPE_LEVEL_HIGH>; + + ranges = <0x02000000 0 0x40000000 + 0x40000000 0 0x40000000>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pci0_intc 1>, + <0 0 0 2 &pci0_intc 2>, + <0 0 0 3 &pci0_intc 3>, + <0 0 0 4 &pci0_intc 4>; + + pci0_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + }; + + pci1: pci@12000000 { + compatible = "xlnx,axi-pcie-host-1.00.a"; + device_type = "pci"; + reg = <0x12000000 0x2000000>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 1 IRQ_TYPE_LEVEL_HIGH>; + + ranges = <0x02000000 0 0x20000000 + 0x20000000 0 0x20000000>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pci1_intc 1>, + <0 0 0 2 &pci1_intc 2>, + <0 0 0 3 &pci1_intc 3>, + <0 0 0 4 &pci1_intc 4>; + + pci1_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + }; + + pci2: pci@14000000 { + compatible = "xlnx,axi-pcie-host-1.00.a"; + device_type = "pci"; + reg = <0x14000000 0x2000000>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 0 IRQ_TYPE_LEVEL_HIGH>; + + ranges = <0x02000000 0 0x16000000 + 0x16000000 0 0x100000>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pci2_intc 1>, + <0 0 0 2 &pci2_intc 2>, + <0 0 0 3 &pci2_intc 3>, + <0 0 0 4 &pci2_intc 4>; + + pci2_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + pci2_root@0,0,0 { + compatible = "pci10ee,7021"; + reg = <0x00000000 0 0 0 0>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + eg20t_bridge@1,0,0 { + compatible = "pci8086,8800"; + reg = <0x00010000 0 0 0 0>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + eg20t_mac@2,0,1 { + compatible = "pci8086,8802"; + reg = <0x00020100 0 0 0 0>; + phy-reset-gpios = <&eg20t_gpio 6 + GPIO_ACTIVE_LOW>; + }; + + eg20t_gpio: eg20t_gpio@2,0,2 { + compatible = "pci8086,8803"; + reg = <0x00020200 0 0 0 0>; + + gpio-controller; + #gpio-cells = <2>; + }; + + eg20t_i2c@2,12,2 { + compatible = "pci8086,8817"; + reg = <0x00026200 0 0 0 0>; + + #address-cells = <1>; + #size-cells = <0>; + + rtc@0x68 { + compatible = "st,m41t81s"; + reg = <0x68>; + }; + }; + }; + }; + }; + + gic: interrupt-controller@16120000 { + compatible = "mti,gic"; + reg = <0x16120000 0x20000>; + + interrupt-controller; + #interrupt-cells = <3>; + + timer { + compatible = "mti,gic-timer"; + interrupts = <GIC_LOCAL 1 IRQ_TYPE_NONE>; + clocks = <&clk_boston BOSTON_CLK_CPU>; + }; + }; + + cdmm@16140000 { + compatible = "mti,mips-cdmm"; + reg = <0x16140000 0x8000>; + }; + + cpc@16200000 { + compatible = "mti,mips-cpc"; + reg = <0x16200000 0x8000>; + }; + + plat_regs: system-controller@17ffd000 { + compatible = "img,boston-platform-regs", "syscon"; + reg = <0x17ffd000 0x1000>; + + clk_boston: clock { + compatible = "img,boston-clock"; + #clock-cells = <1>; + }; + }; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&plat_regs>; + offset = <0x10>; + mask = <0x10>; + }; + + uart0: uart@17ffe000 { + compatible = "ns16550a"; + reg = <0x17ffe000 0x1000>; + reg-shift = <2>; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 3 IRQ_TYPE_LEVEL_HIGH>; + + clocks = <&clk_boston BOSTON_CLK_SYS>; + }; + + lcd: lcd@17fff000 { + compatible = "img,boston-lcd"; + reg = <0x17fff000 0x8>; + }; +}; diff --git a/arch/mips/boot/dts/mti/sead3.dts b/arch/mips/boot/dts/mti/sead3.dts index b112879a5d9d..4f8bc83c2960 100644 --- a/arch/mips/boot/dts/mti/sead3.dts +++ b/arch/mips/boot/dts/mti/sead3.dts @@ -11,15 +11,14 @@ #size-cells = <1>; compatible = "mti,sead-3"; model = "MIPS SEAD-3"; - interrupt-parent = <&gic>; chosen { - stdout-path = "uart1:115200"; + stdout-path = "serial1:115200"; }; aliases { - uart0 = &uart0; - uart1 = &uart1; + serial0 = &uart0; + serial1 = &uart1; }; cpus { @@ -54,18 +53,14 @@ * controller & should be probed first. */ interrupt-parent = <&cpu_intc>; - - timer { - compatible = "mti,gic-timer"; - interrupts = <GIC_LOCAL 1 IRQ_TYPE_NONE>; - }; }; ehci@1b200000 { compatible = "generic-ehci"; reg = <0x1b200000 0x1000>; - interrupts = <0>; /* GIC 0 or CPU 6 */ + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 0 IRQ_TYPE_LEVEL_HIGH>; /* GIC 0 or CPU 6 */ has-transaction-translator; }; @@ -227,7 +222,8 @@ clock-frequency = <14745600>; - interrupts = <3>; /* GIC 3 or CPU 4 */ + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 3 IRQ_TYPE_LEVEL_HIGH>; /* GIC 3 or CPU 4 */ no-loopback-test; }; @@ -241,7 +237,8 @@ clock-frequency = <14745600>; - interrupts = <2>; /* GIC 2 or CPU 4 */ + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 2 IRQ_TYPE_LEVEL_HIGH>; /* GIC 2 or CPU 4 */ no-loopback-test; }; @@ -251,7 +248,8 @@ reg = <0x1f010000 0x10000>; reg-io-width = <4>; - interrupts = <0>; /* GIC 0 or CPU 6 */ + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 0 IRQ_TYPE_LEVEL_HIGH>; /* GIC 0 or CPU 6 */ phy-mode = "mii"; smsc,irq-push-pull; diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig index 320772caf054..92fca3c42eac 100644 --- a/arch/mips/configs/ar7_defconfig +++ b/arch/mips/configs/ar7_defconfig @@ -3,7 +3,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_100=y CONFIG_KEXEC=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_KERNEL_LZMA=y CONFIG_SYSVIPC=y @@ -41,7 +40,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set @@ -86,7 +84,6 @@ CONFIG_MAC80211_RC_DEFAULT_PID=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FIRMWARE_IN_KERNEL is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -99,8 +96,6 @@ CONFIG_FIXED_PHY=y CONFIG_NET_ETHERNET=y CONFIG_MII=y CONFIG_CPMAC=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_PPP=m CONFIG_PPP_MULTILINK=y CONFIG_PPP_FILTER=y @@ -142,7 +137,6 @@ CONFIG_BSD_DISKLABEL=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="rootfstype=squashfs,jffs2" CONFIG_CRYPTO=y diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig index 134879c1310a..25ed914933e5 100644 --- a/arch/mips/configs/ath79_defconfig +++ b/arch/mips/configs/ath79_defconfig @@ -7,7 +7,6 @@ CONFIG_ATH79_MACH_PB44=y CONFIG_ATH79_MACH_UBNT_XM=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_HIGH_RES_TIMERS=y @@ -35,7 +34,6 @@ CONFIG_IP_ADVANCED_ROUTER=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_CFG80211=m CONFIG_MAC80211=m diff --git a/arch/mips/configs/bcm63xx_defconfig b/arch/mips/configs/bcm63xx_defconfig index 5599a9f1e3c6..131b350f014f 100644 --- a/arch/mips/configs/bcm63xx_defconfig +++ b/arch/mips/configs/bcm63xx_defconfig @@ -5,7 +5,6 @@ CONFIG_BCM63XX_CPU_6348=y CONFIG_BCM63XX_CPU_6358=y CONFIG_NO_HZ=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_TINY_RCU=y @@ -33,7 +32,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_CFG80211=y @@ -50,13 +48,10 @@ CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y # CONFIG_BLK_DEV is not set -# CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y CONFIG_BCM63XX_PHY=y CONFIG_NET_ETHERNET=y CONFIG_BCM63XX_ENET=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_B43=y # CONFIG_B43_PHY_LP is not set # CONFIG_INPUT is not set @@ -70,7 +65,6 @@ CONFIG_SERIAL_BCM63XX_CONSOLE=y # CONFIG_HWMON is not set # CONFIG_VGA_ARB is not set CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set CONFIG_USB_OHCI_HCD=y @@ -84,7 +78,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_PROC_KCORE=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_MAGIC_SYSRQ=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=ttyS0,115200" # CONFIG_CRYPTO_HW is not set diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index d20b09d77b53..a55009edbb29 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -4,7 +4,6 @@ CONFIG_SMP=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -60,7 +59,6 @@ CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m CONFIG_INET_XFRM_MODE_TRANSPORT=m CONFIG_INET_XFRM_MODE_TUNNEL=m -# CONFIG_INET_LRO is not set CONFIG_TCP_MD5SIG=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y @@ -182,7 +180,6 @@ CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m @@ -284,7 +281,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_T10DIF=m CONFIG_CRC7=m diff --git a/arch/mips/configs/bmips_be_defconfig b/arch/mips/configs/bmips_be_defconfig index acf7785c4cdb..a7072a14d396 100644 --- a/arch/mips/configs/bmips_be_defconfig +++ b/arch/mips/configs/bmips_be_defconfig @@ -23,7 +23,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_CFG80211=y CONFIG_NL80211_TESTMODE=y diff --git a/arch/mips/configs/capcella_defconfig b/arch/mips/configs/capcella_defconfig index 2924ba34a01b..bd80b5c852dd 100644 --- a/arch/mips/configs/capcella_defconfig +++ b/arch/mips/configs/capcella_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_ZAO_CAPCELLA=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -46,8 +45,6 @@ CONFIG_SMSC_PHY=m CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_8139TOO=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -59,7 +56,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VR41XX=y diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig index d4fda41f00ba..e5b18f1a31a0 100644 --- a/arch/mips/configs/cavium_octeon_defconfig +++ b/arch/mips/configs/cavium_octeon_defconfig @@ -42,7 +42,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_LRO is not set CONFIG_IPV6=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig index 43e0ba24470c..b42cfa7865f9 100644 --- a/arch/mips/configs/ci20_defconfig +++ b/arch/mips/configs/ci20_defconfig @@ -41,7 +41,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set diff --git a/arch/mips/configs/cobalt_defconfig b/arch/mips/configs/cobalt_defconfig index 23b66934e18d..a9066f300665 100644 --- a/arch/mips/configs/cobalt_defconfig +++ b/arch/mips/configs/cobalt_defconfig @@ -1,5 +1,4 @@ CONFIG_MIPS_COBALT=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y @@ -15,17 +14,14 @@ CONFIG_XFRM_USER=y CONFIG_NET_KEY=y CONFIG_NET_KEY_MIGRATE=y CONFIG_INET=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLKDEVS=y CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_LOOP=y -# CONFIG_MISC_DEVICES is not set CONFIG_RAID_ATTRS=y CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set @@ -36,8 +32,6 @@ CONFIG_NET_ETHERNET=y CONFIG_NET_TULIP=y CONFIG_DE2104X=y CONFIG_TULIP=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set @@ -56,7 +50,6 @@ CONFIG_FB_COBALT=y # CONFIG_VGA_CONSOLE is not set CONFIG_HID=m CONFIG_USB=m -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_EHCI_HCD=m # CONFIG_USB_EHCI_TT_NEWSCHED is not set CONFIG_USB_OHCI_HCD=m @@ -84,6 +77,5 @@ CONFIG_NFS_V3_ACL=y CONFIG_NFSD=y CONFIG_NFSD_V3=y CONFIG_NFSD_V3_ACL=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CRC16=y CONFIG_LIBCRC32C=y diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig index 2b6cb41d5715..e149f78901f8 100644 --- a/arch/mips/configs/decstation_defconfig +++ b/arch/mips/configs/decstation_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_DECSTATION=y CONFIG_CPU_R3000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set diff --git a/arch/mips/configs/e55_defconfig b/arch/mips/configs/e55_defconfig index e94d266c4b97..c3ac0209457c 100644 --- a/arch/mips/configs/e55_defconfig +++ b/arch/mips/configs/e55_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_CASIO_E55=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -28,7 +27,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VR41XX=y diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig index 87435897fd50..499f51498ecb 100644 --- a/arch/mips/configs/fuloong2e_defconfig +++ b/arch/mips/configs/fuloong2e_defconfig @@ -3,7 +3,6 @@ CONFIG_64BIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_LOCALVERSION="-fuloong2e" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y @@ -47,7 +46,6 @@ CONFIG_NET_IPGRE=m CONFIG_NET_IPGRE_BROADCAST=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y @@ -79,7 +77,6 @@ CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -88,7 +85,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -101,7 +97,6 @@ CONFIG_NET_9P=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_FW_LOADER=m CONFIG_MTD=m -CONFIG_MTD_CHAR=m CONFIG_MTD_BLOCK=m CONFIG_MTD_CFI=m CONFIG_MTD_JEDECPROBE=m @@ -163,7 +158,6 @@ CONFIG_I2C=m CONFIG_I2C_CHARDEV=m CONFIG_I2C_VIAPRO=m # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FB_RADEON=y # CONFIG_FB_RADEON_I2C is not set @@ -184,7 +178,6 @@ CONFIG_USB_KBD=y CONFIG_USB_MOUSE=y CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_OTG_WHITELIST=y CONFIG_USB_WUSB_CBAF=m CONFIG_USB_C67X00_HCD=m @@ -201,7 +194,6 @@ CONFIG_USB_TMC=m CONFIG_USB_STORAGE=y CONFIG_USB_STORAGE_ONETOUCH=y CONFIG_USB_STORAGE_CYPRESS_ATACB=y -CONFIG_USB_LIBUSUAL=y CONFIG_USB_SEVSEG=m CONFIG_USB_ISIGHTFW=m CONFIG_UIO=m @@ -215,7 +207,6 @@ CONFIG_EXT4_FS=m CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y CONFIG_REISERFS_FS=m -CONFIG_AUTOFS_FS=y CONFIG_AUTOFS4_FS=y CONFIG_FUSE_FS=y CONFIG_ISO9660_FS=m @@ -256,8 +247,6 @@ CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_DEBUG_FS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_CCM=m diff --git a/arch/mips/configs/generic/board-boston.config b/arch/mips/configs/generic/board-boston.config new file mode 100644 index 000000000000..19560a45b683 --- /dev/null +++ b/arch/mips/configs/generic/board-boston.config @@ -0,0 +1,48 @@ +CONFIG_FIT_IMAGE_FDT_BOSTON=y + +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y + +CONFIG_AUXDISPLAY=y +CONFIG_IMG_ASCII_LCD=y + +CONFIG_COMMON_CLK_BOSTON=y + +CONFIG_DMADEVICES=y +CONFIG_PCH_DMA=y + +CONFIG_GPIOLIB=y +CONFIG_GPIO_SYSFS=y +CONFIG_GPIO_PCH=y + +CONFIG_I2C=y +CONFIG_I2C_EG20T=y + +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PCI=y + +CONFIG_NETDEVICES=y +CONFIG_PCH_GBE=y + +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCIE_XILINX=y + +CONFIG_PCH_PHUB=y + +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_M41T80=y + +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y + +CONFIG_SPI=y +CONFIG_SPI_TOPCLIFF_PCH=y + +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig index e24feb0633aa..b1911816337c 100644 --- a/arch/mips/configs/gpr_defconfig +++ b/arch/mips/configs/gpr_defconfig @@ -2,7 +2,6 @@ CONFIG_MIPS_ALCHEMY=y CONFIG_MIPS_GPR=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -59,7 +58,6 @@ CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -68,7 +66,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -166,7 +163,6 @@ CONFIG_YAM=m CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -200,8 +196,6 @@ CONFIG_SMSC_PHY=m CONFIG_NET_ETHERNET=y CONFIG_MII=y CONFIG_MIPS_AU1X00_ENET=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_ATH_COMMON=y CONFIG_ATH_DEBUG=y CONFIG_ATH5K=y @@ -286,14 +280,12 @@ CONFIG_USB_HIDDEV=y CONFIG_USB_KBD=m CONFIG_USB_MOUSE=m CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_ROOT_HUB_TT=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=m -CONFIG_USB_LIBUSUAL=y CONFIG_USB_SERIAL=y CONFIG_USB_EZUSB=y CONFIG_USB_SERIAL_GENERIC=y diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig index ec8e9684296d..83e8fe2064aa 100644 --- a/arch/mips/configs/ip22_defconfig +++ b/arch/mips/configs/ip22_defconfig @@ -4,7 +4,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -46,7 +45,6 @@ CONFIG_INET_IPCOMP=m CONFIG_INET_XFRM_MODE_TRANSPORT=m CONFIG_INET_XFRM_MODE_TUNNEL=m CONFIG_INET_XFRM_MODE_BEET=m -# CONFIG_INET_LRO is not set CONFIG_TCP_MD5SIG=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y @@ -139,7 +137,6 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -148,7 +145,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -163,7 +159,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -174,7 +169,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -215,7 +209,6 @@ CONFIG_RFKILL=m CONFIG_CONNECTOR=m CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m -# CONFIG_MISC_DEVICES is not set CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y @@ -245,8 +238,6 @@ CONFIG_MDIO_BITBANG=m CONFIG_NET_ETHERNET=y CONFIG_SMC91X=m CONFIG_SGISEEQ=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_HOSTAP=m CONFIG_INPUT_MOUSEDEV=m CONFIG_MOUSE_PS2=m @@ -286,7 +277,6 @@ CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m @@ -355,7 +345,6 @@ CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_DEBUG_MEMORY_INIT=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set CONFIG_KEYS=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_NULL=m diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index e582069b44fd..a0d593248668 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -5,7 +5,6 @@ CONFIG_SMP=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_IKCONFIG=y @@ -104,7 +103,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_OSD=m CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y @@ -325,7 +323,6 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_QUOTA_NETLINK_INTERFACE=y -CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_FSCACHE=m @@ -342,7 +339,6 @@ CONFIG_NFS_V3=y CONFIG_RPCSEC_GSS_KRB5=y CONFIG_PARTITION_ADVANCED=y CONFIG_DLM=m -# CONFIG_RCU_CPU_STALL_DETECTOR is not set CONFIG_KEYS=y CONFIG_SECURITYFS=y CONFIG_CRYPTO_FIPS=y @@ -378,7 +374,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_DEV_HIFN_795X=m CONFIG_CRC_T10DIF=m diff --git a/arch/mips/configs/ip28_defconfig b/arch/mips/configs/ip28_defconfig index 4dbf6269b3f9..d0a4c2cfacf8 100644 --- a/arch/mips/configs/ip28_defconfig +++ b/arch/mips/configs/ip28_defconfig @@ -1,7 +1,6 @@ CONFIG_SGI_IP28=y CONFIG_ARC_CONSOLE=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -35,10 +34,8 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set CONFIG_TCP_MD5SIG=y # CONFIG_IPV6 is not set -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y @@ -48,8 +45,6 @@ CONFIG_NETDEVICES=y CONFIG_DUMMY=m CONFIG_NET_ETHERNET=y CONFIG_SGISEEQ=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_MOUSE_PS2_ALPS is not set # CONFIG_MOUSE_PS2_SYNAPTICS is not set CONFIG_VT_HW_CONSOLE_BINDING=y diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig index f9af98f63cff..1e26e58b9dc3 100644 --- a/arch/mips/configs/ip32_defconfig +++ b/arch/mips/configs/ip32_defconfig @@ -1,6 +1,5 @@ CONFIG_SGI_IP32=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -38,7 +37,6 @@ CONFIG_NET_IPGRE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_MD5SIG=y CONFIG_INET6_AH=m @@ -76,8 +74,6 @@ CONFIG_NET_TULIP=y CONFIG_DE2104X=m CONFIG_TULIP=m CONFIG_TULIP_MMIO=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_INPUT_EVDEV=m # CONFIG_SERIO_I8042 is not set CONFIG_SERIO_MACEPS2=y @@ -87,7 +83,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_WATCHDOG=y -CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_GBE=y @@ -117,7 +112,6 @@ CONFIG_EXT3_FS_SECURITY=y CONFIG_QUOTA=y CONFIG_QFMT_V1=m CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m @@ -178,8 +172,6 @@ CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=m CONFIG_MAGIC_SYSRQ=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KEYS=y CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_CBC=y diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig index 3019fce63cd3..9ad1c94376c8 100644 --- a/arch/mips/configs/jazz_defconfig +++ b/arch/mips/configs/jazz_defconfig @@ -1,7 +1,6 @@ CONFIG_MACH_JAZZ=y CONFIG_OLIVETTI_M700=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -85,7 +84,6 @@ CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -94,7 +92,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -109,7 +106,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -120,7 +116,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -276,7 +271,6 @@ CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_QUOTA=y -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m diff --git a/arch/mips/configs/jmr3927_defconfig b/arch/mips/configs/jmr3927_defconfig index 9bc08f275120..af12281a5c33 100644 --- a/arch/mips/configs/jmr3927_defconfig +++ b/arch/mips/configs/jmr3927_defconfig @@ -18,23 +18,18 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_CFI=y CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y -# CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_TC35815=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set @@ -58,5 +53,3 @@ CONFIG_PROC_KCORE=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/mips/configs/lasat_defconfig b/arch/mips/configs/lasat_defconfig index e620a2c3eba4..947a35c7c46c 100644 --- a/arch/mips/configs/lasat_defconfig +++ b/arch/mips/configs/lasat_defconfig @@ -5,7 +5,6 @@ CONFIG_DS1603=y CONFIG_LASAT_SYSCTL=y CONFIG_HZ_1000=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_EXPERT=y @@ -31,7 +30,6 @@ CONFIG_INET=y # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y @@ -44,8 +42,6 @@ CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_PCNET32=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -56,7 +52,6 @@ CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_SERIAL_8250_PCI is not set # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index 8df80c6383f2..1ec8ed8d05d1 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -7,7 +7,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT=y CONFIG_KEXEC=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y @@ -83,8 +82,6 @@ CONFIG_NET_SCHED=y CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y CONFIG_BT=m -CONFIG_BT_L2CAP=y -CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m @@ -142,7 +139,6 @@ CONFIG_8139TOO=y # CONFIG_8139TOO_PIO is not set CONFIG_R8169=y CONFIG_R8169_VLAN=y -# CONFIG_NETDEV_10000 is not set CONFIG_USB_USBNET=m CONFIG_USB_NET_CDC_EEM=m CONFIG_NETCONSOLE=m @@ -205,7 +201,6 @@ CONFIG_USB_ZR364XX=m CONFIG_USB_STKWEBCAM=m CONFIG_USB_S2255=m # CONFIG_RADIO_ADAPTERS is not set -CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MODE_HELPERS=y @@ -290,7 +285,6 @@ CONFIG_HID_WACOM=m CONFIG_HID_ZEROPLUS=m CONFIG_ZEROPLUS_FF=y CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_DYNAMIC_MINORS=y CONFIG_USB_OTG_WHITELIST=y CONFIG_USB_MON=y @@ -313,10 +307,8 @@ CONFIG_USB_STORAGE_SDDR09=m CONFIG_USB_STORAGE_SDDR55=m CONFIG_USB_STORAGE_JUMPSHOT=m CONFIG_USB_STORAGE_ALAUDA=m -CONFIG_USB_LIBUSUAL=y CONFIG_USB_SERIAL=m CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_LED=m CONFIG_USB_GADGET=m CONFIG_USB_GADGET_M66592=y CONFIG_MMC=m @@ -341,7 +333,6 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_QUOTA=y CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -407,8 +398,6 @@ CONFIG_PRINTK_TIME=y CONFIG_FRAME_WARN=1024 CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KEYS=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_NULL=m @@ -446,6 +435,5 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_T10DIF=y diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index 7f95c4b3ab2c..324dfee23dfb 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -95,7 +95,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -252,7 +251,6 @@ CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=m CONFIG_DRM=y CONFIG_DRM_RADEON=y -CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_FB_RADEON=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_PLATFORM=m @@ -335,7 +333,6 @@ CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set -# CONFIG_RCU_CPU_STALL_VERBOSE is not set # CONFIG_FTRACE is not set CONFIG_SECURITY=y CONFIG_SECURITYFS=y diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index e233f878afef..80ecd94ed126 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -133,7 +133,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index fbe085c328ab..35ad1f8d1a79 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -132,7 +132,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig index cbf37dd0c490..77145ecaa23b 100644 --- a/arch/mips/configs/malta_qemu_32r6_defconfig +++ b/arch/mips/configs/malta_qemu_32r6_defconfig @@ -42,7 +42,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig index 35f6ba260df8..cc2687cfdc13 100644 --- a/arch/mips/configs/maltaaprp_defconfig +++ b/arch/mips/configs/maltaaprp_defconfig @@ -43,7 +43,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -135,7 +134,6 @@ CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MATROX=y diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig index 900f14543eeb..55b68b981b05 100644 --- a/arch/mips/configs/maltasmvp_defconfig +++ b/arch/mips/configs/maltasmvp_defconfig @@ -46,7 +46,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig index 8e2738b5e180..5ca590cf1635 100644 --- a/arch/mips/configs/maltasmvp_eva_defconfig +++ b/arch/mips/configs/maltasmvp_eva_defconfig @@ -47,7 +47,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -140,7 +139,6 @@ CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MATROX=y diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig index 6dc4e309a691..7ea7c0ba2666 100644 --- a/arch/mips/configs/maltaup_defconfig +++ b/arch/mips/configs/maltaup_defconfig @@ -42,7 +42,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -134,7 +133,6 @@ CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MATROX=y diff --git a/arch/mips/configs/markeins_defconfig b/arch/mips/configs/markeins_defconfig index 0f08e4623ee4..43ce6576ab1c 100644 --- a/arch/mips/configs/markeins_defconfig +++ b/arch/mips/configs/markeins_defconfig @@ -1,7 +1,6 @@ CONFIG_NEC_MARKEINS=y CONFIG_HZ_1000=y CONFIG_PREEMPT=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -92,7 +91,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -117,7 +115,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -125,7 +122,6 @@ CONFIG_IP6_NF_RAW=m CONFIG_FW_LOADER=m CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y diff --git a/arch/mips/configs/mips_paravirt_defconfig b/arch/mips/configs/mips_paravirt_defconfig index 84cfcb4bf2ea..accf0db1dc6f 100644 --- a/arch/mips/configs/mips_paravirt_defconfig +++ b/arch/mips/configs/mips_paravirt_defconfig @@ -39,7 +39,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_LRO is not set CONFIG_IPV6=y # CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" diff --git a/arch/mips/configs/mpc30x_defconfig b/arch/mips/configs/mpc30x_defconfig index a2c045fab6c5..3486b034f726 100644 --- a/arch/mips/configs/mpc30x_defconfig +++ b/arch/mips/configs/mpc30x_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_VICTOR_MPC30X=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y @@ -31,8 +30,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_PATA_LEGACY=y CONFIG_NETDEVICES=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_USB_PEGASUS=m # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set @@ -45,13 +42,11 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set CONFIG_USB=m CONFIG_USB_OHCI_HCD=m CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VR41XX=y CONFIG_EXT2_FS=y -CONFIG_AUTOFS_FS=y CONFIG_AUTOFS4_FS=y CONFIG_PROC_KCORE=y CONFIG_CONFIGFS_FS=m diff --git a/arch/mips/configs/msp71xx_defconfig b/arch/mips/configs/msp71xx_defconfig index 201edfb2637d..3c8c16b10732 100644 --- a/arch/mips/configs/msp71xx_defconfig +++ b/arch/mips/configs/msp71xx_defconfig @@ -2,7 +2,6 @@ CONFIG_PMC_MSP=y CONFIG_PMC_MSP7120_GW=y CONFIG_CPU_MIPS32_R2=y CONFIG_PREEMPT=y -CONFIG_EXPERIMENTAL=y CONFIG_LOCALVERSION="-pmc" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y @@ -38,7 +37,6 @@ CONFIG_BRIDGE=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index f3f60056bc27..4011f1869e72 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -1,7 +1,6 @@ CONFIG_MIPS_ALCHEMY=y CONFIG_MIPS_MTX1=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -81,7 +80,6 @@ CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -90,7 +88,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -98,7 +95,6 @@ CONFIG_IP_NF_RAW=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -108,7 +104,6 @@ CONFIG_IP6_NF_MATCH_HL=m CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -225,8 +220,6 @@ CONFIG_TOSHIBA_FIR=m CONFIG_VLSI_FIR=m CONFIG_MCS_FIR=m CONFIG_BT=m -CONFIG_BT_L2CAP=y -CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m @@ -246,7 +239,6 @@ CONFIG_BT_HCIBTUART=m CONFIG_BT_HCIVHCI=m CONFIG_CONNECTOR=m CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -257,7 +249,6 @@ CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_CHR_DEV_SG=m @@ -596,7 +587,6 @@ CONFIG_USB_STORAGE_SDDR55=m CONFIG_USB_STORAGE_JUMPSHOT=m CONFIG_USB_STORAGE_ALAUDA=m CONFIG_USB_STORAGE_KARMA=m -CONFIG_USB_LIBUSUAL=y CONFIG_USB_MDC800=m CONFIG_USB_MICROTEK=m CONFIG_USB_SERIAL=m @@ -640,7 +630,6 @@ CONFIG_USB_ADUTUX=m CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m -CONFIG_USB_LED=m CONFIG_USB_CYPRESS_CY7C63=m CONFIG_USB_CYTHERM=m CONFIG_USB_IDMOUSE=m diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig index 07d01827a973..5720ce23e9aa 100644 --- a/arch/mips/configs/nlm_xlp_defconfig +++ b/arch/mips/configs/nlm_xlp_defconfig @@ -6,7 +6,6 @@ CONFIG_KSM=y CONFIG_DEFAULT_MMAP_MIN_ADDR=65536 CONFIG_SMP=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -183,14 +182,12 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -317,7 +314,6 @@ CONFIG_DEVTMPFS_MOUNT=y CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y @@ -607,7 +603,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_CCITT=m CONFIG_CRC7=m diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig index f59969acb724..fea56c535d92 100644 --- a/arch/mips/configs/nlm_xlr_defconfig +++ b/arch/mips/configs/nlm_xlr_defconfig @@ -7,7 +7,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_KEXEC=y -CONFIG_EXPERIMENTAL=y CONFIG_CROSS_COMPILE="" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y @@ -163,7 +162,6 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -171,7 +169,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -186,7 +183,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -197,7 +193,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -308,7 +303,6 @@ CONFIG_BLK_DEV_OSD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_CDROM_PKTCDVD=y -CONFIG_MISC_DEVICES=y CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y @@ -369,7 +363,6 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1374=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_UIO=y CONFIG_UIO_PDRV=m @@ -522,7 +515,6 @@ CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_KGDB=y @@ -568,7 +560,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_CCITT=m CONFIG_CRC7=m diff --git a/arch/mips/configs/pnx8335_stb225_defconfig b/arch/mips/configs/pnx8335_stb225_defconfig index c887066ecc2a..81b5eb89446c 100644 --- a/arch/mips/configs/pnx8335_stb225_defconfig +++ b/arch/mips/configs/pnx8335_stb225_defconfig @@ -5,7 +5,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_128=y CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_SYSVIPC=y @@ -27,12 +26,10 @@ CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_INET_AH=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y @@ -41,15 +38,12 @@ CONFIG_MTD_CFI_GEOMETRY=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_LOOP=y -# CONFIG_MISC_DEVICES is not set CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_ATA=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_MII=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set CONFIG_INPUT_EVDEV=m CONFIG_INPUT_EVBUG=m @@ -94,4 +88,3 @@ CONFIG_NLS_ASCII=m CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/mips/configs/qi_lb60_defconfig b/arch/mips/configs/qi_lb60_defconfig index d7bb8cce1068..3f1333517405 100644 --- a/arch/mips/configs/qi_lb60_defconfig +++ b/arch/mips/configs/qi_lb60_defconfig @@ -34,7 +34,6 @@ CONFIG_IP_MROUTE_MULTIPLE_TABLES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set @@ -109,7 +108,6 @@ CONFIG_USB_GADGET_DEBUG=y CONFIG_USB_ETH=y # CONFIG_USB_ETH_RNDIS is not set CONFIG_MMC=y -CONFIG_MMC_UNSAFE_RESUME=y # CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_JZ4740=y CONFIG_RTC_CLASS=y @@ -183,7 +181,6 @@ CONFIG_PANIC_ON_OOPS=y # CONFIG_FTRACE is not set CONFIG_KGDB=y CONFIG_RUNTIME_DEBUG=y -CONFIG_CRYPTO_ZLIB=y # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_FONTS=y CONFIG_FONT_SUN8x16=y diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig index 5d9d708e12e5..6fa56c6e53f5 100644 --- a/arch/mips/configs/rb532_defconfig +++ b/arch/mips/configs/rb532_defconfig @@ -3,7 +3,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y @@ -39,7 +38,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_CUBIC=m @@ -114,7 +112,6 @@ CONFIG_NET_CLS_IND=y CONFIG_HAMRADIO=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_BLOCK2MTD=y CONFIG_MTD_NAND=y @@ -129,8 +126,6 @@ CONFIG_NET_ETHERNET=y CONFIG_KORINA=y CONFIG_NET_PCI=y CONFIG_VIA_RHINE=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_ATMEL=m CONFIG_PPP=m CONFIG_PPP_MULTILINK=y @@ -183,7 +178,6 @@ CONFIG_BSD_DISKLABEL=y CONFIG_STRIP_ASM_SYMS=y CONFIG_CRYPTO=y CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ZLIB=y # CONFIG_CRYPTO_HW is not set CONFIG_CRC16=m CONFIG_LIBCRC32C=m diff --git a/arch/mips/configs/rbtx49xx_defconfig b/arch/mips/configs/rbtx49xx_defconfig index 43d55e5abacb..fb195e29e449 100644 --- a/arch/mips/configs/rbtx49xx_defconfig +++ b/arch/mips/configs/rbtx49xx_defconfig @@ -31,12 +31,10 @@ CONFIG_IP_PNP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=m CONFIG_MTD_BLOCK_RO=m CONFIG_MTD_CFI=y @@ -50,7 +48,6 @@ CONFIG_MTD_NAND_TXX9NDFMC=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 -# CONFIG_MISC_DEVICES is not set CONFIG_IDE=y CONFIG_BLK_DEV_IDE_TX4938=y CONFIG_BLK_DEV_IDE_TX4939=y @@ -60,8 +57,6 @@ CONFIG_SMC91X=y CONFIG_NE2000=y CONFIG_NET_PCI=y CONFIG_TC35815=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_WLAN is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set @@ -108,5 +103,3 @@ CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index c2b4e3f33a73..99679e514042 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -3,7 +3,6 @@ CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_ARC_CONSOLE=y CONFIG_HZ_1000=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -94,7 +93,6 @@ CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -103,7 +101,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -118,7 +115,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -129,7 +125,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -214,7 +209,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_SX8=m -CONFIG_BLK_DEV_UB=m CONFIG_BLK_DEV_RAM=m CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m @@ -353,7 +347,6 @@ CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m -CONFIG_USB_LED=m CONFIG_USB_CYTHERM=m CONFIG_USB_SISUSBVGA=m CONFIG_USB_LD=m @@ -366,7 +359,6 @@ CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_QUOTA=y -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig index d14ae2fa7d13..c695b7b1c4ae 100644 --- a/arch/mips/configs/rt305x_defconfig +++ b/arch/mips/configs/rt305x_defconfig @@ -5,7 +5,6 @@ CONFIG_CPU_MIPS32_R2=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HZ_100=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_HIGH_RES_TIMERS=y @@ -44,7 +43,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig index 7fca09fedb59..c724bdd6a7e6 100644 --- a/arch/mips/configs/sb1250_swarm_defconfig +++ b/arch/mips/configs/sb1250_swarm_defconfig @@ -4,7 +4,6 @@ CONFIG_64BIT=y CONFIG_SMP=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=15 CONFIG_CGROUPS=y diff --git a/arch/mips/configs/tb0219_defconfig b/arch/mips/configs/tb0219_defconfig index 11f51505d562..4041597e3170 100644 --- a/arch/mips/configs/tb0219_defconfig +++ b/arch/mips/configs/tb0219_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_TANBAC_TB0219=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y @@ -31,7 +30,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_NETWORK_SECMARK=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" @@ -40,7 +38,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_XIP=y -# CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y CONFIG_PHYLIB=m CONFIG_MARVELL_PHY=m @@ -57,7 +54,6 @@ CONFIG_VIA_RHINE=y CONFIG_VIA_RHINE_MMIO=y CONFIG_R8169=y CONFIG_VIA_VELOCITY=y -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -70,7 +66,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_TB0219=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set CONFIG_USB=m CONFIG_USB_MON=m CONFIG_USB_EHCI_HCD=m @@ -91,6 +86,5 @@ CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y CONFIG_NFSD_V3=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="cca=3 mem=64M console=ttyVR0,115200 ip=any root=/dev/nfs" diff --git a/arch/mips/configs/tb0226_defconfig b/arch/mips/configs/tb0226_defconfig index 9327b3af32cd..565f0441c50d 100644 --- a/arch/mips/configs/tb0226_defconfig +++ b/arch/mips/configs/tb0226_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_TANBAC_TB0226=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y @@ -29,7 +28,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_NETWORK_SECMARK=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" @@ -37,7 +35,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_XIP=y -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_SCSI_MULTI_LUN=y @@ -49,8 +46,6 @@ CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_E100=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_USB_CATC=m CONFIG_USB_KAWETH=m CONFIG_USB_PEGASUS=m @@ -66,7 +61,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set CONFIG_USB=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set @@ -87,7 +81,6 @@ CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y CONFIG_NFSD=m CONFIG_NFSD_V3=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="cca=3 mem=32M console=ttyVR0,115200" CONFIG_CRC32=m diff --git a/arch/mips/configs/tb0287_defconfig b/arch/mips/configs/tb0287_defconfig index a967289b7970..a702be602fb9 100644 --- a/arch/mips/configs/tb0287_defconfig +++ b/arch/mips/configs/tb0287_defconfig @@ -1,5 +1,4 @@ CONFIG_MACH_VR41XX=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y @@ -31,7 +30,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_BIC=y CONFIG_TCP_CONG_CUBIC=m @@ -43,7 +41,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_XIP=y -# CONFIG_MISC_DEVICES is not set CONFIG_BLK_DEV_SD=y CONFIG_SCSI_SCAN_ASYNC=y # CONFIG_SCSI_LOWLEVEL is not set @@ -64,7 +61,6 @@ CONFIG_VIA_RHINE=y CONFIG_VIA_RHINE_MMIO=y CONFIG_R8169=y CONFIG_VIA_VELOCITY=y -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -76,7 +72,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set CONFIG_MFD_SM501=y -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FB_SM501=y # CONFIG_VGA_CONSOLE is not set diff --git a/arch/mips/configs/workpad_defconfig b/arch/mips/configs/workpad_defconfig index ee4b2be43c44..a84eac409c9c 100644 --- a/arch/mips/configs/workpad_defconfig +++ b/arch/mips/configs/workpad_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_IBM_WORKPAD=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -28,13 +27,10 @@ CONFIG_IP_MULTICAST=y # CONFIG_IPV6 is not set CONFIG_NETWORK_SECMARK=y CONFIG_BLK_DEV_RAM=m -# CONFIG_MISC_DEVICES is not set CONFIG_IDE=y CONFIG_BLK_DEV_IDECS=m CONFIG_IDE_GENERIC=y CONFIG_NETDEVICES=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_NET_PCMCIA=y CONFIG_PCMCIA_3C589=m CONFIG_PCMCIA_3C574=m diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index a606b3f9196c..51ffbbaddee2 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -9,11 +9,31 @@ config LEGACY_BOARDS kernel is booted without being provided with an FDT via the UHI boot protocol. +config YAMON_DT_SHIM + bool + help + Select this from your board if the board uses the YAMON bootloader + and you wish to include code which helps translate various + YAMON-provided environment variables into a device tree properties. + +comment "Legacy (non-UHI/non-FIT) Boards" + config LEGACY_BOARD_SEAD3 bool "Support MIPS SEAD-3 boards" select LEGACY_BOARDS + select YAMON_DT_SHIM help Enable this to include support for booting on MIPS SEAD-3 FPGA-based development boards, which boot using a legacy boot protocol. +comment "FIT/UHI Boards" + +config FIT_IMAGE_FDT_BOSTON + bool "Include FDT for MIPS Boston boards" + help + Enable this to include the FDT for the MIPS Boston development board + from Imagination Technologies in the FIT kernel image. You should + enable this if you wish to boot on a MIPS Boston board, as it is + expected by the bootloader. + endif diff --git a/arch/mips/generic/Makefile b/arch/mips/generic/Makefile index acb9b6d62b16..56b3ea565ed9 100644 --- a/arch/mips/generic/Makefile +++ b/arch/mips/generic/Makefile @@ -12,5 +12,6 @@ obj-y += init.o obj-y += irq.o obj-y += proc.o +obj-$(CONFIG_YAMON_DT_SHIM) += yamon-dt.o obj-$(CONFIG_LEGACY_BOARD_SEAD3) += board-sead3.o obj-$(CONFIG_KEXEC) += kexec.o diff --git a/arch/mips/generic/board-sead3.c b/arch/mips/generic/board-sead3.c index f4ae0584a33b..f109a6b9fdd0 100644 --- a/arch/mips/generic/board-sead3.c +++ b/arch/mips/generic/board-sead3.c @@ -13,10 +13,12 @@ #include <linux/errno.h> #include <linux/libfdt.h> #include <linux/printk.h> +#include <linux/sizes.h> #include <asm/fw/fw.h> #include <asm/io.h> #include <asm/machine.h> +#include <asm/yamon-dt.h> #define SEAD_CONFIG CKSEG1ADDR(0x1b100110) #define SEAD_CONFIG_GIC_PRESENT BIT(1) @@ -25,6 +27,15 @@ #define MIPS_REVISION_MACHINE (0xf << 4) #define MIPS_REVISION_MACHINE_SEAD3 (0x4 << 4) +/* + * Maximum 384MB RAM at physical address 0, preceding any I/O. + */ +static struct yamon_mem_region mem_regions[] __initdata = { + /* start size */ + { 0, SZ_256M + SZ_128M }, + {} +}; + static __init bool sead3_detect(void) { uint32_t rev; @@ -33,96 +44,9 @@ static __init bool sead3_detect(void) return (rev & MIPS_REVISION_MACHINE) == MIPS_REVISION_MACHINE_SEAD3; } -static __init int append_cmdline(void *fdt) -{ - int err, chosen_off; - - /* find or add chosen node */ - chosen_off = fdt_path_offset(fdt, "/chosen"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_path_offset(fdt, "/chosen@0"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_add_subnode(fdt, 0, "chosen"); - if (chosen_off < 0) { - pr_err("Unable to find or add DT chosen node: %d\n", - chosen_off); - return chosen_off; - } - - err = fdt_setprop_string(fdt, chosen_off, "bootargs", fw_getcmdline()); - if (err) { - pr_err("Unable to set bootargs property: %d\n", err); - return err; - } - - return 0; -} - static __init int append_memory(void *fdt) { - unsigned long phys_memsize, memsize; - __be32 mem_array[2]; - int err, mem_off; - char *var; - - /* find memory size from the bootloader environment */ - var = fw_getenv("memsize"); - if (var) { - err = kstrtoul(var, 0, &phys_memsize); - if (err) { - pr_err("Failed to read memsize env variable '%s'\n", - var); - return -EINVAL; - } - } else { - pr_warn("The bootloader didn't provide memsize: defaulting to 32MB\n"); - phys_memsize = 32 << 20; - } - - /* default to using all available RAM */ - memsize = phys_memsize; - - /* allow the user to override the usable memory */ - var = strstr(arcs_cmdline, "memsize="); - if (var) - memsize = memparse(var + strlen("memsize="), NULL); - - /* if the user says there's more RAM than we thought, believe them */ - phys_memsize = max_t(unsigned long, phys_memsize, memsize); - - /* find or add a memory node */ - mem_off = fdt_path_offset(fdt, "/memory"); - if (mem_off == -FDT_ERR_NOTFOUND) - mem_off = fdt_add_subnode(fdt, 0, "memory"); - if (mem_off < 0) { - pr_err("Unable to find or add memory DT node: %d\n", mem_off); - return mem_off; - } - - err = fdt_setprop_string(fdt, mem_off, "device_type", "memory"); - if (err) { - pr_err("Unable to set memory node device_type: %d\n", err); - return err; - } - - mem_array[0] = 0; - mem_array[1] = cpu_to_be32(phys_memsize); - err = fdt_setprop(fdt, mem_off, "reg", mem_array, sizeof(mem_array)); - if (err) { - pr_err("Unable to set memory regs property: %d\n", err); - return err; - } - - mem_array[0] = 0; - mem_array[1] = cpu_to_be32(memsize); - err = fdt_setprop(fdt, mem_off, "linux,usable-memory", - mem_array, sizeof(mem_array)); - if (err) { - pr_err("Unable to set linux,usable-memory property: %d\n", err); - return err; - } - - return 0; + return yamon_dt_append_memory(fdt, mem_regions); } static __init int remove_gic(void *fdt) @@ -163,14 +87,16 @@ static __init int remove_gic(void *fdt) return -EINVAL; } - err = fdt_setprop_u32(fdt, 0, "interrupt-parent", cpu_phandle); - if (err) { - pr_err("unable to set root interrupt-parent: %d\n", err); - return err; - } - uart_off = fdt_node_offset_by_compatible(fdt, -1, "ns16550a"); while (uart_off >= 0) { + err = fdt_setprop_u32(fdt, uart_off, "interrupt-parent", + cpu_phandle); + if (err) { + pr_warn("unable to set UART interrupt-parent: %d\n", + err); + return err; + } + err = fdt_setprop_u32(fdt, uart_off, "interrupts", cpu_uart_int); if (err) { @@ -193,6 +119,12 @@ static __init int remove_gic(void *fdt) return eth_off; } + err = fdt_setprop_u32(fdt, eth_off, "interrupt-parent", cpu_phandle); + if (err) { + pr_err("unable to set ethernet interrupt-parent: %d\n", err); + return err; + } + err = fdt_setprop_u32(fdt, eth_off, "interrupts", cpu_eth_int); if (err) { pr_err("unable to set ethernet interrupts property: %d\n", err); @@ -205,94 +137,29 @@ static __init int remove_gic(void *fdt) return ehci_off; } - err = fdt_setprop_u32(fdt, ehci_off, "interrupts", cpu_ehci_int); + err = fdt_setprop_u32(fdt, ehci_off, "interrupt-parent", cpu_phandle); if (err) { - pr_err("unable to set EHCI interrupts property: %d\n", err); + pr_err("unable to set EHCI interrupt-parent: %d\n", err); return err; } - return 0; -} - -static __init int serial_config(void *fdt) -{ - const char *yamontty, *mode_var; - char mode_var_name[9], path[18], parity; - unsigned int uart, baud, stop_bits; - bool hw_flow; - int chosen_off, err; - - yamontty = fw_getenv("yamontty"); - if (!yamontty || !strcmp(yamontty, "tty0")) { - uart = 0; - } else if (!strcmp(yamontty, "tty1")) { - uart = 1; - } else { - pr_warn("yamontty environment variable '%s' invalid\n", - yamontty); - uart = 0; - } - - baud = stop_bits = 0; - parity = 0; - hw_flow = false; - - snprintf(mode_var_name, sizeof(mode_var_name), "modetty%u", uart); - mode_var = fw_getenv(mode_var_name); - if (mode_var) { - while (mode_var[0] >= '0' && mode_var[0] <= '9') { - baud *= 10; - baud += mode_var[0] - '0'; - mode_var++; - } - if (mode_var[0] == ',') - mode_var++; - if (mode_var[0]) - parity = mode_var[0]; - if (mode_var[0] == ',') - mode_var++; - if (mode_var[0]) - stop_bits = mode_var[0] - '0'; - if (mode_var[0] == ',') - mode_var++; - if (!strcmp(mode_var, "hw")) - hw_flow = true; - } - - if (!baud) - baud = 38400; - - if (parity != 'e' && parity != 'n' && parity != 'o') - parity = 'n'; - - if (stop_bits != 7 && stop_bits != 8) - stop_bits = 8; - - WARN_ON(snprintf(path, sizeof(path), "uart%u:%u%c%u%s", - uart, baud, parity, stop_bits, - hw_flow ? "r" : "") >= sizeof(path)); - - /* find or add chosen node */ - chosen_off = fdt_path_offset(fdt, "/chosen"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_path_offset(fdt, "/chosen@0"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_add_subnode(fdt, 0, "chosen"); - if (chosen_off < 0) { - pr_err("Unable to find or add DT chosen node: %d\n", - chosen_off); - return chosen_off; - } - - err = fdt_setprop_string(fdt, chosen_off, "stdout-path", path); + err = fdt_setprop_u32(fdt, ehci_off, "interrupts", cpu_ehci_int); if (err) { - pr_err("Unable to set stdout-path property: %d\n", err); + pr_err("unable to set EHCI interrupts property: %d\n", err); return err; } return 0; } +static const struct mips_fdt_fixup sead3_fdt_fixups[] __initconst = { + { yamon_dt_append_cmdline, "append command line" }, + { append_memory, "append memory" }, + { remove_gic, "remove GIC when not present" }, + { yamon_dt_serial_config, "append serial configuration" }, + { }, +}; + static __init const void *sead3_fixup_fdt(const void *fdt, const void *match_data) { @@ -307,29 +174,10 @@ static __init const void *sead3_fixup_fdt(const void *fdt, fw_init_cmdline(); - err = fdt_open_into(fdt, fdt_buf, sizeof(fdt_buf)); - if (err) - panic("Unable to open FDT: %d", err); - - err = append_cmdline(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = append_memory(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = remove_gic(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = serial_config(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = fdt_pack(fdt_buf); + err = apply_mips_fdt_fixups(fdt_buf, sizeof(fdt_buf), + fdt, sead3_fdt_fixups); if (err) - panic("Unable to pack FDT: %d\n", err); + panic("Unable to fixup FDT: %d", err); return fdt_buf; } diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 1231b5a17b37..3f32b376d30e 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -122,6 +122,33 @@ void __init device_tree_init(void) err = register_up_smp_ops(); } +int __init apply_mips_fdt_fixups(void *fdt_out, size_t fdt_out_size, + const void *fdt_in, + const struct mips_fdt_fixup *fixups) +{ + int err; + + err = fdt_open_into(fdt_in, fdt_out, fdt_out_size); + if (err) { + pr_err("Failed to open FDT\n"); + return err; + } + + for (; fixups->apply; fixups++) { + err = fixups->apply(fdt_out); + if (err) { + pr_err("Failed to apply FDT fixup \"%s\"\n", + fixups->description); + return err; + } + } + + err = fdt_pack(fdt_out); + if (err) + pr_err("Failed to pack FDT\n"); + return err; +} + void __init plat_time_init(void) { struct device_node *np; diff --git a/arch/mips/generic/vmlinux.its.S b/arch/mips/generic/vmlinux.its.S index f67fbf1c8541..3390e2f80b80 100644 --- a/arch/mips/generic/vmlinux.its.S +++ b/arch/mips/generic/vmlinux.its.S @@ -29,3 +29,28 @@ }; }; }; + +#ifdef CONFIG_FIT_IMAGE_FDT_BOSTON +/ { + images { + fdt@boston { + description = "img,boston Device Tree"; + data = /incbin/("boot/dts/img/boston.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; + hash@0 { + algo = "sha1"; + }; + }; + }; + + configurations { + conf@boston { + description = "Boston Linux kernel"; + kernel = "kernel@0"; + fdt = "fdt@boston"; + }; + }; +}; +#endif /* CONFIG_FIT_IMAGE_FDT_BOSTON */ diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c new file mode 100644 index 000000000000..6077bca9b364 --- /dev/null +++ b/arch/mips/generic/yamon-dt.c @@ -0,0 +1,240 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * 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. + */ + +#define pr_fmt(fmt) "yamon-dt: " fmt + +#include <linux/bug.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/libfdt.h> +#include <linux/printk.h> + +#include <asm/fw/fw.h> +#include <asm/yamon-dt.h> + +#define MAX_MEM_ARRAY_ENTRIES 2 + +__init int yamon_dt_append_cmdline(void *fdt) +{ + int err, chosen_off; + + /* find or add chosen node */ + chosen_off = fdt_path_offset(fdt, "/chosen"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_path_offset(fdt, "/chosen@0"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_add_subnode(fdt, 0, "chosen"); + if (chosen_off < 0) { + pr_err("Unable to find or add DT chosen node: %d\n", + chosen_off); + return chosen_off; + } + + err = fdt_setprop_string(fdt, chosen_off, "bootargs", fw_getcmdline()); + if (err) { + pr_err("Unable to set bootargs property: %d\n", err); + return err; + } + + return 0; +} + +static unsigned int __init gen_fdt_mem_array( + const struct yamon_mem_region *regions, + __be32 *mem_array, + unsigned int max_entries, + unsigned long memsize) +{ + const struct yamon_mem_region *mr; + unsigned long size; + unsigned int entries = 0; + + for (mr = regions; mr->size && memsize; ++mr) { + if (entries >= max_entries) { + pr_warn("Number of regions exceeds max %u\n", + max_entries); + break; + } + + /* How much of the remaining RAM fits in the next region? */ + size = min_t(unsigned long, memsize, mr->size); + memsize -= size; + + /* Emit a memory region */ + *(mem_array++) = cpu_to_be32(mr->start); + *(mem_array++) = cpu_to_be32(size); + ++entries; + + /* Discard the next mr->discard bytes */ + memsize -= min_t(unsigned long, memsize, mr->discard); + } + return entries; +} + +__init int yamon_dt_append_memory(void *fdt, + const struct yamon_mem_region *regions) +{ + unsigned long phys_memsize, memsize; + __be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES]; + unsigned int mem_entries; + int i, err, mem_off; + char *var, param_name[10], *var_names[] = { + "ememsize", "memsize", + }; + + /* find memory size from the bootloader environment */ + for (i = 0; i < ARRAY_SIZE(var_names); i++) { + var = fw_getenv(var_names[i]); + if (!var) + continue; + + err = kstrtoul(var, 0, &phys_memsize); + if (!err) + break; + + pr_warn("Failed to read the '%s' env variable '%s'\n", + var_names[i], var); + } + + if (!phys_memsize) { + pr_warn("The bootloader didn't provide memsize: defaulting to 32MB\n"); + phys_memsize = 32 << 20; + } + + /* default to using all available RAM */ + memsize = phys_memsize; + + /* allow the user to override the usable memory */ + for (i = 0; i < ARRAY_SIZE(var_names); i++) { + snprintf(param_name, sizeof(param_name), "%s=", var_names[i]); + var = strstr(arcs_cmdline, param_name); + if (!var) + continue; + + memsize = memparse(var + strlen(param_name), NULL); + } + + /* if the user says there's more RAM than we thought, believe them */ + phys_memsize = max_t(unsigned long, phys_memsize, memsize); + + /* find or add a memory node */ + mem_off = fdt_path_offset(fdt, "/memory"); + if (mem_off == -FDT_ERR_NOTFOUND) + mem_off = fdt_add_subnode(fdt, 0, "memory"); + if (mem_off < 0) { + pr_err("Unable to find or add memory DT node: %d\n", mem_off); + return mem_off; + } + + err = fdt_setprop_string(fdt, mem_off, "device_type", "memory"); + if (err) { + pr_err("Unable to set memory node device_type: %d\n", err); + return err; + } + + mem_entries = gen_fdt_mem_array(regions, mem_array, + MAX_MEM_ARRAY_ENTRIES, phys_memsize); + err = fdt_setprop(fdt, mem_off, "reg", + mem_array, mem_entries * 2 * sizeof(mem_array[0])); + if (err) { + pr_err("Unable to set memory regs property: %d\n", err); + return err; + } + + mem_entries = gen_fdt_mem_array(regions, mem_array, + MAX_MEM_ARRAY_ENTRIES, memsize); + err = fdt_setprop(fdt, mem_off, "linux,usable-memory", + mem_array, mem_entries * 2 * sizeof(mem_array[0])); + if (err) { + pr_err("Unable to set linux,usable-memory property: %d\n", err); + return err; + } + + return 0; +} + +__init int yamon_dt_serial_config(void *fdt) +{ + const char *yamontty, *mode_var; + char mode_var_name[9], path[20], parity; + unsigned int uart, baud, stop_bits; + bool hw_flow; + int chosen_off, err; + + yamontty = fw_getenv("yamontty"); + if (!yamontty || !strcmp(yamontty, "tty0")) { + uart = 0; + } else if (!strcmp(yamontty, "tty1")) { + uart = 1; + } else { + pr_warn("yamontty environment variable '%s' invalid\n", + yamontty); + uart = 0; + } + + baud = stop_bits = 0; + parity = 0; + hw_flow = false; + + snprintf(mode_var_name, sizeof(mode_var_name), "modetty%u", uart); + mode_var = fw_getenv(mode_var_name); + if (mode_var) { + while (mode_var[0] >= '0' && mode_var[0] <= '9') { + baud *= 10; + baud += mode_var[0] - '0'; + mode_var++; + } + if (mode_var[0] == ',') + mode_var++; + if (mode_var[0]) + parity = mode_var[0]; + if (mode_var[0] == ',') + mode_var++; + if (mode_var[0]) + stop_bits = mode_var[0] - '0'; + if (mode_var[0] == ',') + mode_var++; + if (!strcmp(mode_var, "hw")) + hw_flow = true; + } + + if (!baud) + baud = 38400; + + if (parity != 'e' && parity != 'n' && parity != 'o') + parity = 'n'; + + if (stop_bits != 7 && stop_bits != 8) + stop_bits = 8; + + WARN_ON(snprintf(path, sizeof(path), "serial%u:%u%c%u%s", + uart, baud, parity, stop_bits, + hw_flow ? "r" : "") >= sizeof(path)); + + /* find or add chosen node */ + chosen_off = fdt_path_offset(fdt, "/chosen"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_path_offset(fdt, "/chosen@0"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_add_subnode(fdt, 0, "chosen"); + if (chosen_off < 0) { + pr_err("Unable to find or add DT chosen node: %d\n", + chosen_off); + return chosen_off; + } + + err = fdt_setprop_string(fdt, chosen_off, "stdout-path", path); + if (err) { + pr_err("Unable to set stdout-path property: %d\n", err); + return err; + } + + return 0; +} diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 2535c7b4c482..7c8aab23bce8 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -12,6 +12,8 @@ generic-y += mm-arch-hooks.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h +generic-y += qrwlock.h +generic-y += qspinlock.h generic-y += sections.h generic-y += segment.h generic-y += serial.h diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h index de781cf54bc7..da80878f2c0d 100644 --- a/arch/mips/include/asm/branch.h +++ b/arch/mips/include/asm/branch.h @@ -74,10 +74,7 @@ static inline int compute_return_epc(struct pt_regs *regs) return __microMIPS_compute_return_epc(regs); if (cpu_has_mips16) return __MIPS16e_compute_return_epc(regs); - return regs->cp0_epc; - } - - if (!delay_slot(regs)) { + } else if (!delay_slot(regs)) { regs->cp0_epc += 4; return 0; } diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index b71ab4a5fd50..903f3bf48419 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -13,153 +13,107 @@ #include <asm/compiler.h> #include <asm/war.h> -static inline unsigned long __xchg_u32(volatile int * m, unsigned int val) -{ - __u32 retval; - - smp_mb__before_llsc(); - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long dummy; - - __asm__ __volatile__( - " .set arch=r4000 \n" - "1: ll %0, %3 # xchg_u32 \n" - " .set mips0 \n" - " move %2, %z4 \n" - " .set arch=r4000 \n" - " sc %2, %1 \n" - " beqzl %2, 1b \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } else if (kernel_uses_llsc) { - unsigned long dummy; - - do { - __asm__ __volatile__( - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " ll %0, %3 # xchg_u32 \n" - " .set mips0 \n" - " move %2, %z4 \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " sc %2, %1 \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), - "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } while (unlikely(!dummy)); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - retval = *m; - *m = val; - raw_local_irq_restore(flags); /* implies memory barrier */ - } - - smp_llsc_mb(); - - return retval; -} +/* + * Using a branch-likely instruction to check the result of an sc instruction + * works around a bug present in R10000 CPUs prior to revision 3.0 that could + * cause ll-sc sequences to execute non-atomically. + */ +#if R10000_LLSC_WAR +# define __scbeqz "beqzl" +#else +# define __scbeqz "beqz" +#endif -#ifdef CONFIG_64BIT -static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val) -{ - __u64 retval; - - smp_mb__before_llsc(); - - if (kernel_uses_llsc && R10000_LLSC_WAR) { - unsigned long dummy; - - __asm__ __volatile__( - " .set arch=r4000 \n" - "1: lld %0, %3 # xchg_u64 \n" - " move %2, %z4 \n" - " scd %2, %1 \n" - " beqzl %2, 1b \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } else if (kernel_uses_llsc) { - unsigned long dummy; - - do { - __asm__ __volatile__( - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " lld %0, %3 # xchg_u64 \n" - " move %2, %z4 \n" - " scd %2, %1 \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), - "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } while (unlikely(!dummy)); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - retval = *m; - *m = val; - raw_local_irq_restore(flags); /* implies memory barrier */ - } +/* + * These functions doesn't exist, so if they are called you'll either: + * + * - Get an error at compile-time due to __compiletime_error, if supported by + * your compiler. + * + * or: + * + * - Get an error at link-time due to the call to the missing function. + */ +extern unsigned long __cmpxchg_called_with_bad_pointer(void) + __compiletime_error("Bad argument size for cmpxchg"); +extern unsigned long __xchg_called_with_bad_pointer(void) + __compiletime_error("Bad argument size for xchg"); - smp_llsc_mb(); +#define __xchg_asm(ld, st, m, val) \ +({ \ + __typeof(*(m)) __ret; \ + \ + if (kernel_uses_llsc) { \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set noat \n" \ + " .set " MIPS_ISA_ARCH_LEVEL " \n" \ + "1: " ld " %0, %2 # __xchg_asm \n" \ + " .set mips0 \n" \ + " move $1, %z3 \n" \ + " .set " MIPS_ISA_ARCH_LEVEL " \n" \ + " " st " $1, %1 \n" \ + "\t" __scbeqz " $1, 1b \n" \ + " .set pop \n" \ + : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ + : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) \ + : "memory"); \ + } else { \ + unsigned long __flags; \ + \ + raw_local_irq_save(__flags); \ + __ret = *m; \ + *m = val; \ + raw_local_irq_restore(__flags); \ + } \ + \ + __ret; \ +}) - return retval; -} -#else -extern __u64 __xchg_u64_unsupported_on_32bit_kernels(volatile __u64 * m, __u64 val); -#define __xchg_u64 __xchg_u64_unsupported_on_32bit_kernels -#endif +extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, + unsigned int size); -static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +static inline unsigned long __xchg(volatile void *ptr, unsigned long x, + int size) { switch (size) { + case 1: + case 2: + return __xchg_small(ptr, x, size); + case 4: - return __xchg_u32(ptr, x); + return __xchg_asm("ll", "sc", (volatile u32 *)ptr, x); + case 8: - return __xchg_u64(ptr, x); - } + if (!IS_ENABLED(CONFIG_64BIT)) + return __xchg_called_with_bad_pointer(); + + return __xchg_asm("lld", "scd", (volatile u64 *)ptr, x); - return x; + default: + return __xchg_called_with_bad_pointer(); + } } #define xchg(ptr, x) \ ({ \ - BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc); \ + __typeof__(*(ptr)) __res; \ \ - ((__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \ + smp_mb__before_llsc(); \ + \ + __res = (__typeof__(*(ptr))) \ + __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ + \ + smp_llsc_mb(); \ + \ + __res; \ }) #define __cmpxchg_asm(ld, st, m, old, new) \ ({ \ __typeof(*(m)) __ret; \ \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noat \n" \ - " .set arch=r4000 \n" \ - "1: " ld " %0, %2 # __cmpxchg_asm \n" \ - " bne %0, %z3, 2f \n" \ - " .set mips0 \n" \ - " move $1, %z4 \n" \ - " .set arch=r4000 \n" \ - " " st " $1, %1 \n" \ - " beqzl $1, 1b \n" \ - "2: \n" \ - " .set pop \n" \ - : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ - : GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new) \ - : "memory"); \ - } else if (kernel_uses_llsc) { \ + if (kernel_uses_llsc) { \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ @@ -170,7 +124,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz " move $1, %z4 \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ " " st " $1, %1 \n" \ - " beqz $1, 1b \n" \ + "\t" __scbeqz " $1, 1b \n" \ " .set pop \n" \ "2: \n" \ : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ @@ -189,44 +143,50 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz __ret; \ }) -/* - * This function doesn't exist, so you'll get a linker error - * if something tries to do an invalid cmpxchg(). - */ -extern void __cmpxchg_called_with_bad_pointer(void); +extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size); + +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) +{ + switch (size) { + case 1: + case 2: + return __cmpxchg_small(ptr, old, new, size); + + case 4: + return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); + + case 8: + /* lld/scd are only available for MIPS64 */ + if (!IS_ENABLED(CONFIG_64BIT)) + return __cmpxchg_called_with_bad_pointer(); + + return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new); -#define __cmpxchg(ptr, old, new, pre_barrier, post_barrier) \ + default: + return __cmpxchg_called_with_bad_pointer(); + } +} + +#define cmpxchg_local(ptr, old, new) \ + ((__typeof__(*(ptr))) \ + __cmpxchg((ptr), \ + (unsigned long)(__typeof__(*(ptr)))(old), \ + (unsigned long)(__typeof__(*(ptr)))(new), \ + sizeof(*(ptr)))) + +#define cmpxchg(ptr, old, new) \ ({ \ - __typeof__(ptr) __ptr = (ptr); \ - __typeof__(*(ptr)) __old = (old); \ - __typeof__(*(ptr)) __new = (new); \ - __typeof__(*(ptr)) __res = 0; \ + __typeof__(*(ptr)) __res; \ \ - pre_barrier; \ - \ - switch (sizeof(*(__ptr))) { \ - case 4: \ - __res = __cmpxchg_asm("ll", "sc", __ptr, __old, __new); \ - break; \ - case 8: \ - if (sizeof(long) == 8) { \ - __res = __cmpxchg_asm("lld", "scd", __ptr, \ - __old, __new); \ - break; \ - } \ - default: \ - __cmpxchg_called_with_bad_pointer(); \ - break; \ - } \ - \ - post_barrier; \ + smp_mb__before_llsc(); \ + __res = cmpxchg_local((ptr), (old), (new)); \ + smp_llsc_mb(); \ \ __res; \ }) -#define cmpxchg(ptr, old, new) __cmpxchg(ptr, old, new, smp_mb__before_llsc(), smp_llsc_mb()) -#define cmpxchg_local(ptr, old, new) __cmpxchg(ptr, old, new, , ) - #ifdef CONFIG_64BIT #define cmpxchg64_local(ptr, o, n) \ ({ \ @@ -245,4 +205,6 @@ extern void __cmpxchg_called_with_bad_pointer(void); #define cmpxchg64(ptr, o, n) cmpxchg64_local((ptr), (o), (n)) #endif +#undef __scbeqz + #endif /* __ASM_CMPXCHG_H */ diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 494d38274142..8baa9033b181 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -138,6 +138,9 @@ #ifndef cpu_has_mips16 #define cpu_has_mips16 (cpu_data[0].ases & MIPS_ASE_MIPS16) #endif +#ifndef cpu_has_mips16e2 +#define cpu_has_mips16e2 (cpu_data[0].ases & MIPS_ASE_MIPS16E2) +#endif #ifndef cpu_has_mdmx #define cpu_has_mdmx (cpu_data[0].ases & MIPS_ASE_MDMX) #endif @@ -487,6 +490,47 @@ # define cpu_has_perf (cpu_data[0].options & MIPS_CPU_PERF) #endif +#if defined(CONFIG_SMP) && defined(__mips_isa_rev) && (__mips_isa_rev >= 6) +/* + * Some systems share FTLB RAMs between threads within a core (siblings in + * kernel parlance). This means that FTLB entries may become invalid at almost + * any point when an entry is evicted due to a sibling thread writing an entry + * to the shared FTLB RAM. + * + * This is only relevant to SMP systems, and the only systems that exhibit this + * property implement MIPSr6 or higher so we constrain support for this to + * kernels that will run on such systems. + */ +# ifndef cpu_has_shared_ftlb_ram +# define cpu_has_shared_ftlb_ram \ + (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM) +# endif + +/* + * Some systems take this a step further & share FTLB entries between siblings. + * This is implemented as TLB writes happening as usual, but if an entry + * written by a sibling exists in the shared FTLB for a translation which would + * otherwise cause a TLB refill exception then the CPU will use the entry + * written by its sibling rather than triggering a refill & writing a matching + * TLB entry for itself. + * + * This is naturally only valid if a TLB entry is known to be suitable for use + * on all siblings in a CPU, and so it only takes effect when MMIDs are in use + * rather than ASIDs or when a TLB entry is marked global. + */ +# ifndef cpu_has_shared_ftlb_entries +# define cpu_has_shared_ftlb_entries \ + (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES) +# endif +#endif /* SMP && __mips_isa_rev >= 6 */ + +#ifndef cpu_has_shared_ftlb_ram +# define cpu_has_shared_ftlb_ram 0 +#endif +#ifndef cpu_has_shared_ftlb_entries +# define cpu_has_shared_ftlb_entries 0 +#endif + /* * Guest capabilities */ diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index bdd6dc18e65c..175fe565f4e1 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -84,6 +84,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) #ifdef CONFIG_SYS_HAS_CPU_MIPS64_R6 case CPU_I6400: + case CPU_I6500: case CPU_P6600: #endif diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 98f59307e6a3..d0c152b989f8 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -124,6 +124,7 @@ #define PRID_IMP_P5600 0xa800 #define PRID_IMP_I6400 0xa900 #define PRID_IMP_M6250 0xab00 +#define PRID_IMP_I6500 0xb000 /* * These are the PRID's for when 23:16 == PRID_COMP_SIBYTE @@ -247,6 +248,7 @@ #define PRID_REV_LOONGSON3B_R1 0x0006 #define PRID_REV_LOONGSON3B_R2 0x0007 #define PRID_REV_LOONGSON3A_R2 0x0008 +#define PRID_REV_LOONGSON3A_R3 0x0009 /* * Older processors used to encode processor version and revision in two @@ -322,7 +324,7 @@ enum cpu_type_enum { */ CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, - CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, + CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, CPU_I6500, CPU_QEMU_GENERIC, @@ -416,6 +418,10 @@ enum cpu_type_enum { #define MIPS_CPU_GUESTID MBIT_ULL(51) /* CPU uses VZ ASE GuestID feature */ #define MIPS_CPU_DRG MBIT_ULL(52) /* CPU has VZ Direct Root to Guest (DRG) */ #define MIPS_CPU_UFR MBIT_ULL(53) /* CPU supports User mode FR switching */ +#define MIPS_CPU_SHARED_FTLB_RAM \ + MBIT_ULL(54) /* CPU shares FTLB RAM with another */ +#define MIPS_CPU_SHARED_FTLB_ENTRIES \ + MBIT_ULL(55) /* CPU shares FTLB entries with another */ /* * CPU ASE encodings @@ -430,5 +436,6 @@ enum cpu_type_enum { #define MIPS_ASE_VZ 0x00000080 /* Virtualization ASE */ #define MIPS_ASE_MSA 0x00000100 /* MIPS SIMD Architecture */ #define MIPS_ASE_DSP3 0x00000200 /* Signal Processing ASE Rev 3*/ +#define MIPS_ASE_MIPS16E2 0x00000400 /* MIPS16e2 */ #endif /* _ASM_CPU_H */ diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index ddd1c918103b..c5d351786416 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -18,7 +18,7 @@ #include <irq.h> #define IRQ_STACK_SIZE THREAD_SIZE -#define IRQ_STACK_START (IRQ_STACK_SIZE - sizeof(unsigned long)) +#define IRQ_STACK_START (IRQ_STACK_SIZE - 16) extern void *irq_stack[NR_CPUS]; diff --git a/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h index ade0356df257..e6a8108cde4e 100644 --- a/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h @@ -40,6 +40,7 @@ #endif #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h index c5b6eef0efa7..bace5b9ae4df 100644 --- a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h @@ -31,6 +31,7 @@ #define cpu_has_ejtag 1 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h b/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h index bc1167dbd4e3..b56cf10b91d3 100644 --- a/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h @@ -19,6 +19,7 @@ #define cpu_has_ejtag 1 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h index 30c5cd9fd973..291fe90aafa5 100644 --- a/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h @@ -37,6 +37,7 @@ #endif #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h b/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h index 21eae03d752a..2ec10237688c 100644 --- a/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h @@ -27,6 +27,7 @@ #define cpu_has_mcheck 0 #define cpu_has_ejtag 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-generic/mc146818rtc.h b/arch/mips/include/asm/mach-generic/mc146818rtc.h index 0b9a942f079d..9c72e540ff56 100644 --- a/arch/mips/include/asm/mach-generic/mc146818rtc.h +++ b/arch/mips/include/asm/mach-generic/mc146818rtc.h @@ -27,7 +27,7 @@ static inline void CMOS_WRITE(unsigned char data, unsigned long addr) outb_p(data, RTC_PORT(1)); } -#define RTC_ALWAYS_BCD 1 +#define RTC_ALWAYS_BCD 0 #ifndef mc146818_decode_year #define mc146818_decode_year(year) ((year) < 70 ? (year) + 2000 : (year) + 1900) diff --git a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h index 9b19b72dba56..b80d5eafc9db 100644 --- a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h @@ -19,6 +19,7 @@ #define cpu_has_32fpr 1 #define cpu_has_counter 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 0 #define cpu_has_cache_cdex_p 1 #define cpu_has_prefetch 0 diff --git a/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h index 7449794eade6..136d6d464e32 100644 --- a/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h @@ -43,6 +43,7 @@ #define cpu_has_ejtag 0 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h index 4cec06d133db..ba8b4e30b3e2 100644 --- a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h @@ -16,6 +16,7 @@ */ #define cpu_has_watch 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 0 #define cpu_has_vce 0 #define cpu_has_cache_cdex_p 0 diff --git a/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h index 241409b78ff1..63b4c889094b 100644 --- a/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h @@ -29,6 +29,7 @@ #define cpu_has_32fpr 1 #define cpu_has_counter 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_vce 0 #define cpu_has_cache_cdex_s 0 #define cpu_has_mcheck 0 diff --git a/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h b/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h index 0933f94a1e69..7c5e576f9d96 100644 --- a/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h @@ -23,6 +23,7 @@ #define cpu_has_ejtag 1 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index d3f3258b7cd4..9f9bb9c53785 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -27,12 +27,22 @@ struct efi_memory_map_loongson { } __packed; enum loongson_cpu_type { - Loongson_2E = 0, - Loongson_2F = 1, - Loongson_3A = 2, - Loongson_3B = 3, - Loongson_1A = 4, - Loongson_1B = 5 + Legacy_2E = 0x0, + Legacy_2F = 0x1, + Legacy_3A = 0x2, + Legacy_3B = 0x3, + Legacy_1A = 0x4, + Legacy_1B = 0x5, + Legacy_2G = 0x6, + Legacy_2H = 0x7, + Loongson_1A = 0x100, + Loongson_1B = 0x101, + Loongson_2E = 0x200, + Loongson_2F = 0x201, + Loongson_2G = 0x202, + Loongson_2H = 0x203, + Loongson_3A = 0x300, + Loongson_3B = 0x301 }; /* diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index 89328a3d44d8..581915ce231c 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -32,6 +32,7 @@ #define cpu_has_mcheck 0 #define cpu_has_mdmx 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mips3d 0 #define cpu_has_mipsmt 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h index 091deb1700e5..0c29ff820bb9 100644 --- a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h @@ -13,6 +13,7 @@ #define cpu_has_4k_cache 1 #define cpu_has_watch 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_counter 1 #define cpu_has_divec 1 #define cpu_has_vce 0 diff --git a/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h b/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h index b15307597ee3..6a1087ee8c6e 100644 --- a/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h @@ -48,6 +48,7 @@ #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h b/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h index d38be668e338..e1e182300fea 100644 --- a/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h @@ -17,6 +17,7 @@ #define cpu_has_counter 1 #define cpu_has_watch 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 0 #define cpu_has_cache_cdex_p 1 #define cpu_has_prefetch 0 diff --git a/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h b/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h index 92927b62b5a0..7022358057fd 100644 --- a/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h @@ -13,6 +13,7 @@ */ #define cpu_has_watch 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 1 #define cpu_has_vce 0 #define cpu_has_cache_cdex_p 0 diff --git a/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h b/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h index 7f5144c6ce2d..b9d39dc45420 100644 --- a/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h @@ -6,6 +6,7 @@ #define cpu_has_inclusive_pcaches 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h index 6b444cd9526f..ecb6c7335484 100644 --- a/arch/mips/include/asm/machine.h +++ b/arch/mips/include/asm/machine.h @@ -60,4 +60,35 @@ mips_machine_is_compatible(const struct mips_machine *mach, const void *fdt) return NULL; } +/** + * struct mips_fdt_fixup - Describe a fixup to apply to an FDT + * @apply: applies the fixup to @fdt, returns zero on success else -errno + * @description: a short description of the fixup + * + * Describes a fixup applied to an FDT blob by the @apply function. The + * @description field provides a short description of the fixup intended for + * use in error messages if the @apply function returns non-zero. + */ +struct mips_fdt_fixup { + int (*apply)(void *fdt); + const char *description; +}; + +/** + * apply_mips_fdt_fixups() - apply fixups to an FDT blob + * @fdt_out: buffer in which to place the fixed-up FDT + * @fdt_out_size: the size of the @fdt_out buffer + * @fdt_in: the FDT blob + * @fixups: pointer to an array of fixups to be applied + * + * Loop through the array of fixups pointed to by @fixups, calling the apply + * function on each until either one returns an error or we reach the end of + * the list as indicated by an entry with a NULL apply field. + * + * Return: zero on success, else -errno + */ +extern int __init apply_mips_fdt_fixups(void *fdt_out, size_t fdt_out_size, + const void *fdt_in, + const struct mips_fdt_fixup *fixups); + #endif /* __MIPS_ASM_MACHINE_H__ */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 6875b69f59f7..dbb0eceda2c6 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -652,6 +652,7 @@ #define MIPS_CONF5_SBRI (_ULCAST_(1) << 6) #define MIPS_CONF5_FRE (_ULCAST_(1) << 8) #define MIPS_CONF5_UFE (_ULCAST_(1) << 9) +#define MIPS_CONF5_CA2 (_ULCAST_(1) << 14) #define MIPS_CONF5_MSAEN (_ULCAST_(1) << 27) #define MIPS_CONF5_EVA (_ULCAST_(1) << 28) #define MIPS_CONF5_CV (_ULCAST_(1) << 29) diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index 702c273e67a9..e51add184717 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -47,8 +47,8 @@ typedef struct { #define Elf_Mips_Rel Elf32_Rel #define Elf_Mips_Rela Elf32_Rela -#define ELF_MIPS_R_SYM(rel) ELF32_R_SYM(rel.r_info) -#define ELF_MIPS_R_TYPE(rel) ELF32_R_TYPE(rel.r_info) +#define ELF_MIPS_R_SYM(rel) ELF32_R_SYM((rel).r_info) +#define ELF_MIPS_R_TYPE(rel) ELF32_R_TYPE((rel).r_info) #endif @@ -65,8 +65,8 @@ typedef struct { #define Elf_Mips_Rel Elf64_Mips_Rel #define Elf_Mips_Rela Elf64_Mips_Rela -#define ELF_MIPS_R_SYM(rel) (rel.r_sym) -#define ELF_MIPS_R_TYPE(rel) (rel.r_type) +#define ELF_MIPS_R_SYM(rel) ((rel).r_sym) +#define ELF_MIPS_R_TYPE(rel) ((rel).r_type) #endif diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index a8df44d60607..a7d21da16b6a 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -9,431 +9,9 @@ #ifndef _ASM_SPINLOCK_H #define _ASM_SPINLOCK_H -#include <linux/compiler.h> - -#include <asm/barrier.h> #include <asm/processor.h> -#include <asm/compiler.h> -#include <asm/war.h> - -/* - * Your basic SMP spinlocks, allowing only a single CPU anywhere - * - * Simple spin lock operations. There are two variants, one clears IRQ's - * on the local processor, one does not. - * - * These are fair FIFO ticket locks - * - * (the type definitions are in asm/spinlock_types.h) - */ - - -/* - * Ticket locks are conceptually two parts, one indicating the current head of - * the queue, and the other indicating the current tail. The lock is acquired - * by atomically noting the tail and incrementing it by one (thus adding - * ourself to the queue and noting our position), then waiting until the head - * becomes equal to the the initial value of the tail. - */ - -static inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - u32 counters = ACCESS_ONCE(lock->lock); - - return ((counters >> 16) ^ counters) & 0xffff; -} - -static inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - return lock.h.serving_now == lock.h.ticket; -} - -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - u16 owner = READ_ONCE(lock->h.serving_now); - smp_rmb(); - for (;;) { - arch_spinlock_t tmp = READ_ONCE(*lock); - - if (tmp.h.serving_now == tmp.h.ticket || - tmp.h.serving_now != owner) - break; - - cpu_relax(); - } - smp_acquire__after_ctrl_dep(); -} - -static inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - u32 counters = ACCESS_ONCE(lock->lock); - - return (((counters >> 16) - counters) & 0xffff) > 1; -} -#define arch_spin_is_contended arch_spin_is_contended - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - int my_ticket; - int tmp; - int inc = 0x10000; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__ ( - " .set push # arch_spin_lock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " addu %[my_ticket], %[ticket], %[inc] \n" - " sc %[my_ticket], %[ticket_ptr] \n" - " beqzl %[my_ticket], 1b \n" - " nop \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[ticket], %[ticket], 0xffff \n" - " bne %[ticket], %[my_ticket], 4f \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - "2: \n" - " .subsection 2 \n" - "4: andi %[ticket], %[ticket], 0xffff \n" - " sll %[ticket], 5 \n" - " \n" - "6: bnez %[ticket], 6b \n" - " subu %[ticket], 1 \n" - " \n" - " lhu %[ticket], %[serving_now_ptr] \n" - " beq %[ticket], %[my_ticket], 2b \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - " b 4b \n" - " subu %[ticket], %[ticket], 1 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [serving_now_ptr] "+m" (lock->h.serving_now), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (my_ticket) - : [inc] "r" (inc)); - } else { - __asm__ __volatile__ ( - " .set push # arch_spin_lock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " addu %[my_ticket], %[ticket], %[inc] \n" - " sc %[my_ticket], %[ticket_ptr] \n" - " beqz %[my_ticket], 1b \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[ticket], %[ticket], 0xffff \n" - " bne %[ticket], %[my_ticket], 4f \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - "2: .insn \n" - " .subsection 2 \n" - "4: andi %[ticket], %[ticket], 0xffff \n" - " sll %[ticket], 5 \n" - " \n" - "6: bnez %[ticket], 6b \n" - " subu %[ticket], 1 \n" - " \n" - " lhu %[ticket], %[serving_now_ptr] \n" - " beq %[ticket], %[my_ticket], 2b \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - " b 4b \n" - " subu %[ticket], %[ticket], 1 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [serving_now_ptr] "+m" (lock->h.serving_now), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (my_ticket) - : [inc] "r" (inc)); - } - - smp_llsc_mb(); -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - unsigned int serving_now = lock->h.serving_now + 1; - wmb(); - lock->h.serving_now = (u16)serving_now; - nudge_writes(); -} - -static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) -{ - int tmp, tmp2, tmp3; - int inc = 0x10000; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__ ( - " .set push # arch_spin_trylock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[now_serving], %[ticket], 0xffff \n" - " bne %[my_ticket], %[now_serving], 3f \n" - " addu %[ticket], %[ticket], %[inc] \n" - " sc %[ticket], %[ticket_ptr] \n" - " beqzl %[ticket], 1b \n" - " li %[ticket], 1 \n" - "2: \n" - " .subsection 2 \n" - "3: b 2b \n" - " li %[ticket], 0 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (tmp2), - [now_serving] "=&r" (tmp3) - : [inc] "r" (inc)); - } else { - __asm__ __volatile__ ( - " .set push # arch_spin_trylock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[now_serving], %[ticket], 0xffff \n" - " bne %[my_ticket], %[now_serving], 3f \n" - " addu %[ticket], %[ticket], %[inc] \n" - " sc %[ticket], %[ticket_ptr] \n" - " beqz %[ticket], 1b \n" - " li %[ticket], 1 \n" - "2: .insn \n" - " .subsection 2 \n" - "3: b 2b \n" - " li %[ticket], 0 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (tmp2), - [now_serving] "=&r" (tmp3) - : [inc] "r" (inc)); - } - - smp_llsc_mb(); - - return tmp; -} - -/* - * Read-write spinlocks, allowing multiple readers but only one writer. - * - * NOTE! it is quite common to have readers in interrupts but no interrupt - * writers. For those circumstances we can "mix" irq-safe locks - any writer - * needs to get a irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ - -/* - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(rw) ((rw)->lock >= 0) - -/* - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(rw) (!(rw)->lock) - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_read_lock \n" - "1: ll %1, %2 \n" - " bltz %1, 1b \n" - " addu %1, 1 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - " nop \n" - " .set reorder \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_lock \n" - " bltz %1, 1b \n" - " addu %1, 1 \n" - "2: sc %1, %0 \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - } - - smp_llsc_mb(); -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - smp_mb__before_llsc(); - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_unlock \n" - " addiu %1, -1 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_unlock \n" - " addiu %1, -1 \n" - " sc %1, %0 \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - } -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_write_lock \n" - "1: ll %1, %2 \n" - " bnez %1, 1b \n" - " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - " nop \n" - " .set reorder \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - "1: ll %1, %2 # arch_write_lock \n" - " bnez %1, 1b \n" - " lui %1, 0x8000 \n" - "2: sc %1, %0 \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - } - - smp_llsc_mb(); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - smp_mb__before_llsc(); - - __asm__ __volatile__( - " # arch_write_unlock \n" - " sw $0, %0 \n" - : "=m" (rw->lock) - : "m" (rw->lock) - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp; - int ret; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_read_trylock \n" - " li %2, 0 \n" - "1: ll %1, %3 \n" - " bltz %1, 2f \n" - " addu %1, 1 \n" - " sc %1, %0 \n" - " .set reorder \n" - " beqzl %1, 1b \n" - " nop \n" - __WEAK_LLSC_MB - " li %2, 1 \n" - "2: \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - __asm__ __volatile__( - " .set noreorder # arch_read_trylock \n" - " li %2, 0 \n" - "1: ll %1, %3 \n" - " bltz %1, 2f \n" - " addu %1, 1 \n" - " sc %1, %0 \n" - " beqz %1, 1b \n" - " nop \n" - " .set reorder \n" - __WEAK_LLSC_MB - " li %2, 1 \n" - "2: .insn \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } - - return ret; -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp; - int ret; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_write_trylock \n" - " li %2, 0 \n" - "1: ll %1, %3 \n" - " bnez %1, 2f \n" - " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - " nop \n" - __WEAK_LLSC_MB - " li %2, 1 \n" - " .set reorder \n" - "2: \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - " ll %1, %3 # arch_write_trylock \n" - " li %2, 0 \n" - " bnez %1, 2f \n" - " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " li %2, 1 \n" - "2: .insn \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), - "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - - smp_llsc_mb(); - } - - return ret; -} +#include <asm/qrwlock.h> +#include <asm/qspinlock.h> #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/mips/include/asm/spinlock_types.h b/arch/mips/include/asm/spinlock_types.h index 9b2528e612c0..177e722eb96c 100644 --- a/arch/mips/include/asm/spinlock_types.h +++ b/arch/mips/include/asm/spinlock_types.h @@ -1,37 +1,7 @@ #ifndef _ASM_SPINLOCK_TYPES_H #define _ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - -#include <linux/types.h> - -#include <asm/byteorder.h> - -typedef union { - /* - * bits 0..15 : serving_now - * bits 16..31 : ticket - */ - u32 lock; - struct { -#ifdef __BIG_ENDIAN - u16 ticket; - u16 serving_now; -#else - u16 serving_now; - u16 ticket; -#endif - } h; -} arch_spinlock_t; - -#define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0 } - -typedef struct { - volatile unsigned int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { 0 } +#include <asm-generic/qspinlock_types.h> +#include <asm-generic/qrwlock_types.h> #endif diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index d87882513ee3..7c713025b23f 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -85,7 +85,7 @@ static inline void syscall_set_return_value(struct task_struct *task, { if (error) { regs->regs[2] = -error; - regs->regs[7] = -1; + regs->regs[7] = 1; } else { regs->regs[2] = val; regs->regs[7] = 0; diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 9700251159b1..b71306947290 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -497,283 +497,6 @@ do { \ extern void __put_user_unknown(void); /* - * ul{b,h,w} are macros and there are no equivalent macros for EVA. - * EVA unaligned access is handled in the ADE exception handler. - */ -#ifndef CONFIG_EVA -/* - * put_user_unaligned: - Write a simple value into user space. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Returns zero on success, or -EFAULT on error. - */ -#define put_user_unaligned(x,ptr) \ - __put_user_unaligned_check((x),(ptr),sizeof(*(ptr))) - -/* - * get_user_unaligned: - Get a simple variable from user space. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Returns zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ -#define get_user_unaligned(x,ptr) \ - __get_user_unaligned_check((x),(ptr),sizeof(*(ptr))) - -/* - * __put_user_unaligned: - Write a simple value into user space, with less checking. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Returns zero on success, or -EFAULT on error. - */ -#define __put_user_unaligned(x,ptr) \ - __put_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) - -/* - * __get_user_unaligned: - Get a simple variable from user space, with less checking. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Returns zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ -#define __get_user_unaligned(x,ptr) \ - __get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) - -/* - * Yuck. We need two variants, one for 64bit operation and one - * for 32 bit mode and old iron. - */ -#ifdef CONFIG_32BIT -#define __GET_USER_UNALIGNED_DW(val, ptr) \ - __get_user_unaligned_asm_ll32(val, ptr) -#endif -#ifdef CONFIG_64BIT -#define __GET_USER_UNALIGNED_DW(val, ptr) \ - __get_user_unaligned_asm(val, "uld", ptr) -#endif - -extern void __get_user_unaligned_unknown(void); - -#define __get_user_unaligned_common(val, size, ptr) \ -do { \ - switch (size) { \ - case 1: __get_data_asm(val, "lb", ptr); break; \ - case 2: __get_data_unaligned_asm(val, "ulh", ptr); break; \ - case 4: __get_data_unaligned_asm(val, "ulw", ptr); break; \ - case 8: __GET_USER_UNALIGNED_DW(val, ptr); break; \ - default: __get_user_unaligned_unknown(); break; \ - } \ -} while (0) - -#define __get_user_unaligned_nocheck(x,ptr,size) \ -({ \ - int __gu_err; \ - \ - __get_user_unaligned_common((x), size, ptr); \ - __gu_err; \ -}) - -#define __get_user_unaligned_check(x,ptr,size) \ -({ \ - int __gu_err = -EFAULT; \ - const __typeof__(*(ptr)) __user * __gu_ptr = (ptr); \ - \ - if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \ - __get_user_unaligned_common((x), size, __gu_ptr); \ - \ - __gu_err; \ -}) - -#define __get_data_unaligned_asm(val, insn, addr) \ -{ \ - long __gu_tmp; \ - \ - __asm__ __volatile__( \ - "1: " insn " %1, %3 \n" \ - "2: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "3: li %0, %4 \n" \ - " move %1, $0 \n" \ - " j 2b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " "__UA_ADDR "\t1b, 3b \n" \ - " "__UA_ADDR "\t1b + 4, 3b \n" \ - " .previous \n" \ - : "=r" (__gu_err), "=r" (__gu_tmp) \ - : "0" (0), "o" (__m(addr)), "i" (-EFAULT)); \ - \ - (val) = (__typeof__(*(addr))) __gu_tmp; \ -} - -/* - * Get a long long 64 using 32 bit registers. - */ -#define __get_user_unaligned_asm_ll32(val, addr) \ -{ \ - unsigned long long __gu_tmp; \ - \ - __asm__ __volatile__( \ - "1: ulw %1, (%3) \n" \ - "2: ulw %D1, 4(%3) \n" \ - " move %0, $0 \n" \ - "3: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "4: li %0, %4 \n" \ - " move %1, $0 \n" \ - " move %D1, $0 \n" \ - " j 3b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " " __UA_ADDR " 1b, 4b \n" \ - " " __UA_ADDR " 1b + 4, 4b \n" \ - " " __UA_ADDR " 2b, 4b \n" \ - " " __UA_ADDR " 2b + 4, 4b \n" \ - " .previous \n" \ - : "=r" (__gu_err), "=&r" (__gu_tmp) \ - : "0" (0), "r" (addr), "i" (-EFAULT)); \ - (val) = (__typeof__(*(addr))) __gu_tmp; \ -} - -/* - * Yuck. We need two variants, one for 64bit operation and one - * for 32 bit mode and old iron. - */ -#ifdef CONFIG_32BIT -#define __PUT_USER_UNALIGNED_DW(ptr) __put_user_unaligned_asm_ll32(ptr) -#endif -#ifdef CONFIG_64BIT -#define __PUT_USER_UNALIGNED_DW(ptr) __put_user_unaligned_asm("usd", ptr) -#endif - -#define __put_user_unaligned_common(ptr, size) \ -do { \ - switch (size) { \ - case 1: __put_data_asm("sb", ptr); break; \ - case 2: __put_user_unaligned_asm("ush", ptr); break; \ - case 4: __put_user_unaligned_asm("usw", ptr); break; \ - case 8: __PUT_USER_UNALIGNED_DW(ptr); break; \ - default: __put_user_unaligned_unknown(); break; \ -} while (0) - -#define __put_user_unaligned_nocheck(x,ptr,size) \ -({ \ - __typeof__(*(ptr)) __pu_val; \ - int __pu_err = 0; \ - \ - __pu_val = (x); \ - __put_user_unaligned_common(ptr, size); \ - __pu_err; \ -}) - -#define __put_user_unaligned_check(x,ptr,size) \ -({ \ - __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - __typeof__(*(ptr)) __pu_val = (x); \ - int __pu_err = -EFAULT; \ - \ - if (likely(access_ok(VERIFY_WRITE, __pu_addr, size))) \ - __put_user_unaligned_common(__pu_addr, size); \ - \ - __pu_err; \ -}) - -#define __put_user_unaligned_asm(insn, ptr) \ -{ \ - __asm__ __volatile__( \ - "1: " insn " %z2, %3 # __put_user_unaligned_asm\n" \ - "2: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "3: li %0, %4 \n" \ - " j 2b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " " __UA_ADDR " 1b, 3b \n" \ - " .previous \n" \ - : "=r" (__pu_err) \ - : "0" (0), "Jr" (__pu_val), "o" (__m(ptr)), \ - "i" (-EFAULT)); \ -} - -#define __put_user_unaligned_asm_ll32(ptr) \ -{ \ - __asm__ __volatile__( \ - "1: sw %2, (%3) # __put_user_unaligned_asm_ll32 \n" \ - "2: sw %D2, 4(%3) \n" \ - "3: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "4: li %0, %4 \n" \ - " j 3b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " " __UA_ADDR " 1b, 4b \n" \ - " " __UA_ADDR " 1b + 4, 4b \n" \ - " " __UA_ADDR " 2b, 4b \n" \ - " " __UA_ADDR " 2b + 4, 4b \n" \ - " .previous" \ - : "=r" (__pu_err) \ - : "0" (0), "r" (__pu_val), "r" (ptr), \ - "i" (-EFAULT)); \ -} - -extern void __put_user_unaligned_unknown(void); -#endif - -/* * We're generating jump to subroutines which will be outside the range of * jump instructions */ diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h index 3748f4d120a5..59dae37f6b8d 100644 --- a/arch/mips/include/asm/uasm.h +++ b/arch/mips/include/asm/uasm.h @@ -72,9 +72,12 @@ Ip_u1u2s3(_beq); Ip_u1u2s3(_beql); Ip_u1s2(_bgez); Ip_u1s2(_bgezl); +Ip_u1s2(_bgtz); +Ip_u1s2(_blez); Ip_u1s2(_bltz); Ip_u1s2(_bltzl); Ip_u1u2s3(_bne); +Ip_u1(_break); Ip_u2s3u1(_cache); Ip_u1u2(_cfc1); Ip_u2u1(_cfcmsa); @@ -82,19 +85,28 @@ Ip_u1u2(_ctc1); Ip_u2u1(_ctcmsa); Ip_u2u1s3(_daddiu); Ip_u3u1u2(_daddu); +Ip_u1u2(_ddivu); Ip_u1(_di); Ip_u2u1msbu3(_dins); Ip_u2u1msbu3(_dinsm); +Ip_u2u1msbu3(_dinsu); Ip_u1u2(_divu); Ip_u1u2u3(_dmfc0); Ip_u1u2u3(_dmtc0); +Ip_u1u2(_dmultu); Ip_u2u1u3(_drotr); Ip_u2u1u3(_drotr32); +Ip_u2u1(_dsbh); +Ip_u2u1(_dshd); Ip_u2u1u3(_dsll); Ip_u2u1u3(_dsll32); +Ip_u3u2u1(_dsllv); Ip_u2u1u3(_dsra); +Ip_u2u1u3(_dsra32); +Ip_u3u2u1(_dsrav); Ip_u2u1u3(_dsrl); Ip_u2u1u3(_dsrl32); +Ip_u3u2u1(_dsrlv); Ip_u3u1u2(_dsubu); Ip_0(_eret); Ip_u2u1msbu3(_ext); @@ -104,6 +116,7 @@ Ip_u1(_jal); Ip_u2u1(_jalr); Ip_u1(_jr); Ip_u2s3u1(_lb); +Ip_u2s3u1(_lbu); Ip_u2s3u1(_ld); Ip_u3u1u2(_ldx); Ip_u2s3u1(_lh); @@ -112,27 +125,35 @@ Ip_u2s3u1(_ll); Ip_u2s3u1(_lld); Ip_u1s2(_lui); Ip_u2s3u1(_lw); +Ip_u2s3u1(_lwu); Ip_u3u1u2(_lwx); Ip_u1u2u3(_mfc0); Ip_u1u2u3(_mfhc0); Ip_u1(_mfhi); Ip_u1(_mflo); +Ip_u3u1u2(_movn); +Ip_u3u1u2(_movz); Ip_u1u2u3(_mtc0); Ip_u1u2u3(_mthc0); Ip_u1(_mthi); Ip_u1(_mtlo); Ip_u3u1u2(_mul); +Ip_u1u2(_multu); +Ip_u3u1u2(_nor); Ip_u3u1u2(_or); Ip_u2u1u3(_ori); Ip_u2s3u1(_pref); Ip_0(_rfe); Ip_u2u1u3(_rotr); +Ip_u2s3u1(_sb); Ip_u2s3u1(_sc); Ip_u2s3u1(_scd); Ip_u2s3u1(_sd); +Ip_u2s3u1(_sh); Ip_u2u1u3(_sll); Ip_u3u2u1(_sllv); Ip_s3s1s2(_slt); +Ip_u2u1s3(_slti); Ip_u2u1s3(_sltiu); Ip_u3u1u2(_sltu); Ip_u2u1u3(_sra); @@ -248,6 +269,15 @@ static inline void uasm_i_dsrl_safe(u32 **p, unsigned int a1, uasm_i_dsrl32(p, a1, a2, a3 - 32); } +static inline void uasm_i_dsra_safe(u32 **p, unsigned int a1, + unsigned int a2, unsigned int a3) +{ + if (a3 < 32) + uasm_i_dsra(p, a1, a2, a3); + else + uasm_i_dsra32(p, a1, a2, a3 - 32); +} + /* Handle relocations. */ struct uasm_reloc { u32 *addr; diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h index 8f4ca5dd992b..b7cd6cf77b83 100644 --- a/arch/mips/include/asm/vdso.h +++ b/arch/mips/include/asm/vdso.h @@ -79,8 +79,8 @@ union mips_vdso_data { struct { u64 xtime_sec; u64 xtime_nsec; - u32 wall_to_mono_sec; - u32 wall_to_mono_nsec; + u64 wall_to_mono_sec; + u64 wall_to_mono_nsec; u32 seq_count; u32 cs_shift; u8 clock_mode; diff --git a/arch/mips/include/asm/yamon-dt.h b/arch/mips/include/asm/yamon-dt.h new file mode 100644 index 000000000000..485cfe3e45e1 --- /dev/null +++ b/arch/mips/include/asm/yamon-dt.h @@ -0,0 +1,64 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * 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 __MIPS_ASM_YAMON_DT_H__ +#define __MIPS_ASM_YAMON_DT_H__ + +#include <linux/types.h> + +/** + * struct yamon_mem_region - Represents a contiguous range of physical RAM. + * @start: Start physical address. + * @size: Maximum size of region. + * @discard: Length of additional memory to discard after the region. + */ +struct yamon_mem_region { + phys_addr_t start; + phys_addr_t size; + phys_addr_t discard; +}; + +/** + * yamon_dt_append_cmdline() - Append YAMON-provided command line to /chosen + * @fdt: the FDT blob + * + * Write the YAMON-provided command line to the bootargs property of the + * /chosen node in @fdt. + * + * Return: 0 on success, else -errno + */ +extern __init int yamon_dt_append_cmdline(void *fdt); + +/** + * yamon_dt_append_memory() - Append YAMON-provided memory info to /memory + * @fdt: the FDT blob + * @regions: zero size terminated array of physical memory regions + * + * Generate a /memory node in @fdt based upon memory size information provided + * by YAMON in its environment and the @regions array. + * + * Return: 0 on success, else -errno + */ +extern __init int yamon_dt_append_memory(void *fdt, + const struct yamon_mem_region *regions); + +/** + * yamon_dt_serial_config() - Append YAMON-provided serial config to /chosen + * @fdt: the FDT blob + * + * Generate a stdout-path property in the /chosen node of @fdt, based upon + * information provided in the YAMON environment about the UART configuration + * of the system. + * + * Return: 0 on success, else -errno + */ +extern __init int yamon_dt_serial_config(void *fdt); + +#endif /* __MIPS_ASM_YAMON_DT_H__ */ diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index b5e46ae872d3..d61897535926 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -276,12 +276,19 @@ enum lx_func { */ enum bshfl_func { wsbh_op = 0x2, - dshd_op = 0x5, seb_op = 0x10, seh_op = 0x18, }; /* + * DBSHFL opcodes + */ +enum dbshfl_func { + dsbh_op = 0x2, + dshd_op = 0x5, +}; + +/* * MSA minor opcodes. */ enum msa_func { @@ -755,6 +762,16 @@ struct msa_mi10_format { /* MSA MI10 */ ;)))))) }; +struct dsp_format { /* SPEC3 DSP format instructions */ + __BITFIELD_FIELD(unsigned int opcode : 6, + __BITFIELD_FIELD(unsigned int base : 5, + __BITFIELD_FIELD(unsigned int index : 5, + __BITFIELD_FIELD(unsigned int rd : 5, + __BITFIELD_FIELD(unsigned int op : 5, + __BITFIELD_FIELD(unsigned int func : 6, + ;)))))) +}; + struct spec3_format { /* SPEC3 */ __BITFIELD_FIELD(unsigned int opcode:6, __BITFIELD_FIELD(unsigned int rs:5, @@ -1046,6 +1063,7 @@ union mips_instruction { struct b_format b_format; struct ps_format ps_format; struct v_format v_format; + struct dsp_format dsp_format; struct spec3_format spec3_format; struct fb_format fb_format; struct fp0_format fp0_format; diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 9a0e37b92ce0..46c0581256f1 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds -obj-y += cpu-probe.o branch.o elf.o entry.o genex.o idle.o irq.o \ +obj-y += cmpxchg.o cpu-probe.o branch.o elf.o entry.o genex.o idle.o irq.o \ process.o prom.o ptrace.o reset.o setup.o signal.o \ syscall.o time.o topology.o traps.o unaligned.o watch.o \ vdso.o cacheinfo.o @@ -31,7 +31,6 @@ obj-$(CONFIG_SYNC_R4K) += sync-r4k.o obj-$(CONFIG_DEBUG_FS) += segment.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_MODULES_USE_ELF_RELA) += module-rela.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index f702a459a830..b79ed9af9886 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs) * * @regs: Pointer to pt_regs * @insn: branch instruction to decode - * @returns: -EFAULT on error and forces SIGBUS, and on success + * @returns: -EFAULT on error and forces SIGILL, and on success * returns 0 or BRANCH_LIKELY_TAKEN as appropriate after * evaluating the branch. * @@ -431,7 +431,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* Fall through */ case jr_op: if (NO_R6EMU && insn.r_format.func == jr_op) - goto sigill_r6; + goto sigill_r2r6; regs->cp0_epc = regs->regs[insn.r_format.rs]; break; } @@ -446,7 +446,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, switch (insn.i_format.rt) { case bltzl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -459,7 +459,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -473,10 +473,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bltzal_op: case bltzall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bltzall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bltzall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a NAL @@ -507,10 +505,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezal_op: case bgezall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bgezall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bgezall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a BAL @@ -556,6 +552,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * These are unconditional and in j_format. */ + case jalx_op: case jal_op: regs->regs[31] = regs->cp0_epc + 8; case j_op: @@ -573,7 +570,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, */ case beql_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) { @@ -587,7 +584,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bnel_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) { @@ -601,7 +598,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case blezl_op: /* not really i_format */ if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case blez_op: /* * Compact branches for R6 for the @@ -636,7 +633,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgtzl_op: if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgtz_op: /* * Compact branches for R6 for the @@ -774,35 +771,27 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, #else case bc6_op: /* Only valid for MIPS R6 */ - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; regs->cp0_epc += 8; break; case balc6_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BALC */ regs->regs[31] = epc + 4; epc += 4 + (insn.i_format.simmediate << 2); regs->cp0_epc = epc; break; case pop66_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BEQZC || JIC */ regs->cp0_epc += 8; break; case pop76_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BNEZC || JIALC */ if (!insn.i_format.rs) { /* JIALC: set $31/ra */ @@ -814,10 +803,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case pop10_op: case pop30_op: /* Only valid for MIPS R6 */ - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* * Compact branches: * bovc, beqc, beqzalc, bnvc, bnec, bnezlac @@ -831,12 +818,18 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, return ret; sigill_dsp: - printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm); - force_sig(SIGBUS, current); + pr_debug("%s: DSP branch but not DSP ASE - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); + return -EFAULT; +sigill_r2r6: + pr_debug("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); return -EFAULT; sigill_r6: - pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", - current->comm); + pr_debug("%s: R6 branch but no MIPSr6 ISA support - sending SIGILL.\n", + current->comm); force_sig(SIGILL, current); return -EFAULT; } diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c new file mode 100644 index 000000000000..7730f1d3434f --- /dev/null +++ b/arch/mips/kernel/cmpxchg.c @@ -0,0 +1,109 @@ +/* + * Copyright (C) 2017 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * 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. + */ + +#include <linux/bitops.h> +#include <asm/cmpxchg.h> + +unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size) +{ + u32 old32, new32, load32, mask; + volatile u32 *ptr32; + unsigned int shift; + + /* Check that ptr is naturally aligned */ + WARN_ON((unsigned long)ptr & (size - 1)); + + /* Mask value to the correct size. */ + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0); + val &= mask; + + /* + * Calculate a shift & mask that correspond to the value we wish to + * exchange within the naturally aligned 4 byte integerthat includes + * it. + */ + shift = (unsigned long)ptr & 0x3; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + shift ^= sizeof(u32) - size; + shift *= BITS_PER_BYTE; + mask <<= shift; + + /* + * Calculate a pointer to the naturally aligned 4 byte integer that + * includes our byte of interest, and load its value. + */ + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3); + load32 = *ptr32; + + do { + old32 = load32; + new32 = (load32 & ~mask) | (val << shift); + load32 = cmpxchg(ptr32, old32, new32); + } while (load32 != old32); + + return (load32 & mask) >> shift; +} + +unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) +{ + u32 mask, old32, new32, load32; + volatile u32 *ptr32; + unsigned int shift; + u8 load; + + /* Check that ptr is naturally aligned */ + WARN_ON((unsigned long)ptr & (size - 1)); + + /* Mask inputs to the correct size. */ + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0); + old &= mask; + new &= mask; + + /* + * Calculate a shift & mask that correspond to the value we wish to + * compare & exchange within the naturally aligned 4 byte integer + * that includes it. + */ + shift = (unsigned long)ptr & 0x3; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + shift ^= sizeof(u32) - size; + shift *= BITS_PER_BYTE; + mask <<= shift; + + /* + * Calculate a pointer to the naturally aligned 4 byte integer that + * includes our byte of interest, and load its value. + */ + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3); + load32 = *ptr32; + + while (true) { + /* + * Ensure the byte we want to exchange matches the expected + * old value, and if not then bail. + */ + load = (load32 & mask) >> shift; + if (load != old) + return load; + + /* + * Calculate the old & new values of the naturally aligned + * 4 byte integer that include the byte we want to exchange. + * Attempt to exchange the old value for the new value, and + * return if we succeed. + */ + old32 = (load32 & ~mask) | (old << shift); + new32 = (load32 & ~mask) | (new << shift); + load32 = cmpxchg(ptr32, old32, new32); + if (load32 == old32) + return old; + } +} diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index a00e87b0256d..b849fe6aad94 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -22,6 +22,7 @@ #define GCR_CL_COHERENCE_OFS 0x2008 #define GCR_CL_ID_OFS 0x2028 +#define CPC_CL_VC_STOP_OFS 0x2020 #define CPC_CL_VC_RUN_OFS 0x2028 .extern mips_cm_base @@ -376,8 +377,12 @@ LEAF(mips_cps_boot_vpes) PTR_LI t2, UNCAC_BASE PTR_ADD t1, t1, t2 - /* Set VC_RUN to the VPE mask */ + /* Start any other VPs that ought to be running */ PTR_S ta2, CPC_CL_VC_RUN_OFS(t1) + + /* Ensure this VP stops running if it shouldn't be */ + not ta2 + PTR_S ta2, CPC_CL_VC_STOP_OFS(t1) ehb #elif defined(CONFIG_MIPS_MT) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 1aba27786bd5..d08afc7dc507 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -564,6 +564,7 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags) back_to_back_c0_hazard(); break; case CPU_I6400: + case CPU_I6500: /* There's no way to disable the FTLB */ if (!(flags & FTLB_EN)) return 1; @@ -844,6 +845,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c) c->options |= MIPS_CPU_MVH; if (cpu_has_mips_r6 && (config5 & MIPS_CONF5_VP)) c->options |= MIPS_CPU_VP; + if (config5 & MIPS_CONF5_CA2) + c->ases |= MIPS_ASE_MIPS16E2; return config5 & MIPS_CONF_M; } @@ -1635,6 +1638,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_I6400; __cpu_name[cpu] = "MIPS I6400"; break; + case PRID_IMP_I6500: + c->cputype = CPU_I6500; + __cpu_name[cpu] = "MIPS I6500"; + break; case PRID_IMP_M5150: c->cputype = CPU_M5150; __cpu_name[cpu] = "MIPS M5150"; @@ -1648,6 +1655,17 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) decode_configs(c); spram_config(); + + switch (__get_cpu_type(c->cputype)) { + case CPU_I6500: + c->options |= MIPS_CPU_SHARED_FTLB_ENTRIES; + /* fall-through */ + case CPU_I6400: + c->options |= MIPS_CPU_SHARED_FTLB_RAM; + /* fall-through */ + default: + break; + } } static inline void cpu_probe_alchemy(struct cpuinfo_mips *c, unsigned int cpu) @@ -1831,6 +1849,12 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); break; + case PRID_REV_LOONGSON3A_R3: + c->cputype = CPU_LOONGSON3; + __cpu_name[cpu] = "ICT Loongson-3"; + set_elf_platform(cpu, "loongson3a"); + set_isa(c, MIPS_CPU_ISA_M64R2); + break; } decode_configs(c); diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 659e6d3ae335..cb0c57f860d4 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -265,15 +265,34 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) u32 val; preempt_disable(); - curr_core = current_cpu_data.core; - spin_lock_irqsave(&per_cpu(cm_core_lock, curr_core), - per_cpu(cm_core_lock_flags, curr_core)); if (mips_cm_revision() >= CM_REV_CM3) { val = core << CM3_GCR_Cx_OTHER_CORE_SHF; val |= vp << CM3_GCR_Cx_OTHER_VP_SHF; + + /* + * We need to disable interrupts in SMP systems in order to + * ensure that we don't interrupt the caller with code which + * may modify the redirect register. We do so here in a + * slightly obscure way by using a spin lock, since this has + * the neat property of also catching any nested uses of + * mips_cm_lock_other() leading to a deadlock or a nice warning + * with lockdep enabled. + */ + spin_lock_irqsave(this_cpu_ptr(&cm_core_lock), + *this_cpu_ptr(&cm_core_lock_flags)); } else { - BUG_ON(vp != 0); + WARN_ON(vp != 0); + + /* + * We only have a GCR_CL_OTHER per core in systems with + * CM 2.5 & older, so have to ensure other VP(E)s don't + * race with us. + */ + curr_core = current_cpu_data.core; + spin_lock_irqsave(&per_cpu(cm_core_lock, curr_core), + per_cpu(cm_core_lock_flags, curr_core)); + val = core << CM_GCR_Cx_OTHER_CORENUM_SHF; } @@ -288,10 +307,17 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) void mips_cm_unlock_other(void) { - unsigned curr_core = current_cpu_data.core; + unsigned int curr_core; + + if (mips_cm_revision() < CM_REV_CM3) { + curr_core = current_cpu_data.core; + spin_unlock_irqrestore(&per_cpu(cm_core_lock, curr_core), + per_cpu(cm_core_lock_flags, curr_core)); + } else { + spin_unlock_irqrestore(this_cpu_ptr(&cm_core_lock), + *this_cpu_ptr(&cm_core_lock_flags)); + } - spin_unlock_irqrestore(&per_cpu(cm_core_lock, curr_core), - per_cpu(cm_core_lock_flags, curr_core)); preempt_enable(); } diff --git a/arch/mips/kernel/module-rela.c b/arch/mips/kernel/module-rela.c deleted file mode 100644 index 781168834456..000000000000 --- a/arch/mips/kernel/module-rela.c +++ /dev/null @@ -1,202 +0,0 @@ -/* - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (C) 2001 Rusty Russell. - * Copyright (C) 2003, 2004 Ralf Baechle (ralf@linux-mips.org) - * Copyright (C) 2005 Thiemo Seufer - * Copyright (C) 2015 Imagination Technologies Ltd. - */ - -#include <linux/elf.h> -#include <linux/err.h> -#include <linux/errno.h> -#include <linux/moduleloader.h> - -extern int apply_r_mips_none(struct module *me, u32 *location, Elf_Addr v); - -static int apply_r_mips_32_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *location = v; - - return 0; -} - -static int apply_r_mips_26_rela(struct module *me, u32 *location, Elf_Addr v) -{ - if (v % 4) { - pr_err("module %s: dangerous R_MIPS_26 RELA relocation\n", - me->name); - return -ENOEXEC; - } - - if ((v & 0xf0000000) != (((unsigned long)location + 4) & 0xf0000000)) { - pr_err("module %s: relocation overflow\n", me->name); - return -ENOEXEC; - } - - *location = (*location & ~0x03ffffff) | ((v >> 2) & 0x03ffffff); - - return 0; -} - -static int apply_r_mips_hi16_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *location = (*location & 0xffff0000) | - ((((long long) v + 0x8000LL) >> 16) & 0xffff); - - return 0; -} - -static int apply_r_mips_lo16_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *location = (*location & 0xffff0000) | (v & 0xffff); - - return 0; -} - -static int apply_r_mips_pc_rela(struct module *me, u32 *location, Elf_Addr v, - unsigned bits) -{ - unsigned long mask = GENMASK(bits - 1, 0); - unsigned long se_bits; - long offset; - - if (v % 4) { - pr_err("module %s: dangerous R_MIPS_PC%u RELA relocation\n", - me->name, bits); - return -ENOEXEC; - } - - offset = ((long)v - (long)location) >> 2; - - /* check the sign bit onwards are identical - ie. we didn't overflow */ - se_bits = (offset & BIT(bits - 1)) ? ~0ul : 0; - if ((offset & ~mask) != (se_bits & ~mask)) { - pr_err("module %s: relocation overflow\n", me->name); - return -ENOEXEC; - } - - *location = (*location & ~mask) | (offset & mask); - - return 0; -} - -static int apply_r_mips_pc16_rela(struct module *me, u32 *location, Elf_Addr v) -{ - return apply_r_mips_pc_rela(me, location, v, 16); -} - -static int apply_r_mips_pc21_rela(struct module *me, u32 *location, Elf_Addr v) -{ - return apply_r_mips_pc_rela(me, location, v, 21); -} - -static int apply_r_mips_pc26_rela(struct module *me, u32 *location, Elf_Addr v) -{ - return apply_r_mips_pc_rela(me, location, v, 26); -} - -static int apply_r_mips_64_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *(Elf_Addr *)location = v; - - return 0; -} - -static int apply_r_mips_higher_rela(struct module *me, u32 *location, - Elf_Addr v) -{ - *location = (*location & 0xffff0000) | - ((((long long) v + 0x80008000LL) >> 32) & 0xffff); - - return 0; -} - -static int apply_r_mips_highest_rela(struct module *me, u32 *location, - Elf_Addr v) -{ - *location = (*location & 0xffff0000) | - ((((long long) v + 0x800080008000LL) >> 48) & 0xffff); - - return 0; -} - -static int (*reloc_handlers_rela[]) (struct module *me, u32 *location, - Elf_Addr v) = { - [R_MIPS_NONE] = apply_r_mips_none, - [R_MIPS_32] = apply_r_mips_32_rela, - [R_MIPS_26] = apply_r_mips_26_rela, - [R_MIPS_HI16] = apply_r_mips_hi16_rela, - [R_MIPS_LO16] = apply_r_mips_lo16_rela, - [R_MIPS_PC16] = apply_r_mips_pc16_rela, - [R_MIPS_64] = apply_r_mips_64_rela, - [R_MIPS_HIGHER] = apply_r_mips_higher_rela, - [R_MIPS_HIGHEST] = apply_r_mips_highest_rela, - [R_MIPS_PC21_S2] = apply_r_mips_pc21_rela, - [R_MIPS_PC26_S2] = apply_r_mips_pc26_rela, -}; - -int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, - unsigned int symindex, unsigned int relsec, - struct module *me) -{ - Elf_Mips_Rela *rel = (void *) sechdrs[relsec].sh_addr; - int (*handler)(struct module *me, u32 *location, Elf_Addr v); - Elf_Sym *sym; - u32 *location; - unsigned int i, type; - Elf_Addr v; - int res; - - pr_debug("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); - - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { - /* This is where to make the change */ - location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr - + rel[i].r_offset; - /* This is the symbol it is referring to */ - sym = (Elf_Sym *)sechdrs[symindex].sh_addr - + ELF_MIPS_R_SYM(rel[i]); - if (sym->st_value >= -MAX_ERRNO) { - /* Ignore unresolved weak symbol */ - if (ELF_ST_BIND(sym->st_info) == STB_WEAK) - continue; - pr_warn("%s: Unknown symbol %s\n", - me->name, strtab + sym->st_name); - return -ENOENT; - } - - type = ELF_MIPS_R_TYPE(rel[i]); - - if (type < ARRAY_SIZE(reloc_handlers_rela)) - handler = reloc_handlers_rela[type]; - else - handler = NULL; - - if (!handler) { - pr_err("%s: Unknown relocation type %u\n", - me->name, type); - return -EINVAL; - } - - v = sym->st_value + rel[i].r_addend; - res = handler(me, location, v); - if (res) - return res; - } - - return 0; -} diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index 50c020c47e54..491605137b03 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -53,22 +53,25 @@ void *module_alloc(unsigned long size) } #endif -int apply_r_mips_none(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_none(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { return 0; } -static int apply_r_mips_32_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_32(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - *location += v; + *location = base + v; return 0; } -static int apply_r_mips_26_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_26(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { if (v % 4) { - pr_err("module %s: dangerous R_MIPS_26 REL relocation\n", + pr_err("module %s: dangerous R_MIPS_26 relocation\n", me->name); return -ENOEXEC; } @@ -80,15 +83,22 @@ static int apply_r_mips_26_rel(struct module *me, u32 *location, Elf_Addr v) } *location = (*location & ~0x03ffffff) | - ((*location + (v >> 2)) & 0x03ffffff); + ((base + (v >> 2)) & 0x03ffffff); return 0; } -static int apply_r_mips_hi16_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_hi16(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { struct mips_hi16 *n; + if (rela) { + *location = (*location & 0xffff0000) | + ((((long long) v + 0x8000LL) >> 16) & 0xffff); + return 0; + } + /* * We cannot relocate this one now because we don't know the value of * the carry we need to add. Save the information, and let LO16 do the @@ -117,12 +127,18 @@ static void free_relocation_chain(struct mips_hi16 *l) } } -static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_lo16(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - unsigned long insnlo = *location; + unsigned long insnlo = base; struct mips_hi16 *l; Elf_Addr val, vallo; + if (rela) { + *location = (*location & 0xffff0000) | (v & 0xffff); + return 0; + } + /* Sign extend the addend we extract from the lo insn. */ vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000; @@ -178,26 +194,26 @@ out_danger: free_relocation_chain(l); me->arch.r_mips_hi16_list = NULL; - pr_err("module %s: dangerous R_MIPS_LO16 REL relocation\n", me->name); + pr_err("module %s: dangerous R_MIPS_LO16 relocation\n", me->name); return -ENOEXEC; } -static int apply_r_mips_pc_rel(struct module *me, u32 *location, Elf_Addr v, - unsigned bits) +static int apply_r_mips_pc(struct module *me, u32 *location, u32 base, + Elf_Addr v, unsigned int bits) { unsigned long mask = GENMASK(bits - 1, 0); unsigned long se_bits; long offset; if (v % 4) { - pr_err("module %s: dangerous R_MIPS_PC%u REL relocation\n", + pr_err("module %s: dangerous R_MIPS_PC%u relocation\n", me->name, bits); return -ENOEXEC; } - /* retrieve & sign extend implicit addend */ - offset = *location & mask; + /* retrieve & sign extend implicit addend if any */ + offset = base & mask; offset |= (offset & BIT(bits - 1)) ? ~mask : 0; offset += ((long)v - (long)location) >> 2; @@ -214,99 +230,192 @@ static int apply_r_mips_pc_rel(struct module *me, u32 *location, Elf_Addr v, return 0; } -static int apply_r_mips_pc16_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_pc16(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) +{ + return apply_r_mips_pc(me, location, base, v, 16); +} + +static int apply_r_mips_pc21(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) +{ + return apply_r_mips_pc(me, location, base, v, 21); +} + +static int apply_r_mips_pc26(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) +{ + return apply_r_mips_pc(me, location, base, v, 26); +} + +static int apply_r_mips_64(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - return apply_r_mips_pc_rel(me, location, v, 16); + if (WARN_ON(!rela)) + return -EINVAL; + + *(Elf_Addr *)location = v; + + return 0; } -static int apply_r_mips_pc21_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_higher(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - return apply_r_mips_pc_rel(me, location, v, 21); + if (WARN_ON(!rela)) + return -EINVAL; + + *location = (*location & 0xffff0000) | + ((((long long)v + 0x80008000LL) >> 32) & 0xffff); + + return 0; } -static int apply_r_mips_pc26_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_highest(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - return apply_r_mips_pc_rel(me, location, v, 26); + if (WARN_ON(!rela)) + return -EINVAL; + + *location = (*location & 0xffff0000) | + ((((long long)v + 0x800080008000LL) >> 48) & 0xffff); + + return 0; } -static int (*reloc_handlers_rel[]) (struct module *me, u32 *location, - Elf_Addr v) = { +/** + * reloc_handler() - Apply a particular relocation to a module + * @me: the module to apply the reloc to + * @location: the address at which the reloc is to be applied + * @base: the existing value at location for REL-style; 0 for RELA-style + * @v: the value of the reloc, with addend for RELA-style + * + * Each implemented reloc_handler function applies a particular type of + * relocation to the module @me. Relocs that may be found in either REL or RELA + * variants can be handled by making use of the @base & @v parameters which are + * set to values which abstract the difference away from the particular reloc + * implementations. + * + * Return: 0 upon success, else -ERRNO + */ +typedef int (*reloc_handler)(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela); + +/* The handlers for known reloc types */ +static reloc_handler reloc_handlers[] = { [R_MIPS_NONE] = apply_r_mips_none, - [R_MIPS_32] = apply_r_mips_32_rel, - [R_MIPS_26] = apply_r_mips_26_rel, - [R_MIPS_HI16] = apply_r_mips_hi16_rel, - [R_MIPS_LO16] = apply_r_mips_lo16_rel, - [R_MIPS_PC16] = apply_r_mips_pc16_rel, - [R_MIPS_PC21_S2] = apply_r_mips_pc21_rel, - [R_MIPS_PC26_S2] = apply_r_mips_pc26_rel, + [R_MIPS_32] = apply_r_mips_32, + [R_MIPS_26] = apply_r_mips_26, + [R_MIPS_HI16] = apply_r_mips_hi16, + [R_MIPS_LO16] = apply_r_mips_lo16, + [R_MIPS_PC16] = apply_r_mips_pc16, + [R_MIPS_64] = apply_r_mips_64, + [R_MIPS_HIGHER] = apply_r_mips_higher, + [R_MIPS_HIGHEST] = apply_r_mips_highest, + [R_MIPS_PC21_S2] = apply_r_mips_pc21, + [R_MIPS_PC26_S2] = apply_r_mips_pc26, }; -int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, - unsigned int symindex, unsigned int relsec, - struct module *me) +static int __apply_relocate(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me, bool rela) { - Elf_Mips_Rel *rel = (void *) sechdrs[relsec].sh_addr; - int (*handler)(struct module *me, u32 *location, Elf_Addr v); + union { + Elf_Mips_Rel *rel; + Elf_Mips_Rela *rela; + } r; + reloc_handler handler; Elf_Sym *sym; - u32 *location; + u32 *location, base; unsigned int i, type; Elf_Addr v; - int res; + int err = 0; + size_t reloc_sz; pr_debug("Applying relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); + r.rel = (void *)sechdrs[relsec].sh_addr; + reloc_sz = rela ? sizeof(*r.rela) : sizeof(*r.rel); me->arch.r_mips_hi16_list = NULL; - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + for (i = 0; i < sechdrs[relsec].sh_size / reloc_sz; i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr - + rel[i].r_offset; + + r.rel->r_offset; /* This is the symbol it is referring to */ sym = (Elf_Sym *)sechdrs[symindex].sh_addr - + ELF_MIPS_R_SYM(rel[i]); + + ELF_MIPS_R_SYM(*r.rel); if (sym->st_value >= -MAX_ERRNO) { /* Ignore unresolved weak symbol */ if (ELF_ST_BIND(sym->st_info) == STB_WEAK) continue; pr_warn("%s: Unknown symbol %s\n", me->name, strtab + sym->st_name); - return -ENOENT; + err = -ENOENT; + goto out; } - type = ELF_MIPS_R_TYPE(rel[i]); - - if (type < ARRAY_SIZE(reloc_handlers_rel)) - handler = reloc_handlers_rel[type]; + type = ELF_MIPS_R_TYPE(*r.rel); + if (type < ARRAY_SIZE(reloc_handlers)) + handler = reloc_handlers[type]; else handler = NULL; if (!handler) { pr_err("%s: Unknown relocation type %u\n", me->name, type); - return -EINVAL; + err = -EINVAL; + goto out; } - v = sym->st_value; - res = handler(me, location, v); - if (res) - return res; + if (rela) { + v = sym->st_value + r.rela->r_addend; + base = 0; + r.rela = &r.rela[1]; + } else { + v = sym->st_value; + base = *location; + r.rel = &r.rel[1]; + } + + err = handler(me, location, base, v, rela); + if (err) + goto out; } +out: /* - * Normally the hi16 list should be deallocated at this point. A + * Normally the hi16 list should be deallocated at this point. A * malformed binary however could contain a series of R_MIPS_HI16 - * relocations not followed by a R_MIPS_LO16 relocation. In that - * case, free up the list and return an error. + * relocations not followed by a R_MIPS_LO16 relocation, or if we hit + * an error processing a reloc we might have gotten here before + * reaching the R_MIPS_LO16. In either case, free up the list and + * return an error. */ if (me->arch.r_mips_hi16_list) { free_relocation_chain(me->arch.r_mips_hi16_list); me->arch.r_mips_hi16_list = NULL; - - return -ENOEXEC; + err = err ?: -ENOEXEC; } - return 0; + return err; +} + +int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + return __apply_relocate(sechdrs, strtab, symindex, relsec, me, false); +} + +#ifdef CONFIG_MODULES_USE_ELF_RELA +int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + return __apply_relocate(sechdrs, strtab, symindex, relsec, me, true); } +#endif /* CONFIG_MODULES_USE_ELF_RELA */ /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_dbetables(unsigned long addr) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index f3e301f95aef..9e6c74bf66c4 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -814,7 +814,7 @@ static const struct mips_perf_event mipsxxcore_event_map2 [PERF_COUNT_HW_BRANCH_MISSES] = { 0x27, CNTR_ODD, T }, }; -static const struct mips_perf_event i6400_event_map[PERF_COUNT_HW_MAX] = { +static const struct mips_perf_event i6x00_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { 0x00, CNTR_EVEN | CNTR_ODD }, [PERF_COUNT_HW_INSTRUCTIONS] = { 0x01, CNTR_EVEN | CNTR_ODD }, /* These only count dcache, not icache */ @@ -1014,7 +1014,7 @@ static const struct mips_perf_event mipsxxcore_cache_map2 }, }; -static const struct mips_perf_event i6400_cache_map +static const struct mips_perf_event i6x00_cache_map [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { @@ -1610,6 +1610,7 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) #endif break; case CPU_I6400: + case CPU_I6500: /* 8-bit event numbers */ base_id = config & 0xff; raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; @@ -1770,8 +1771,13 @@ init_hw_perf_events(void) break; case CPU_I6400: mipspmu.name = "mips/I6400"; - mipspmu.general_event_map = &i6400_event_map; - mipspmu.cache_event_map = &i6400_cache_map; + mipspmu.general_event_map = &i6x00_event_map; + mipspmu.cache_event_map = &i6x00_cache_map; + break; + case CPU_I6500: + mipspmu.name = "mips/I6500"; + mipspmu.general_event_map = &i6x00_event_map; + mipspmu.cache_event_map = &i6x00_cache_map; break; case CPU_1004K: mipspmu.name = "mips/1004K"; diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 4eff2aed7360..70604c753aa4 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -83,7 +83,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) } seq_printf(m, "isa\t\t\t:"); - if (cpu_has_mips_r1) + if (cpu_has_mips_1) seq_printf(m, " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); @@ -109,6 +109,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "ASEs implemented\t:"); if (cpu_has_mips16) seq_printf(m, "%s", " mips16"); + if (cpu_has_mips16e2) seq_printf(m, "%s", " mips16e2"); if (cpu_has_mdmx) seq_printf(m, "%s", " mdmx"); if (cpu_has_mips3d) seq_printf(m, "%s", " mips3d"); if (cpu_has_smartmips) seq_printf(m, "%s", " smartmips"); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 6931fe722a0b..6dd13641a418 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -868,14 +868,39 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) tracehook_report_syscall_entry(regs)) return -1; - if (secure_computing(NULL) == -1) - return -1; +#ifdef CONFIG_SECCOMP + if (unlikely(test_thread_flag(TIF_SECCOMP))) { + int ret, i; + struct seccomp_data sd; + + sd.nr = syscall; + sd.arch = syscall_get_arch(); + for (i = 0; i < 6; i++) { + unsigned long v, r; + + r = mips_get_syscall_arg(&v, current, regs, i); + sd.args[i] = r ? 0 : v; + } + sd.instruction_pointer = KSTK_EIP(current); + + ret = __secure_computing(&sd); + if (ret == -1) + return ret; + } +#endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[2]); audit_syscall_entry(syscall, regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); + + /* + * Negative syscall numbers are mistaken for rejected syscalls, but + * won't have had the return value set appropriately, so we do so now. + */ + if (syscall < 0) + syscall_set_return_value(current, regs, -ENOSYS, 0); return syscall; } @@ -895,7 +920,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->regs[2]); + trace_sys_exit(regs, regs_return_value(regs)); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 80ed68b2c95e..27c2f90eeb21 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -371,7 +371,7 @@ EXPORT(sys_call_table) PTR sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 49765b44aa9b..65d5aeeb9bdb 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -311,7 +311,7 @@ EXPORT(sys_call_table) PTR sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_io_setup /* 5200 */ PTR sys_io_destroy PTR sys_io_getevents diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 90bad2d1b2d3..cbf190ef9e8a 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -302,7 +302,7 @@ EXPORT(sysn32_call_table) PTR compat_sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR compat_sys_io_setup /* 6200 */ PTR sys_io_destroy PTR compat_sys_io_getevents diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 2dd70bd104e1..c30bc520885f 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -371,7 +371,7 @@ EXPORT(sys32_call_table) PTR compat_sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 01d1dbde5fbf..fe3939726765 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -670,6 +670,46 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); +static int __init early_parse_memmap(char *p) +{ + char *oldp; + u64 start_at, mem_size; + + if (!p) + return -EINVAL; + + if (!strncmp(p, "exactmap", 8)) { + pr_err("\"memmap=exactmap\" invalid on MIPS\n"); + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; + + if (*p == '@') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, BOOT_MEM_RAM); + } else if (*p == '#') { + pr_err("\"memmap=nn#ss\" (force ACPI data) invalid on MIPS\n"); + return -EINVAL; + } else if (*p == '$') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, BOOT_MEM_RESERVED); + } else { + pr_err("\"memmap\" invalid format!\n"); + return -EINVAL; + } + + if (*p == '\0') { + usermem = 1; + return 0; + } else + return -EINVAL; +} +early_param("memmap", early_parse_memmap); + #ifdef CONFIG_PROC_VMCORE unsigned long setup_elfcorehdr, setup_elfcorehdr_size; static int __init early_parse_elfcorehdr(char *p) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 36954ddd0b9f..f832e99ad4c3 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -142,9 +142,11 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) /* Warn the user if the CCA prevents multi-core */ ncores = mips_cm_numcores(); - if (cca_unsuitable && ncores > 1) { - pr_warn("Using only one core due to unsuitable CCA 0x%x\n", - cca); + if ((cca_unsuitable || cpu_has_dc_aliases) && ncores > 1) { + pr_warn("Using only one core due to %s%s%s\n", + cca_unsuitable ? "unsuitable CCA" : "", + (cca_unsuitable && cpu_has_dc_aliases) ? " & " : "", + cpu_has_dc_aliases ? "dcache aliasing" : ""); for_each_present_cpu(c) { if (cpu_data[c].core) @@ -488,6 +490,7 @@ static void cps_cpu_die(unsigned int cpu) { unsigned core = cpu_data[cpu].core; unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]); + ktime_t fail_time; unsigned stat; int err; @@ -514,6 +517,7 @@ static void cps_cpu_die(unsigned int cpu) * state, the latter happening when a JTAG probe is connected * in which case the CPC will refuse to power down the core. */ + fail_time = ktime_add_ms(ktime_get(), 2000); do { mips_cm_lock_other(core, 0); mips_cpc_lock_other(core); @@ -521,9 +525,28 @@ static void cps_cpu_die(unsigned int cpu) stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; mips_cpc_unlock_other(); mips_cm_unlock_other(); - } while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 && - stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 && - stat != CPC_Cx_STAT_CONF_SEQSTATE_U2); + + if (stat == CPC_Cx_STAT_CONF_SEQSTATE_D0 || + stat == CPC_Cx_STAT_CONF_SEQSTATE_D2 || + stat == CPC_Cx_STAT_CONF_SEQSTATE_U2) + break; + + /* + * The core ought to have powered down, but didn't & + * now we don't really know what state it's in. It's + * likely that its _pwr_up pin has been wired to logic + * 1 & it powered back up as soon as we powered it + * down... + * + * The best we can do is warn the user & continue in + * the hope that the core is doing nothing harmful & + * might behave properly if we online it later. + */ + if (WARN(ktime_after(ktime_get(), fail_time), + "CPU%u hasn't powered down, seq. state %u\n", + cpu, stat >> CPC_Cx_STAT_CONF_SEQSTATE_SHF)) + break; + } while (1); /* Indicate the core is powered off */ bitmap_clear(core_power, core, 1); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index aba1afb64b62..770d4d1516cb 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -335,6 +335,9 @@ int mips_smp_ipi_free(const struct cpumask *mask) static int __init mips_smp_ipi_init(void) { + if (num_possible_cpus() == 1) + return 0; + mips_smp_ipi_allocate(cpu_possible_mask); call_desc = irq_to_desc(call_virq); diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 1dfa7f5796c7..58c6f634b550 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -29,6 +29,7 @@ #include <linux/sched/task_stack.h> #include <asm/asm.h> +#include <asm/asm-eva.h> #include <asm/branch.h> #include <asm/cachectl.h> #include <asm/cacheflush.h> @@ -131,16 +132,14 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) __asm__ __volatile__ ( " .set "MIPS_ISA_ARCH_LEVEL" \n" " li %[err], 0 \n" - "1: ll %[old], (%[addr]) \n" + "1: \n" + user_ll("%[old]", "(%[addr])") " move %[tmp], %[new] \n" - "2: sc %[tmp], (%[addr]) \n" - " bnez %[tmp], 4f \n" + "2: \n" + user_sc("%[tmp]", "(%[addr])") + " beqz %[tmp], 1b \n" "3: \n" " .insn \n" - " .subsection 2 \n" - "4: b 1b \n" - " .previous \n" - " \n" " .section .fixup,\"ax\" \n" "5: li %[err], %[efault] \n" " j 3b \n" @@ -192,6 +191,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) unreachable(); } +/* + * mips_atomic_set() normally returns directly via syscall_exit potentially + * clobbering static registers, so be sure to preserve them. + */ +save_static_function(sys_sysmips); + SYSCALL_DEFINE3(sysmips, long, cmd, long, arg1, long, arg2) { switch (cmd) { diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index f806ee56e639..5eaf2578ac04 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -939,88 +939,114 @@ static void emulate_load_store_insn(struct pt_regs *regs, * The remaining opcodes are the ones that are really of * interest. */ -#ifdef CONFIG_EVA case spec3_op: - /* - * we can land here only from kernel accessing user memory, - * so we need to "switch" the address limit to user space, so - * address check can work properly. - */ - seg = get_fs(); - set_fs(USER_DS); - switch (insn.spec3_format.func) { - case lhe_op: - if (!access_ok(VERIFY_READ, addr, 2)) { - set_fs(seg); - goto sigbus; - } - LoadHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case lwe_op: - if (!access_ok(VERIFY_READ, addr, 4)) { - set_fs(seg); - goto sigbus; + if (insn.dsp_format.func == lx_op) { + switch (insn.dsp_format.op) { + case lwx_op: + if (!access_ok(VERIFY_READ, addr, 4)) + goto sigbus; + LoadW(addr, value, res); + if (res) + goto fault; + compute_return_epc(regs); + regs->regs[insn.dsp_format.rd] = value; + break; + case lhx_op: + if (!access_ok(VERIFY_READ, addr, 2)) + goto sigbus; + LoadHW(addr, value, res); + if (res) + goto fault; + compute_return_epc(regs); + regs->regs[insn.dsp_format.rd] = value; + break; + default: + goto sigill; } + } +#ifdef CONFIG_EVA + else { + /* + * we can land here only from kernel accessing user + * memory, so we need to "switch" the address limit to + * user space, so that address check can work properly. + */ + seg = get_fs(); + set_fs(USER_DS); + switch (insn.spec3_format.func) { + case lhe_op: + if (!access_ok(VERIFY_READ, addr, 2)) { + set_fs(seg); + goto sigbus; + } + LoadHWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case lwe_op: + if (!access_ok(VERIFY_READ, addr, 4)) { + set_fs(seg); + goto sigbus; + } LoadWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case lhue_op: - if (!access_ok(VERIFY_READ, addr, 2)) { - set_fs(seg); - goto sigbus; - } - LoadHWUE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case she_op: - if (!access_ok(VERIFY_WRITE, addr, 2)) { - set_fs(seg); - goto sigbus; - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; - StoreHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - break; - case swe_op: - if (!access_ok(VERIFY_WRITE, addr, 4)) { - set_fs(seg); - goto sigbus; - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; - StoreWE(addr, value, res); - if (res) { + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case lhue_op: + if (!access_ok(VERIFY_READ, addr, 2)) { + set_fs(seg); + goto sigbus; + } + LoadHWUE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case she_op: + if (!access_ok(VERIFY_WRITE, addr, 2)) { + set_fs(seg); + goto sigbus; + } + compute_return_epc(regs); + value = regs->regs[insn.spec3_format.rt]; + StoreHWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + break; + case swe_op: + if (!access_ok(VERIFY_WRITE, addr, 4)) { + set_fs(seg); + goto sigbus; + } + compute_return_epc(regs); + value = regs->regs[insn.spec3_format.rt]; + StoreWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + break; + default: set_fs(seg); - goto fault; + goto sigill; } - break; - default: set_fs(seg); - goto sigill; } - set_fs(seg); - break; #endif + break; case lh_op: if (!access_ok(VERIFY_READ, addr, 2)) goto sigbus; @@ -1984,6 +2010,8 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) u16 __user *pc16; unsigned long origpc; union mips16e_instruction mips16inst, oldinst; + unsigned int opcode; + int extended = 0; origpc = regs->cp0_epc; orig31 = regs->regs[31]; @@ -1996,6 +2024,7 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) /* skip EXTEND instruction */ if (mips16inst.ri.opcode == MIPS16e_extend_op) { + extended = 1; pc16++; __get_user(mips16inst.full, pc16); } else if (delay_slot(regs)) { @@ -2008,7 +2037,8 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) goto sigbus; } - switch (mips16inst.ri.opcode) { + opcode = mips16inst.ri.opcode; + switch (opcode) { case MIPS16e_i64_op: /* I64 or RI64 instruction */ switch (mips16inst.i64.func) { /* I64/RI64 func field check */ case MIPS16e_ldpc_func: @@ -2028,9 +2058,40 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) goto sigbus; case MIPS16e_swsp_op: + reg = reg16to32[mips16inst.ri.rx]; + if (extended && cpu_has_mips16e2) + switch (mips16inst.ri.imm >> 5) { + case 0: /* SWSP */ + case 1: /* SWGP */ + break; + case 2: /* SHGP */ + opcode = MIPS16e_sh_op; + break; + default: + goto sigbus; + } + break; + case MIPS16e_lwpc_op: + reg = reg16to32[mips16inst.ri.rx]; + break; + case MIPS16e_lwsp_op: reg = reg16to32[mips16inst.ri.rx]; + if (extended && cpu_has_mips16e2) + switch (mips16inst.ri.imm >> 5) { + case 0: /* LWSP */ + case 1: /* LWGP */ + break; + case 2: /* LHGP */ + opcode = MIPS16e_lh_op; + break; + case 4: /* LHUGP */ + opcode = MIPS16e_lhu_op; + break; + default: + goto sigbus; + } break; case MIPS16e_i8_op: @@ -2044,7 +2105,7 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) break; } - switch (mips16inst.ri.opcode) { + switch (opcode) { case MIPS16e_lb_op: case MIPS16e_lbu_op: diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S index 3114a2ed1f4e..03e3304d6ae5 100644 --- a/arch/mips/lib/memcpy.S +++ b/arch/mips/lib/memcpy.S @@ -28,6 +28,9 @@ #ifdef CONFIG_MIPS_MALTA #undef CONFIG_CPU_HAS_PREFETCH #endif +#ifdef CONFIG_CPU_MIPSR6 +#undef CONFIG_CPU_HAS_PREFETCH +#endif #include <asm/asm.h> #include <asm/asm-offsets.h> diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c index 6afa21850267..1e8a955ae5a8 100644 --- a/arch/mips/loongson64/common/env.c +++ b/arch/mips/loongson64/common/env.c @@ -90,7 +90,9 @@ void __init prom_init_env(void) cpu_clock_freq = ecpu->cpu_clock_freq; loongson_sysconf.cputype = ecpu->cputype; - if (ecpu->cputype == Loongson_3A) { + switch (ecpu->cputype) { + case Legacy_3A: + case Loongson_3A: loongson_sysconf.cores_per_node = 4; loongson_sysconf.cores_per_package = 4; smp_group[0] = 0x900000003ff01000; @@ -111,7 +113,9 @@ void __init prom_init_env(void) loongson_freqctrl[3] = 0x900030001fe001d0; loongson_sysconf.ht_control_base = 0x90000EFDFB000000; loongson_sysconf.workarounds = WORKAROUND_CPUFREQ; - } else if (ecpu->cputype == Loongson_3B) { + break; + case Legacy_3B: + case Loongson_3B: loongson_sysconf.cores_per_node = 4; /* One chip has 2 nodes */ loongson_sysconf.cores_per_package = 8; smp_group[0] = 0x900000003ff01000; @@ -132,7 +136,8 @@ void __init prom_init_env(void) loongson_freqctrl[3] = 0x900060001fe001d0; loongson_sysconf.ht_control_base = 0x90001EFDFB000000; loongson_sysconf.workarounds = WORKAROUND_CPUHOTPLUG; - } else { + break; + default: loongson_sysconf.cores_per_node = 1; loongson_sysconf.cores_per_package = 1; loongson_chipcfg[0] = 0x900000001fe00180; @@ -193,6 +198,7 @@ void __init prom_init_env(void) break; case PRID_REV_LOONGSON3A_R1: case PRID_REV_LOONGSON3A_R2: + case PRID_REV_LOONGSON3A_R3: cpu_clock_freq = 900000000; break; case PRID_REV_LOONGSON3B_R1: diff --git a/arch/mips/loongson64/common/init.c b/arch/mips/loongson64/common/init.c index 9b987fe98b5b..6ef17120722f 100644 --- a/arch/mips/loongson64/common/init.c +++ b/arch/mips/loongson64/common/init.c @@ -10,13 +10,25 @@ #include <linux/bootmem.h> #include <asm/bootinfo.h> +#include <asm/traps.h> #include <asm/smp-ops.h> +#include <asm/cacheflush.h> #include <loongson.h> /* Loongson CPU address windows config space base address */ unsigned long __maybe_unused _loongson_addrwincfg_base; +static void __init mips_nmi_setup(void) +{ + void *base; + extern char except_vec_nmi; + + base = (void *)(CAC_BASE + 0x380); + memcpy(base, &except_vec_nmi, 0x80); + flush_icache_range((unsigned long)base, (unsigned long)base + 0x80); +} + void __init prom_init(void) { #ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG @@ -40,6 +52,7 @@ void __init prom_init(void) /*init the uart base address */ prom_init_uart_base(); register_smp_ops(&loongson3_smp_ops); + board_nmi_handler_setup = mips_nmi_setup; } void __init prom_free_prom_memory(void) diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/loongson-3/irq.c index 548f759454dc..7202e52cd046 100644 --- a/arch/mips/loongson64/loongson-3/irq.c +++ b/arch/mips/loongson64/loongson-3/irq.c @@ -9,18 +9,69 @@ #include "smp.h" +extern void loongson3_send_irq_by_ipi(int cpu, int irqs); + +unsigned int irq_cpu[16] = {[0 ... 15] = -1}; unsigned int ht_irq[] = {0, 1, 3, 4, 5, 6, 7, 8, 12, 14, 15}; +unsigned int local_irq = 1<<0 | 1<<1 | 1<<2 | 1<<7 | 1<<8 | 1<<12; + +int plat_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, + bool force) +{ + unsigned int cpu; + struct cpumask new_affinity; + + /* I/O devices are connected on package-0 */ + cpumask_copy(&new_affinity, affinity); + for_each_cpu(cpu, affinity) + if (cpu_data[cpu].package > 0) + cpumask_clear_cpu(cpu, &new_affinity); + + if (cpumask_empty(&new_affinity)) + return -EINVAL; + + cpumask_copy(d->common->affinity, &new_affinity); + + return IRQ_SET_MASK_OK_NOCOPY; +} static void ht_irqdispatch(void) { unsigned int i, irq; + struct irq_data *irqd; + struct cpumask affinity; irq = LOONGSON_HT1_INT_VECTOR(0); LOONGSON_HT1_INT_VECTOR(0) = irq; /* Acknowledge the IRQs */ for (i = 0; i < ARRAY_SIZE(ht_irq); i++) { - if (irq & (0x1 << ht_irq[i])) + if (!(irq & (0x1 << ht_irq[i]))) + continue; + + /* handled by local core */ + if (local_irq & (0x1 << ht_irq[i])) { do_IRQ(ht_irq[i]); + continue; + } + + irqd = irq_get_irq_data(ht_irq[i]); + cpumask_and(&affinity, irqd->common->affinity, cpu_active_mask); + if (cpumask_empty(&affinity)) { + do_IRQ(ht_irq[i]); + continue; + } + + irq_cpu[ht_irq[i]] = cpumask_next(irq_cpu[ht_irq[i]], &affinity); + if (irq_cpu[ht_irq[i]] >= nr_cpu_ids) + irq_cpu[ht_irq[i]] = cpumask_first(&affinity); + + if (irq_cpu[ht_irq[i]] == 0) { + do_IRQ(ht_irq[i]); + continue; + } + + /* balanced by other cores */ + loongson3_send_irq_by_ipi(irq_cpu[ht_irq[i]], (0x1 << ht_irq[i])); } } @@ -120,11 +171,16 @@ void irq_router_init(void) void __init mach_init_irq(void) { + struct irq_chip *chip; + clear_c0_status(ST0_IM | ST0_BEV); irq_router_init(); mips_cpu_irq_init(); init_i8259_irqs(); + chip = irq_get_chip(I8259A_IRQ_BASE); + chip->irq_set_affinity = plat_set_irq_affinity; + irq_set_chip_and_handler(LOONGSON_UART_IRQ, &loongson_irq_chip, handle_level_irq); diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 64659fc73940..b7a355c3c408 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -254,13 +254,21 @@ loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action) loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(i)]); } +#define IPI_IRQ_OFFSET 6 + +void loongson3_send_irq_by_ipi(int cpu, int irqs) +{ + loongson3_ipi_write32(irqs << IPI_IRQ_OFFSET, ipi_set0_regs[cpu_logical_map(cpu)]); +} + void loongson3_ipi_interrupt(struct pt_regs *regs) { int i, cpu = smp_processor_id(); - unsigned int action, c0count; + unsigned int action, c0count, irqs; /* Load the ipi register to figure out what we're supposed to do */ action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]); + irqs = action >> IPI_IRQ_OFFSET; /* Clear the ipi register to clear the interrupt */ loongson3_ipi_write32((u32)action, ipi_clear0_regs[cpu_logical_map(cpu)]); @@ -282,6 +290,14 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) core0_c0count[i] = c0count; __wbflush(); /* Let others see the result ASAP */ } + + if (irqs) { + int irq; + while ((irq = ffs(irqs))) { + do_IRQ(irq-1); + irqs &= ~(1<<(irq-1)); + } + } } #define MAX_LOOPS 800 @@ -503,7 +519,7 @@ static void loongson3a_r1_play_dead(int *state_addr) : "a1"); } -static void loongson3a_r2_play_dead(int *state_addr) +static void loongson3a_r2r3_play_dead(int *state_addr) { register int val; register long cpuid, core, node, count; @@ -664,8 +680,9 @@ void play_dead(void) (void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead); break; case PRID_REV_LOONGSON3A_R2: + case PRID_REV_LOONGSON3A_R3: play_dead_at_ckseg1 = - (void *)CKSEG1ADDR((unsigned long)loongson3a_r2_play_dead); + (void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead); break; case PRID_REV_LOONGSON3B_R1: case PRID_REV_LOONGSON3B_R2: diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index f12fde10c8ad..f08a7b4facb9 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -1142,7 +1142,7 @@ emul: case mfhc_op: if (!cpu_has_mips_r2_r6) - goto sigill; + return SIGILL; /* copregister rd -> gpr[rt] */ if (MIPSInst_RT(ir) != 0) { @@ -1153,7 +1153,7 @@ emul: case mthc_op: if (!cpu_has_mips_r2_r6) - goto sigill; + return SIGILL; /* copregister rd <- gpr[rt] */ SITOHREG(xcp->regs[MIPSInst_RT(ir)], MIPSInst_RD(ir)); @@ -1376,7 +1376,6 @@ branch_common: xcp->regs[MIPSInst_RS(ir)]; break; default: -sigill: return SIGILL; } @@ -2524,6 +2523,35 @@ dcopuop: return 0; } +/* + * Emulate FPU instructions. + * + * If we use FPU hardware, then we have been typically called to handle + * an unimplemented operation, such as where an operand is a NaN or + * denormalized. In that case exit the emulation loop after a single + * iteration so as to let hardware execute any subsequent instructions. + * + * If we have no FPU hardware or it has been disabled, then continue + * emulating floating-point instructions until one of these conditions + * has occurred: + * + * - a non-FPU instruction has been encountered, + * + * - an attempt to emulate has ended with a signal, + * + * - the ISA mode has been switched. + * + * We need to terminate the emulation loop if we got switched to the + * MIPS16 mode, whether supported or not, so that we do not attempt + * to emulate a MIPS16 instruction as a regular MIPS FPU instruction. + * Similarly if we got switched to the microMIPS mode and only the + * regular MIPS mode is supported, so that we do not attempt to emulate + * a microMIPS instruction as a regular MIPS FPU instruction. Or if + * we got switched to the regular MIPS mode and only the microMIPS mode + * is supported, so that we do not attempt to emulate a regular MIPS + * instruction that should cause an Address Error exception instead. + * For simplicity we always terminate upon an ISA mode switch. + */ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr) { @@ -2609,6 +2637,15 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; if (sig) break; + /* + * We have to check for the ISA bit explicitly here, + * because `get_isa16_mode' may return 0 if support + * for code compression has been globally disabled, + * or otherwise we may produce the wrong signal or + * even proceed successfully where we must not. + */ + if ((xcp->cp0_epc ^ prevepc) & 0x1) + break; cond_resched(); } while (xcp->cp0_epc > prevepc); diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 3fe99cb271a9..81d6a15c93d0 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1453,6 +1453,7 @@ static void probe_pcache(void) case CPU_20KC: case CPU_25KF: case CPU_I6400: + case CPU_I6500: case CPU_SB1: case CPU_SB1A: case CPU_XLR: @@ -1512,6 +1513,7 @@ static void probe_pcache(void) case CPU_ALCHEMY: case CPU_I6400: + case CPU_I6500: c->icache.flags |= MIPS_CACHE_IC_F_DC; break; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index ed1c5297547a..5aadc69c8ce3 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -153,8 +153,7 @@ static int scratchpad_offset(int i) */ static int m4kc_tlbp_war(void) { - return (current_cpu_data.processor_id & 0xffff00) == - (PRID_COMP_MIPS | PRID_IMP_4KC); + return current_cpu_type() == CPU_4KC; } /* Handle labels (which must be positive integers). */ @@ -2015,6 +2014,26 @@ static void build_r3000_tlb_modify_handler(void) } #endif /* CONFIG_MIPS_PGD_C0_CONTEXT */ +static bool cpu_has_tlbex_tlbp_race(void) +{ + /* + * When a Hardware Table Walker is running it can replace TLB entries + * at any time, leading to a race between it & the CPU. + */ + if (cpu_has_htw) + return true; + + /* + * If the CPU shares FTLB RAM with its siblings then our entry may be + * replaced at any time by a sibling performing a write to the FTLB. + */ + if (cpu_has_shared_ftlb_ram) + return true; + + /* In all other cases there ought to be no race condition to handle */ + return false; +} + /* * R4000 style TLB load/store/modify handlers. */ @@ -2051,7 +2070,7 @@ build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l, iPTE_LW(p, wr.r1, wr.r2); /* get even pte */ if (!m4kc_tlbp_war()) { build_tlb_probe_entry(p); - if (cpu_has_htw) { + if (cpu_has_tlbex_tlbp_race()) { /* race condition happens, leaving */ uasm_i_ehb(p); uasm_i_mfc0(p, wr.r3, C0_INDEX); @@ -2125,6 +2144,14 @@ static void build_r4000_tlb_load_handler(void) } uasm_i_nop(&p); + /* + * Warn if something may race with us & replace the TLB entry + * before we read it here. Everything with such races should + * also have dedicated RiXi exception handlers, so this + * shouldn't be hit. + */ + WARN(cpu_has_tlbex_tlbp_race(), "Unhandled race in RiXi path"); + uasm_i_tlbr(&p); switch (current_cpu_type()) { @@ -2192,6 +2219,14 @@ static void build_r4000_tlb_load_handler(void) } uasm_i_nop(&p); + /* + * Warn if something may race with us & replace the TLB entry + * before we read it here. Everything with such races should + * also have dedicated RiXi exception handlers, so this + * shouldn't be hit. + */ + WARN(cpu_has_tlbex_tlbp_race(), "Unhandled race in RiXi path"); + uasm_i_tlbr(&p); switch (current_cpu_type()) { diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c index 277cf52d80e1..c28ff53c8da0 100644 --- a/arch/mips/mm/uasm-micromips.c +++ b/arch/mips/mm/uasm-micromips.c @@ -40,93 +40,92 @@ #include "uasm.c" -static struct insn insn_table_MM[] = { - { insn_addu, M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD }, - { insn_addiu, M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_and, M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD }, - { insn_andi, M(mm_andi32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, - { insn_beq, M(mm_beq32_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beql, 0, 0 }, - { insn_bgez, M(mm_pool32i_op, mm_bgez_op, 0, 0, 0, 0), RS | BIMM }, - { insn_bgezl, 0, 0 }, - { insn_bltz, M(mm_pool32i_op, mm_bltz_op, 0, 0, 0, 0), RS | BIMM }, - { insn_bltzl, 0, 0 }, - { insn_bne, M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM }, - { insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM }, - { insn_cfc1, M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS }, - { insn_cfcmsa, M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE }, - { insn_ctc1, M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS }, - { insn_ctcmsa, M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE }, - { insn_daddu, 0, 0 }, - { insn_daddiu, 0, 0 }, - { insn_di, M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS }, - { insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS }, - { insn_dmfc0, 0, 0 }, - { insn_dmtc0, 0, 0 }, - { insn_dsll, 0, 0 }, - { insn_dsll32, 0, 0 }, - { insn_dsra, 0, 0 }, - { insn_dsrl, 0, 0 }, - { insn_dsrl32, 0, 0 }, - { insn_drotr, 0, 0 }, - { insn_drotr32, 0, 0 }, - { insn_dsubu, 0, 0 }, - { insn_eret, M(mm_pool32a_op, 0, 0, 0, mm_eret_op, mm_pool32axf_op), 0 }, - { insn_ins, M(mm_pool32a_op, 0, 0, 0, 0, mm_ins_op), RT | RS | RD | RE }, - { insn_ext, M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE }, - { insn_j, M(mm_j32_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jal, M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jalr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS }, - { insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS }, - { insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_ld, 0, 0 }, - { insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM }, - { insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM }, - { insn_lld, 0, 0 }, - { insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM }, - { insn_lw, M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_mfc0, M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD }, - { insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS }, - { insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS }, - { insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD }, - { insn_mthi, M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS }, - { insn_mtlo, M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS }, - { insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD }, - { insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD }, - { insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, - { insn_pref, M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM }, - { insn_rfe, 0, 0 }, - { insn_sc, M(mm_pool32c_op, 0, 0, (mm_sc_func << 1), 0, 0), RT | RS | SIMM }, - { insn_scd, 0, 0 }, - { insn_sd, 0, 0 }, - { insn_sll, M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD }, - { insn_sllv, M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD }, - { insn_slt, M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD }, - { insn_sltiu, M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_sltu, M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD }, - { insn_sra, M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD }, - { insn_srl, M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD }, - { insn_srlv, M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD }, - { insn_rotr, M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD }, - { insn_subu, M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD }, - { insn_sw, M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_sync, M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS }, - { insn_tlbp, M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0 }, - { insn_tlbr, M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0 }, - { insn_tlbwi, M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0 }, - { insn_tlbwr, M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0 }, - { insn_wait, M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM }, - { insn_wsbh, M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS }, - { insn_xor, M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD }, - { insn_xori, M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, - { insn_dins, 0, 0 }, - { insn_dinsm, 0, 0 }, - { insn_syscall, M(mm_pool32a_op, 0, 0, 0, mm_syscall_op, mm_pool32axf_op), SCIMM}, - { insn_bbit0, 0, 0 }, - { insn_bbit1, 0, 0 }, - { insn_lwx, 0, 0 }, - { insn_ldx, 0, 0 }, - { insn_invalid, 0, 0 } +static const struct insn const insn_table_MM[insn_invalid] = { + [insn_addu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD}, + [insn_addiu] = {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_and] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD}, + [insn_andi] = {M(mm_andi32_op, 0, 0, 0, 0, 0), RT | RS | UIMM}, + [insn_beq] = {M(mm_beq32_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_beql] = {0, 0}, + [insn_bgez] = {M(mm_pool32i_op, mm_bgez_op, 0, 0, 0, 0), RS | BIMM}, + [insn_bgezl] = {0, 0}, + [insn_bltz] = {M(mm_pool32i_op, mm_bltz_op, 0, 0, 0, 0), RS | BIMM}, + [insn_bltzl] = {0, 0}, + [insn_bne] = {M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM}, + [insn_cache] = {M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM}, + [insn_cfc1] = {M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS}, + [insn_cfcmsa] = {M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE}, + [insn_ctc1] = {M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS}, + [insn_ctcmsa] = {M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE}, + [insn_daddu] = {0, 0}, + [insn_daddiu] = {0, 0}, + [insn_di] = {M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS}, + [insn_divu] = {M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS}, + [insn_dmfc0] = {0, 0}, + [insn_dmtc0] = {0, 0}, + [insn_dsll] = {0, 0}, + [insn_dsll32] = {0, 0}, + [insn_dsra] = {0, 0}, + [insn_dsrl] = {0, 0}, + [insn_dsrl32] = {0, 0}, + [insn_drotr] = {0, 0}, + [insn_drotr32] = {0, 0}, + [insn_dsubu] = {0, 0}, + [insn_eret] = {M(mm_pool32a_op, 0, 0, 0, mm_eret_op, mm_pool32axf_op), 0}, + [insn_ins] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_ins_op), RT | RS | RD | RE}, + [insn_ext] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE}, + [insn_j] = {M(mm_j32_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jal] = {M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jalr] = {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS}, + [insn_jr] = {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS}, + [insn_lb] = {M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_ld] = {0, 0}, + [insn_lh] = {M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM}, + [insn_ll] = {M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM}, + [insn_lld] = {0, 0}, + [insn_lui] = {M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM}, + [insn_lw] = {M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_mfc0] = {M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD}, + [insn_mfhi] = {M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS}, + [insn_mflo] = {M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS}, + [insn_mtc0] = {M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD}, + [insn_mthi] = {M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS}, + [insn_mtlo] = {M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS}, + [insn_mul] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD}, + [insn_or] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD}, + [insn_ori] = {M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM}, + [insn_pref] = {M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM}, + [insn_rfe] = {0, 0}, + [insn_sc] = {M(mm_pool32c_op, 0, 0, (mm_sc_func << 1), 0, 0), RT | RS | SIMM}, + [insn_scd] = {0, 0}, + [insn_sd] = {0, 0}, + [insn_sll] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD}, + [insn_sllv] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD}, + [insn_slt] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD}, + [insn_sltiu] = {M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_sltu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD}, + [insn_sra] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD}, + [insn_srl] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD}, + [insn_srlv] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD}, + [insn_rotr] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD}, + [insn_subu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD}, + [insn_sw] = {M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_sync] = {M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS}, + [insn_tlbp] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0}, + [insn_tlbr] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0}, + [insn_tlbwi] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0}, + [insn_tlbwr] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0}, + [insn_wait] = {M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM}, + [insn_wsbh] = {M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS}, + [insn_xor] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD}, + [insn_xori] = {M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM}, + [insn_dins] = {0, 0}, + [insn_dinsm] = {0, 0}, + [insn_syscall] = {M(mm_pool32a_op, 0, 0, 0, mm_syscall_op, mm_pool32axf_op), SCIMM}, + [insn_bbit0] = {0, 0}, + [insn_bbit1] = {0, 0}, + [insn_lwx] = {0, 0}, + [insn_ldx] = {0, 0}, }; #undef M @@ -156,20 +155,17 @@ static inline u32 build_jimm(u32 arg) */ static void build_insn(u32 **buf, enum opcode opc, ...) { - struct insn *ip = NULL; - unsigned int i; + const struct insn *ip; va_list ap; u32 op; - for (i = 0; insn_table_MM[i].opcode != insn_invalid; i++) - if (insn_table_MM[i].opcode == opc) { - ip = &insn_table_MM[i]; - break; - } - - if (!ip || (opc == insn_daddiu && r4k_daddiu_bug())) + if (opc < 0 || opc >= insn_invalid || + (opc == insn_daddiu && r4k_daddiu_bug()) || + (insn_table_MM[opc].match == 0 && insn_table_MM[opc].fields == 0)) panic("Unsupported Micro-assembler instruction %d", opc); + ip = &insn_table_MM[opc]; + op = ip->match; va_start(ap, opc); if (ip->fields & RS) { diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index 2277499fe6ae..3f74f6c1f065 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -48,126 +48,145 @@ #include "uasm.c" -static struct insn insn_table[] = { - { insn_addiu, M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_addu, M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD }, - { insn_andi, M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_and, M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD }, - { insn_bbit0, M(lwc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_bbit1, M(swc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beql, M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beq, M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_bgezl, M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM }, - { insn_bgez, M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM }, - { insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM }, - { insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM }, - { insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, +static const struct insn const insn_table[insn_invalid] = { + [insn_addiu] = {M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_addu] = {M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD}, + [insn_and] = {M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD}, + [insn_andi] = {M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, + [insn_bbit0] = {M(lwc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_bbit1] = {M(swc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_beq] = {M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_beql] = {M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_bgez] = {M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM}, + [insn_bgezl] = {M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM}, + [insn_bgtz] = {M(bgtz_op, 0, 0, 0, 0, 0), RS | BIMM}, + [insn_blez] = {M(blez_op, 0, 0, 0, 0, 0), RS | BIMM}, + [insn_bltz] = {M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM}, + [insn_bltzl] = {M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM}, + [insn_bne] = {M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_break] = {M(spec_op, 0, 0, 0, 0, break_op), SCIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_cache] = {M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_cache, M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, + [insn_cache] = {M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9}, #endif - { insn_cfc1, M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD }, - { insn_cfcmsa, M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE }, - { insn_ctc1, M(cop1_op, ctc_op, 0, 0, 0, 0), RT | RD }, - { insn_ctcmsa, M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE }, - { insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD }, - { insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE }, - { insn_di, M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT }, - { insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE }, - { insn_divu, M(spec_op, 0, 0, 0, 0, divu_op), RS | RT }, - { insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_drotr32, M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE }, - { insn_drotr, M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE }, - { insn_dsll32, M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE }, - { insn_dsll, M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE }, - { insn_dsra, M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE }, - { insn_dsrl32, M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE }, - { insn_dsrl, M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE }, - { insn_dsubu, M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD }, - { insn_eret, M(cop0_op, cop_op, 0, 0, 0, eret_op), 0 }, - { insn_ext, M(spec3_op, 0, 0, 0, 0, ext_op), RS | RT | RD | RE }, - { insn_ins, M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE }, - { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jal, M(jal_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jalr, M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD }, - { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, + [insn_cfc1] = {M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD}, + [insn_cfcmsa] = {M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE}, + [insn_ctc1] = {M(cop1_op, ctc_op, 0, 0, 0, 0), RT | RD}, + [insn_ctcmsa] = {M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE}, + [insn_daddiu] = {M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_daddu] = {M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD}, + [insn_ddivu] = {M(spec_op, 0, 0, 0, 0, ddivu_op), RS | RT}, + [insn_di] = {M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT}, + [insn_dins] = {M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE}, + [insn_dinsm] = {M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE}, + [insn_dinsu] = {M(spec3_op, 0, 0, 0, 0, dinsu_op), RS | RT | RD | RE}, + [insn_divu] = {M(spec_op, 0, 0, 0, 0, divu_op), RS | RT}, + [insn_dmfc0] = {M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_dmtc0] = {M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_dmultu] = {M(spec_op, 0, 0, 0, 0, dmultu_op), RS | RT}, + [insn_drotr] = {M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE}, + [insn_drotr32] = {M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE}, + [insn_dsbh] = {M(spec3_op, 0, 0, 0, dsbh_op, dbshfl_op), RT | RD}, + [insn_dshd] = {M(spec3_op, 0, 0, 0, dshd_op, dbshfl_op), RT | RD}, + [insn_dsll] = {M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE}, + [insn_dsll32] = {M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE}, + [insn_dsllv] = {M(spec_op, 0, 0, 0, 0, dsllv_op), RS | RT | RD}, + [insn_dsra] = {M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE}, + [insn_dsra32] = {M(spec_op, 0, 0, 0, 0, dsra32_op), RT | RD | RE}, + [insn_dsrav] = {M(spec_op, 0, 0, 0, 0, dsrav_op), RS | RT | RD}, + [insn_dsrl] = {M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE}, + [insn_dsrl32] = {M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE}, + [insn_dsrlv] = {M(spec_op, 0, 0, 0, 0, dsrlv_op), RS | RT | RD}, + [insn_dsubu] = {M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD}, + [insn_eret] = {M(cop0_op, cop_op, 0, 0, 0, eret_op), 0}, + [insn_ext] = {M(spec3_op, 0, 0, 0, 0, ext_op), RS | RT | RD | RE}, + [insn_ins] = {M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE}, + [insn_j] = {M(j_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jal] = {M(jal_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jalr] = {M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD}, #ifndef CONFIG_CPU_MIPSR6 - { insn_jr, M(spec_op, 0, 0, 0, 0, jr_op), RS }, + [insn_jr] = {M(spec_op, 0, 0, 0, 0, jr_op), RS}, #else - { insn_jr, M(spec_op, 0, 0, 0, 0, jalr_op), RS }, + [insn_jr] = {M(spec_op, 0, 0, 0, 0, jalr_op), RS}, #endif - { insn_lb, M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ld, M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD }, - { insn_lh, M(lh_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_lhu, M(lhu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_lb] = {M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lbu] = {M(lbu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_ld] = {M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lddir] = {M(lwc2_op, 0, 0, 0, lddir_op, mult_op), RS | RT | RD}, + [insn_ldpte] = {M(lwc2_op, 0, 0, 0, ldpte_op, mult_op), RS | RD}, + [insn_ldx] = {M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD}, + [insn_lh] = {M(lh_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lhu] = {M(lhu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_lld, M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ll, M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_ll] = {M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lld] = {M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_lld, M6(spec3_op, 0, 0, 0, lld6_op), RS | RT | SIMM9 }, - { insn_ll, M6(spec3_op, 0, 0, 0, ll6_op), RS | RT | SIMM9 }, + [insn_ll] = {M6(spec3_op, 0, 0, 0, ll6_op), RS | RT | SIMM9}, + [insn_lld] = {M6(spec3_op, 0, 0, 0, lld6_op), RS | RT | SIMM9}, #endif - { insn_lui, M(lui_op, 0, 0, 0, 0, 0), RT | SIMM }, - { insn_lw, M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD }, - { insn_mfc0, M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mfhc0, M(cop0_op, mfhc0_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mfhi, M(spec_op, 0, 0, 0, 0, mfhi_op), RD }, - { insn_mflo, M(spec_op, 0, 0, 0, 0, mflo_op), RD }, - { insn_mtc0, M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mthc0, M(cop0_op, mthc0_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mthi, M(spec_op, 0, 0, 0, 0, mthi_op), RS }, - { insn_mtlo, M(spec_op, 0, 0, 0, 0, mtlo_op), RS }, + [insn_lui] = {M(lui_op, 0, 0, 0, 0, 0), RT | SIMM}, + [insn_lw] = {M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lwu] = {M(lwu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lwx] = {M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD}, + [insn_mfc0] = {M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mfhc0] = {M(cop0_op, mfhc0_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mfhi] = {M(spec_op, 0, 0, 0, 0, mfhi_op), RD}, + [insn_mflo] = {M(spec_op, 0, 0, 0, 0, mflo_op), RD}, + [insn_movn] = {M(spec_op, 0, 0, 0, 0, movn_op), RS | RT | RD}, + [insn_movz] = {M(spec_op, 0, 0, 0, 0, movz_op), RS | RT | RD}, + [insn_mtc0] = {M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mthc0] = {M(cop0_op, mthc0_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mthi] = {M(spec_op, 0, 0, 0, 0, mthi_op), RS}, + [insn_mtlo] = {M(spec_op, 0, 0, 0, 0, mtlo_op), RS}, #ifndef CONFIG_CPU_MIPSR6 - { insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD}, + [insn_mul] = {M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD}, #else - { insn_mul, M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD}, + [insn_mul] = {M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD}, #endif - { insn_ori, M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_or, M(spec_op, 0, 0, 0, 0, or_op), RS | RT | RD }, + [insn_multu] = {M(spec_op, 0, 0, 0, 0, multu_op), RS | RT}, + [insn_nor] = {M(spec_op, 0, 0, 0, 0, nor_op), RS | RT | RD}, + [insn_or] = {M(spec_op, 0, 0, 0, 0, or_op), RS | RT | RD}, + [insn_ori] = {M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_pref, M(pref_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_pref] = {M(pref_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_pref, M6(spec3_op, 0, 0, 0, pref6_op), RS | RT | SIMM9 }, + [insn_pref] = {M6(spec3_op, 0, 0, 0, pref6_op), RS | RT | SIMM9}, #endif - { insn_rfe, M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0 }, - { insn_rotr, M(spec_op, 1, 0, 0, 0, srl_op), RT | RD | RE }, + [insn_rfe] = {M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0}, + [insn_rotr] = {M(spec_op, 1, 0, 0, 0, srl_op), RT | RD | RE}, + [insn_sb] = {M(sb_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_scd, M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sc, M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_sc] = {M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_scd] = {M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_scd, M6(spec3_op, 0, 0, 0, scd6_op), RS | RT | SIMM9 }, - { insn_sc, M6(spec3_op, 0, 0, 0, sc6_op), RS | RT | SIMM9 }, + [insn_sc] = {M6(spec3_op, 0, 0, 0, sc6_op), RS | RT | SIMM9}, + [insn_scd] = {M6(spec3_op, 0, 0, 0, scd6_op), RS | RT | SIMM9}, #endif - { insn_sd, M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sll, M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE }, - { insn_sllv, M(spec_op, 0, 0, 0, 0, sllv_op), RS | RT | RD }, - { insn_slt, M(spec_op, 0, 0, 0, 0, slt_op), RS | RT | RD }, - { insn_sltiu, M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sltu, M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD }, - { insn_sra, M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE }, - { insn_srl, M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE }, - { insn_srlv, M(spec_op, 0, 0, 0, 0, srlv_op), RS | RT | RD }, - { insn_subu, M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD }, - { insn_sw, M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sync, M(spec_op, 0, 0, 0, 0, sync_op), RE }, - { insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM}, - { insn_tlbp, M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0 }, - { insn_tlbr, M(cop0_op, cop_op, 0, 0, 0, tlbr_op), 0 }, - { insn_tlbwi, M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0 }, - { insn_tlbwr, M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0 }, - { insn_wait, M(cop0_op, cop_op, 0, 0, 0, wait_op), SCIMM }, - { insn_wsbh, M(spec3_op, 0, 0, 0, wsbh_op, bshfl_op), RT | RD }, - { insn_xori, M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_xor, M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD }, - { insn_yield, M(spec3_op, 0, 0, 0, 0, yield_op), RS | RD }, - { insn_ldpte, M(lwc2_op, 0, 0, 0, ldpte_op, mult_op), RS | RD }, - { insn_lddir, M(lwc2_op, 0, 0, 0, lddir_op, mult_op), RS | RT | RD }, - { insn_invalid, 0, 0 } + [insn_sd] = {M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sh] = {M(sh_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sll] = {M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE}, + [insn_sllv] = {M(spec_op, 0, 0, 0, 0, sllv_op), RS | RT | RD}, + [insn_slt] = {M(spec_op, 0, 0, 0, 0, slt_op), RS | RT | RD}, + [insn_slti] = {M(slti_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sltiu] = {M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sltu] = {M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD}, + [insn_sra] = {M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE}, + [insn_srl] = {M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE}, + [insn_srlv] = {M(spec_op, 0, 0, 0, 0, srlv_op), RS | RT | RD}, + [insn_subu] = {M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD}, + [insn_sw] = {M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sync] = {M(spec_op, 0, 0, 0, 0, sync_op), RE}, + [insn_syscall] = {M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM}, + [insn_tlbp] = {M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0}, + [insn_tlbr] = {M(cop0_op, cop_op, 0, 0, 0, tlbr_op), 0}, + [insn_tlbwi] = {M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0}, + [insn_tlbwr] = {M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0}, + [insn_wait] = {M(cop0_op, cop_op, 0, 0, 0, wait_op), SCIMM}, + [insn_wsbh] = {M(spec3_op, 0, 0, 0, wsbh_op, bshfl_op), RT | RD}, + [insn_xor] = {M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD}, + [insn_xori] = {M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, + [insn_yield] = {M(spec3_op, 0, 0, 0, 0, yield_op), RS | RD}, }; #undef M @@ -196,20 +215,17 @@ static inline u32 build_jimm(u32 arg) */ static void build_insn(u32 **buf, enum opcode opc, ...) { - struct insn *ip = NULL; - unsigned int i; + const struct insn *ip; va_list ap; u32 op; - for (i = 0; insn_table[i].opcode != insn_invalid; i++) - if (insn_table[i].opcode == opc) { - ip = &insn_table[i]; - break; - } - - if (!ip || (opc == insn_daddiu && r4k_daddiu_bug())) + if (opc < 0 || opc >= insn_invalid || + (opc == insn_daddiu && r4k_daddiu_bug()) || + (insn_table[opc].match == 0 && insn_table[opc].fields == 0)) panic("Unsupported Micro-assembler instruction %d", opc); + ip = &insn_table[opc]; + op = ip->match; va_start(ap, opc); if (ip->fields & RS) diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index 730363b59bac..57570c0649b4 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -46,26 +46,29 @@ enum fields { #define SIMM9_MASK 0x1ff enum opcode { - insn_invalid, insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1, - insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl, - insn_bne, insn_cache, insn_cfc1, insn_cfcmsa, insn_ctc1, insn_ctcmsa, - insn_daddiu, insn_daddu, insn_di, insn_dins, insn_dinsm, insn_divu, - insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll, - insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret, - insn_ext, insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, - insn_ld, insn_ldx, insn_lh, insn_ll, insn_lld, insn_lui, insn_lw, - insn_lwx, insn_mfc0, insn_mfhc0, insn_mfhi, insn_mflo, insn_mtc0, - insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_or, insn_ori, - insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll, - insn_sllv, insn_slt, insn_sltiu, insn_sltu, insn_sra, insn_srl, + insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bgtz, insn_blez, + insn_bltz, insn_bltzl, insn_bne, insn_break, insn_cache, insn_cfc1, + insn_cfcmsa, insn_ctc1, insn_ctcmsa, insn_daddiu, insn_daddu, insn_ddivu, + insn_di, insn_dins, insn_dinsm, insn_dinsu, insn_divu, insn_dmfc0, + insn_dmtc0, insn_dmultu, insn_drotr, insn_drotr32, insn_dsbh, insn_dshd, + insn_dsll, insn_dsll32, insn_dsllv, insn_dsra, insn_dsra32, insn_dsrav, + insn_dsrl, insn_dsrl32, insn_dsrlv, insn_dsubu, insn_eret, insn_ext, + insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, insn_lbu, + insn_ld, insn_lddir, insn_ldpte, insn_ldx, insn_lh, insn_lhu, + insn_ll, insn_lld, insn_lui, insn_lw, insn_lwu, insn_lwx, insn_mfc0, + insn_mfhc0, insn_mfhi, insn_mflo, insn_movn, insn_movz, insn_mtc0, + insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_multu, insn_nor, + insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sb, + insn_sc, insn_scd, insn_sd, insn_sh, insn_sll, insn_sllv, + insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor, - insn_xori, insn_yield, insn_lddir, insn_ldpte, insn_lhu, + insn_xori, insn_yield, + insn_invalid /* insn_invalid must be last */ }; struct insn { - enum opcode opcode; u32 match; enum fields fields; }; @@ -215,6 +218,13 @@ Ip_u2u1msbu3(op) \ } \ UASM_EXPORT_SYMBOL(uasm_i##op); +#define I_u2u1msb32msb3(op) \ +Ip_u2u1msbu3(op) \ +{ \ + build_insn(buf, insn##op, b, a, c+d-33, c-32); \ +} \ +UASM_EXPORT_SYMBOL(uasm_i##op); + #define I_u2u1msbdu3(op) \ Ip_u2u1msbu3(op) \ { \ @@ -265,25 +275,36 @@ I_u1u2s3(_beq) I_u1u2s3(_beql) I_u1s2(_bgez) I_u1s2(_bgezl) +I_u1s2(_bgtz) +I_u1s2(_blez) I_u1s2(_bltz) I_u1s2(_bltzl) I_u1u2s3(_bne) +I_u1(_break) I_u2s3u1(_cache) I_u1u2(_cfc1) I_u2u1(_cfcmsa) I_u1u2(_ctc1) I_u2u1(_ctcmsa) +I_u1u2(_ddivu) I_u1u2u3(_dmfc0) I_u1u2u3(_dmtc0) +I_u1u2(_dmultu) I_u2u1s3(_daddiu) I_u3u1u2(_daddu) I_u1(_di); I_u1u2(_divu) +I_u2u1(_dsbh); +I_u2u1(_dshd); I_u2u1u3(_dsll) I_u2u1u3(_dsll32) +I_u3u2u1(_dsllv) I_u2u1u3(_dsra) +I_u2u1u3(_dsra32) +I_u3u2u1(_dsrav) I_u2u1u3(_dsrl) I_u2u1u3(_dsrl32) +I_u3u2u1(_dsrlv) I_u2u1u3(_drotr) I_u2u1u3(_drotr32) I_u3u1u2(_dsubu) @@ -295,6 +316,7 @@ I_u1(_jal) I_u2u1(_jalr) I_u1(_jr) I_u2s3u1(_lb) +I_u2s3u1(_lbu) I_u2s3u1(_ld) I_u2s3u1(_lh) I_u2s3u1(_lhu) @@ -302,8 +324,11 @@ I_u2s3u1(_ll) I_u2s3u1(_lld) I_u1s2(_lui) I_u2s3u1(_lw) +I_u2s3u1(_lwu) I_u1u2u3(_mfc0) I_u1u2u3(_mfhc0) +I_u3u1u2(_movn) +I_u3u1u2(_movz) I_u1(_mfhi) I_u1(_mflo) I_u1u2u3(_mtc0) @@ -311,15 +336,20 @@ I_u1u2u3(_mthc0) I_u1(_mthi) I_u1(_mtlo) I_u3u1u2(_mul) -I_u2u1u3(_ori) +I_u1u2(_multu) +I_u3u1u2(_nor) I_u3u1u2(_or) +I_u2u1u3(_ori) I_0(_rfe) +I_u2s3u1(_sb) I_u2s3u1(_sc) I_u2s3u1(_scd) I_u2s3u1(_sd) +I_u2s3u1(_sh) I_u2u1u3(_sll) I_u3u2u1(_sllv) I_s3s1s2(_slt) +I_u2u1s3(_slti) I_u2u1s3(_sltiu) I_u3u1u2(_sltu) I_u2u1u3(_sra) @@ -340,6 +370,7 @@ I_u2u1u3(_xori) I_u2u1(_yield) I_u2u1msbu3(_dins); I_u2u1msb32u3(_dinsm); +I_u2u1msb32msb3(_dinsu); I_u1(_syscall); I_u1u2s3(_bbit0); I_u1u2s3(_bbit1); diff --git a/arch/mips/net/Makefile b/arch/mips/net/Makefile index 8c2771401f54..47d678416715 100644 --- a/arch/mips/net/Makefile +++ b/arch/mips/net/Makefile @@ -1,3 +1,4 @@ # MIPS networking code -obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_asm.o +obj-$(CONFIG_MIPS_CBPF_JIT) += bpf_jit.o bpf_jit_asm.o +obj-$(CONFIG_MIPS_EBPF_JIT) += ebpf_jit.o diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index ce89c9e294f9..974276e828b2 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -20,6 +20,46 @@ #include <asm/unistd.h> #include <asm/vdso.h> +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +static __always_inline long gettimeofday_fallback(struct timeval *_tv, + struct timezone *_tz) +{ + register struct timezone *tz asm("a1") = _tz; + register struct timeval *tv asm("a0") = _tv; + register long ret asm("v0"); + register long nr asm("v0") = __NR_gettimeofday; + register long error asm("a3"); + + asm volatile( + " syscall\n" + : "=r" (ret), "=r" (error) + : "r" (tv), "r" (tz), "r" (nr) + : "memory"); + + return error ? -ret : ret; +} + +#endif + +static __always_inline long clock_gettime_fallback(clockid_t _clkid, + struct timespec *_ts) +{ + register struct timespec *ts asm("a1") = _ts; + register clockid_t clkid asm("a0") = _clkid; + register long ret asm("v0"); + register long nr asm("v0") = __NR_clock_gettime; + register long error asm("a3"); + + asm volatile( + " syscall\n" + : "=r" (ret), "=r" (error) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return error ? -ret : ret; +} + static __always_inline int do_realtime_coarse(struct timespec *ts, const union mips_vdso_data *data) { @@ -39,8 +79,8 @@ static __always_inline int do_monotonic_coarse(struct timespec *ts, const union mips_vdso_data *data) { u32 start_seq; - u32 to_mono_sec; - u32 to_mono_nsec; + u64 to_mono_sec; + u64 to_mono_nsec; do { start_seq = vdso_data_read_begin(data); @@ -148,8 +188,8 @@ static __always_inline int do_monotonic(struct timespec *ts, { u32 start_seq; u64 ns; - u32 to_mono_sec; - u32 to_mono_nsec; + u64 to_mono_sec; + u64 to_mono_nsec; do { start_seq = vdso_data_read_begin(data); @@ -187,7 +227,7 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) ret = do_realtime(&ts, data); if (ret) - return ret; + return gettimeofday_fallback(tv, tz); if (tv) { tv->tv_sec = ts.tv_sec; @@ -202,12 +242,12 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) return 0; } -#endif /* CONFIG_CLKSRC_MIPS_GIC */ +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) { const union mips_vdso_data *data = get_vdso_data(); - int ret; + int ret = -1; switch (clkid) { case CLOCK_REALTIME_COARSE: @@ -223,10 +263,11 @@ int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) ret = do_monotonic(ts, data); break; default: - ret = -ENOSYS; break; } - /* If we return -ENOSYS libc should fall back to a syscall. */ + if (ret) + ret = clock_gettime_fallback(clkid, ts); + return ret; } diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 1fd962a07f52..cab33a0d0e82 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -6,7 +6,6 @@ */ #include <asm/page.h> #include <asm/cache.h> -#include <asm-generic/uaccess-unaligned.h> #include <linux/bug.h> #include <linux/string.h> diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 2b90335194a7..a2cc8010cd72 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -560,7 +560,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) * Atomically increments @v by 1, so long as @v is non-zero. * Returns non-zero if @v was non-zero, and zero otherwise. */ -static __inline__ long atomic64_inc_not_zero(atomic64_t *v) +static __inline__ int atomic64_inc_not_zero(atomic64_t *v) { long t1, t2; @@ -579,7 +579,7 @@ static __inline__ long atomic64_inc_not_zero(atomic64_t *v) : "r" (&v->counter) : "cc", "xer", "memory"); - return t1; + return t1 != 0; } #endif /* __powerpc64__ */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index ef930ba500f9..3130a73652c7 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -876,6 +876,15 @@ struct OpalIoPhb4ErrorData { enum { OPAL_REINIT_CPUS_HILE_BE = (1 << 0), OPAL_REINIT_CPUS_HILE_LE = (1 << 1), + + /* These two define the base MMU mode of the host on P9 + * + * On P9 Nimbus DD2.0 and Cumlus (and later), KVM can still + * create hash guests in "radix" mode with care (full core + * switch only). + */ + OPAL_REINIT_CPUS_MMU_HASH = (1 << 2), + OPAL_REINIT_CPUS_MMU_RADIX = (1 << 3), }; typedef struct oppanel_line { diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 7e50e47375d6..a3b6575c7842 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1303,7 +1303,7 @@ static inline void msr_check_and_clear(unsigned long bits) " .llong 0\n" \ ".previous" \ : "=r" (rval) \ - : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \ + : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) #else #define mftb() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 4cf57f2126e6..9c0e60ca1666 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -90,9 +90,6 @@ #define __put_user_inatomic(x, ptr) \ __put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user - extern long __put_user_bad(void); /* diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 10cb2896b2ae..610955fe8b81 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -218,13 +218,20 @@ __init_tlb_power8: ptesync 1: blr +/* + * Flush the TLB in hash mode. Hash must flush with RIC=2 once for process + * and one for partition scope to clear process and partition table entries. + */ __init_tlb_power9: - li r6,POWER9_TLB_SETS_HASH + li r6,POWER9_TLB_SETS_HASH - 1 mtctr r6 li r7,0xc00 /* IS field = 0b11 */ + li r8,0 ptesync -2: tlbiel r7 - addi r7,r7,0x1000 + PPC_TLBIEL(7, 8, 2, 1, 0) + PPC_TLBIEL(7, 8, 2, 0, 0) +2: addi r7,r7,0x1000 + PPC_TLBIEL(7, 8, 0, 0, 0) bdnz 2b ptesync 1: blr diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 4c7656dc4e04..1df770e8cbe0 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -94,9 +94,6 @@ static void (*init_pmu_registers)(void); static void cpufeatures_flush_tlb(void) { - unsigned long rb; - unsigned int i, num_sets; - /* * This is a temporary measure to keep equivalent TLB flush as the * cputable based setup code. @@ -105,24 +102,15 @@ static void cpufeatures_flush_tlb(void) case PVR_POWER8: case PVR_POWER8E: case PVR_POWER8NVL: - num_sets = POWER8_TLB_SETS; + __flush_tlb_power8(POWER8_TLB_SETS); break; case PVR_POWER9: - num_sets = POWER9_TLB_SETS_HASH; + __flush_tlb_power9(POWER9_TLB_SETS_HASH); break; default: - num_sets = 1; pr_err("unknown CPU version for boot TLB flush\n"); break; } - - asm volatile("ptesync" : : : "memory"); - rb = TLBIEL_INVAL_SET; - for (i = 0; i < num_sets; i++) { - asm volatile("tlbiel %0" : : "r" (rb)); - rb += 1 << TLBIEL_INVAL_SET_SHIFT; - } - asm volatile("ptesync" : : : "memory"); } static void __restore_cpu_cpufeatures(void) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index d24e689e893f..b76ca198e09c 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -53,6 +53,60 @@ static void flush_tlb_206(unsigned int num_sets, unsigned int action) asm volatile("ptesync" : : : "memory"); } +static void flush_tlb_300(unsigned int num_sets, unsigned int action) +{ + unsigned long rb; + unsigned int i; + unsigned int r; + + switch (action) { + case TLB_INVAL_SCOPE_GLOBAL: + rb = TLBIEL_INVAL_SET; + break; + case TLB_INVAL_SCOPE_LPID: + rb = TLBIEL_INVAL_SET_LPID; + break; + default: + BUG(); + break; + } + + asm volatile("ptesync" : : : "memory"); + + if (early_radix_enabled()) + r = 1; + else + r = 0; + + /* + * First flush table/PWC caches with set 0, then flush the + * rest of the sets, partition scope. Radix must then do it + * all again with process scope. Hash just has to flush + * process table. + */ + asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : + "r"(rb), "r"(0), "i"(2), "i"(0), "r"(r)); + for (i = 1; i < num_sets; i++) { + unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT); + + asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : + "r"(rb+set), "r"(0), "i"(2), "i"(0), "r"(r)); + } + + asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : + "r"(rb), "r"(0), "i"(2), "i"(1), "r"(r)); + if (early_radix_enabled()) { + for (i = 1; i < num_sets; i++) { + unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT); + + asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : + "r"(rb+set), "r"(0), "i"(2), "i"(1), "r"(r)); + } + } + + asm volatile("ptesync" : : : "memory"); +} + /* * Generic routines to flush TLB on POWER processors. These routines * are used as flush_tlb hook in the cpu_spec. @@ -79,7 +133,7 @@ void __flush_tlb_power9(unsigned int action) else num_sets = POWER9_TLB_SETS_HASH; - flush_tlb_206(num_sets, action); + flush_tlb_300(num_sets, action); } diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index c119044cad0d..8ac0bd2bddb0 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -614,6 +614,18 @@ _GLOBAL(kexec_sequence) li r0,0 std r0,16(r1) +BEGIN_FTR_SECTION + /* + * This is the best time to turn AMR/IAMR off. + * key 0 is used in radix for supervisor<->user + * protection, but on hash key 0 is reserved + * ideally we want to enter with a clean state. + * NOTE, we rely on r0 being 0 from above. + */ + mtspr SPRN_IAMR,r0 + mtspr SPRN_AMOR,r0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + /* save regs for local vars on new stack. * yes, we won't go back, but ... */ diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 33117f8a0882..ee33327686ae 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -683,8 +683,10 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 19: switch ((instr >> 1) & 0x3ff) { case 0: /* mcrf */ - rd = (instr >> 21) & 0x1c; - ra = (instr >> 16) & 0x1c; + rd = 7 - ((instr >> 23) & 0x7); + ra = 7 - ((instr >> 18) & 0x7); + rd *= 4; + ra *= 4; val = (regs->ccr >> ra) & 0xf; regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd); goto instr_done; @@ -964,6 +966,19 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, #endif case 19: /* mfcr */ + if ((instr >> 20) & 1) { + imm = 0xf0000000UL; + for (sh = 0; sh < 8; ++sh) { + if (instr & (0x80000 >> sh)) { + regs->gpr[rd] = regs->ccr & imm; + break; + } + imm >>= 4; + } + + goto instr_done; + } + regs->gpr[rd] = regs->ccr; regs->gpr[rd] &= 0xffffffffUL; goto instr_done; diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 71de2c6d88f3..abed1fe6992f 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -138,6 +138,14 @@ static int radix__init_new_context(struct mm_struct *mm) rts_field = radix__get_tree_size(); process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE); + /* + * Order the above store with subsequent update of the PID + * register (at which point HW can start loading/caching + * the entry) and the corresponding load by the MMU from + * the L2 cache. + */ + asm volatile("ptesync;isync" : : : "memory"); + mm->context.npu_context = NULL; return index; @@ -223,9 +231,15 @@ void destroy_context(struct mm_struct *mm) mm->context.cop_lockp = NULL; #endif /* CONFIG_PPC_ICSWX */ - if (radix_enabled()) - process_tb[mm->context.id].prtb1 = 0; - else + if (radix_enabled()) { + /* + * Radix doesn't have a valid bit in the process table + * entries. However we know that at least P9 implementation + * will avoid caching an entry with an invalid RTS field, + * and 0 is invalid. So this will do. + */ + process_tb[mm->context.id].prtb0 = 0; + } else subpage_prot_free(mm); destroy_pagetable_page(mm); __destroy_context(mm->context.id); diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 8125160be7bc..3f3aa9a7063a 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -90,13 +90,15 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) * MMCRA[SDAR_MODE] will be set to 0b01 * For rest * MMCRA[SDAR_MODE] will be set from event code. + * If sdar_mode from event is zero, default to 0b01. Hardware + * requires that we set a non-zero value. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) { if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE)) *mmcra &= MMCRA_SDAR_MODE_NO_UPDATES; - else if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) + else if (!cpu_has_feature(CPU_FTR_POWER9_DD1) && p9_SDAR_MODE(event)) *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; - else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + else *mmcra |= MMCRA_SDAR_MODE_TLB; } else *mmcra |= MMCRA_SDAR_MODE_TLB; diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h index 80204e064362..50689180a6c1 100644 --- a/arch/powerpc/perf/power9-events-list.h +++ b/arch/powerpc/perf/power9-events-list.h @@ -51,8 +51,12 @@ EVENT(PM_DTLB_MISS, 0x300fc) EVENT(PM_ITLB_MISS, 0x400fc) /* Run_Instructions */ EVENT(PM_RUN_INST_CMPL, 0x500fa) +/* Alternate event code for PM_RUN_INST_CMPL */ +EVENT(PM_RUN_INST_CMPL_ALT, 0x400fa) /* Run_cycles */ EVENT(PM_RUN_CYC, 0x600f4) +/* Alternate event code for Run_cycles */ +EVENT(PM_RUN_CYC_ALT, 0x200f4) /* Instruction Dispatched */ EVENT(PM_INST_DISP, 0x200f2) EVENT(PM_INST_DISP_ALT, 0x300f2) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index f17435e4a489..2280cf87ff9c 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -107,6 +107,8 @@ extern struct attribute_group isa207_pmu_format_group; /* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index d8af9bc0489f..9558d725a99b 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -605,6 +605,24 @@ static const match_table_t spufs_tokens = { { Opt_err, NULL }, }; +static int spufs_show_options(struct seq_file *m, struct dentry *root) +{ + struct spufs_sb_info *sbi = spufs_get_sb_info(root->d_sb); + struct inode *inode = root->d_inode; + + if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, inode->i_uid)); + if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, inode->i_gid)); + if ((inode->i_mode & S_IALLUGO) != 0775) + seq_printf(m, ",mode=%o", inode->i_mode); + if (sbi->debug) + seq_puts(m, ",debug"); + return 0; +} + static int spufs_parse_options(struct super_block *sb, char *options, struct inode *root) { @@ -724,11 +742,9 @@ spufs_fill_super(struct super_block *sb, void *data, int silent) .destroy_inode = spufs_destroy_inode, .statfs = simple_statfs, .evict_inode = spufs_evict_inode, - .show_options = generic_show_options, + .show_options = spufs_show_options, }; - save_mount_options(sb, data); - info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 59684b4af4d1..9b87abb178f0 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -59,6 +59,8 @@ static struct task_struct *kopald_tsk; void opal_configure_cores(void) { + u64 reinit_flags = 0; + /* Do the actual re-init, This will clobber all FPRs, VRs, etc... * * It will preserve non volatile GPRs and HSPRG0/1. It will @@ -66,11 +68,24 @@ void opal_configure_cores(void) * but it might clobber a bunch. */ #ifdef __BIG_ENDIAN__ - opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); + reinit_flags |= OPAL_REINIT_CPUS_HILE_BE; #else - opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE); + reinit_flags |= OPAL_REINIT_CPUS_HILE_LE; #endif + /* + * POWER9 always support running hash: + * ie. Host hash supports hash guests + * Host radix supports hash/radix guests + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + reinit_flags |= OPAL_REINIT_CPUS_MMU_HASH; + if (early_radix_enabled()) + reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX; + } + + opal_reinit_cpus(reinit_flags); + /* Restore some bits */ if (cur_cpu_spec->cpu_restore) cur_cpu_spec->cpu_restore(); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 2dc7e5fb86c3..897aa1400eb8 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -225,6 +225,8 @@ static void pnv_kexec_wait_secondaries_down(void) static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { + u64 reinit_flags; + if (xive_enabled()) xive_kexec_teardown_cpu(secondary); else @@ -254,8 +256,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) * We might be running as little-endian - now that interrupts * are disabled, reset the HILE bit to big-endian so we don't * take interrupts in the wrong endian later + * + * We reinit to enable both radix and hash on P9 to ensure + * the mode used by the next kernel is always supported. */ - opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); + reinit_flags = OPAL_REINIT_CPUS_HILE_BE; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX | + OPAL_REINIT_CPUS_MMU_HASH; + opal_reinit_cpus(reinit_flags); } } #endif /* CONFIG_KEXEC_CORE */ diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 28b528197cf5..304cfe44df50 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -249,9 +249,6 @@ int __put_user_bad(void) __attribute__((noreturn)); int __get_user_bad(void) __attribute__((noreturn)); -#define __put_user_unaligned __put_user -#define __get_user_unaligned __get_user - unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n); diff --git a/arch/sh/include/asm/flat.h b/arch/sh/include/asm/flat.h index 5d84df5e27f6..275fcae23539 100644 --- a/arch/sh/include/asm/flat.h +++ b/arch/sh/include/asm/flat.h @@ -12,11 +12,22 @@ #ifndef __ASM_SH_FLAT_H #define __ASM_SH_FLAT_H +#include <asm/unaligned.h> + #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val,rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = get_unaligned((__force u32 *)rp); + return 0; +} +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + put_unaligned(addr, (__force u32 *)rp); + return 0; +} #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) ({ (void)p; 0; }) diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 113d84eaa15e..6d4c997d1a9e 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -9,7 +9,6 @@ #include <linux/string.h> #include <asm/asi.h> #include <asm/spitfire.h> -#include <asm-generic/uaccess-unaligned.h> #include <asm/extable_64.h> #include <asm/processor.h> diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index d0c79c1c54b4..cb4fbe7e4f88 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -19,7 +19,6 @@ * User space memory access functions */ #include <linux/mm.h> -#include <asm-generic/uaccess-unaligned.h> #include <asm/processor.h> #include <asm/page.h> diff --git a/arch/tile/include/uapi/arch/abi.h b/arch/tile/include/uapi/arch/abi.h index c55a3d432644..328e62260272 100644 --- a/arch/tile/include/uapi/arch/abi.h +++ b/arch/tile/include/uapi/arch/abi.h @@ -20,58 +20,17 @@ #ifndef __ARCH_ABI_H__ -#if !defined __need_int_reg_t && !defined __DOXYGEN__ -# define __ARCH_ABI_H__ -# include <arch/chip.h> -#endif - -/* Provide the basic machine types. */ -#ifndef __INT_REG_BITS - -/** Number of bits in a register. */ -#if defined __tilegx__ -# define __INT_REG_BITS 64 -#elif defined __tilepro__ -# define __INT_REG_BITS 32 -#elif !defined __need_int_reg_t +#ifndef __tile__ /* support uncommon use of arch headers in non-tile builds */ # include <arch/chip.h> # define __INT_REG_BITS CHIP_WORD_SIZE() -#else -# error Unrecognized architecture with __need_int_reg_t -#endif - -#if __INT_REG_BITS == 64 - -#ifndef __ASSEMBLER__ -/** Unsigned type that can hold a register. */ -typedef unsigned long long __uint_reg_t; - -/** Signed type that can hold a register. */ -typedef long long __int_reg_t; -#endif - -/** String prefix to use for printf(). */ -#define __INT_REG_FMT "ll" - -#else - -#ifndef __ASSEMBLER__ -/** Unsigned type that can hold a register. */ -typedef unsigned long __uint_reg_t; - -/** Signed type that can hold a register. */ -typedef long __int_reg_t; -#endif - -/** String prefix to use for printf(). */ -#define __INT_REG_FMT "l" - #endif -#endif /* __INT_REG_BITS */ +#include <arch/intreg.h> +/* __need_int_reg_t is deprecated: just include <arch/intreg.h> */ #ifndef __need_int_reg_t +#define __ARCH_ABI_H__ #ifndef __ASSEMBLER__ /** Unsigned type that can hold a register. */ diff --git a/arch/tile/include/uapi/arch/intreg.h b/arch/tile/include/uapi/arch/intreg.h new file mode 100644 index 000000000000..1cf2fbf74306 --- /dev/null +++ b/arch/tile/include/uapi/arch/intreg.h @@ -0,0 +1,70 @@ +/* + * Copyright 2017 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * @file + * + * Provide types and defines for the type that can hold a register, + * in the implementation namespace. + */ + +#ifndef __ARCH_INTREG_H__ +#define __ARCH_INTREG_H__ + +/* + * Get number of bits in a register. __INT_REG_BITS may be defined + * prior to including this header to force a particular bit width. + */ + +#ifndef __INT_REG_BITS +# if defined __tilegx__ +# define __INT_REG_BITS 64 +# elif defined __tilepro__ +# define __INT_REG_BITS 32 +# else +# error Unrecognized architecture +# endif +#endif + +#if __INT_REG_BITS == 64 + +# ifndef __ASSEMBLER__ +/** Unsigned type that can hold a register. */ +typedef unsigned long long __uint_reg_t; + +/** Signed type that can hold a register. */ +typedef long long __int_reg_t; +# endif + +/** String prefix to use for printf(). */ +# define __INT_REG_FMT "ll" + +#elif __INT_REG_BITS == 32 + +# ifndef __ASSEMBLER__ +/** Unsigned type that can hold a register. */ +typedef unsigned long __uint_reg_t; + +/** Signed type that can hold a register. */ +typedef long __int_reg_t; +# endif + +/** String prefix to use for printf(). */ +# define __INT_REG_FMT "l" + +#else +# error Unrecognized value of __INT_REG_BITS +#endif + +#endif /* !__ARCH_INTREG_H__ */ diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index 3a97e4d7205c..5f757e04bcd2 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -857,36 +857,6 @@ void __init mem_init(void) #endif } -/* - * this is for the non-NUMA, single node SMP system case. - * Specifically, in the case of x86, we will always add - * memory to the highmem for now. - */ -#ifndef CONFIG_NEED_MULTIPLE_NODES -int arch_add_memory(u64 start, u64 size, bool for_device) -{ - struct pglist_data *pgdata = &contig_page_data; - struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1; - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - - return __add_pages(zone, start_pfn, nr_pages); -} - -int remove_memory(u64 start, u64 size) -{ - return -EINVAL; -} - -#ifdef CONFIG_MEMORY_HOTREMOVE -int arch_remove_memory(u64 start, u64 size) -{ - /* TODO */ - return -EBUSY; -} -#endif -#endif - struct kmem_cache *pgd_cache; void __init pgtable_cache_init(void) diff --git a/arch/um/Makefile b/arch/um/Makefile index 0ca46ededfc7..6ca4f66085c1 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -59,10 +59,14 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um # Same things for in6addr_loopback and mktime - found in libc. For these two we # only get link-time error, luckily. # +# -Dlongjmp=kernel_longjmp prevents anything from referencing the libpthread.a +# embedded copy of longjmp, same thing for setjmp. +# # These apply to USER_CFLAGS to. KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \ $(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap \ + -Dlongjmp=kernel_longjmp -Dsetjmp=kernel_setjmp \ -Din6addr_loopback=kernel_in6addr_loopback \ -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c index 7b361f36ca96..c90817b04da9 100644 --- a/arch/um/drivers/stdio_console.c +++ b/arch/um/drivers/stdio_console.c @@ -192,6 +192,9 @@ __uml_exitcall(console_exit); static int console_chan_setup(char *str) { + if (!strncmp(str, "sole=", 5)) /* console= option specifies tty */ + return 0; + line_setup(vt_conf, MAX_TTYS, &def_conf, str, "console"); return 1; } diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 133055311dce..9e6d5997cfc4 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -15,7 +15,7 @@ PROVIDE (_unprotected_end = .); . = ALIGN(4096); - .note : { *(.note.*) } + NOTES EXCEPTION_TABLE(0) BUG_TABLE diff --git a/arch/um/include/asm/io.h b/arch/um/include/asm/io.h new file mode 100644 index 000000000000..8f35d574f35b --- /dev/null +++ b/arch/um/include/asm/io.h @@ -0,0 +1,17 @@ +#ifndef _ASM_UM_IO_H +#define _ASM_UM_IO_H + +#define ioremap ioremap +static inline void __iomem *ioremap(phys_addr_t offset, size_t size) +{ + return (void __iomem *)(unsigned long)offset; +} + +#define iounmap iounmap +static inline void iounmap(void __iomem *addr) +{ +} + +#include <asm-generic/io.h> + +#endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index cd1fa97776c3..574e03fc7ba2 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -242,6 +242,10 @@ extern void setup_hostinfo(char *buf, int len); extern void os_dump_core(void) __attribute__ ((noreturn)); extern void um_early_printk(const char *s, unsigned int n); extern void os_fix_helper_signals(void); +extern void os_info(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); +extern void os_warn(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); /* time.c */ extern void os_idle_sleep(unsigned long long nsecs); diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h index a9deece956bf..13f404e1262b 100644 --- a/arch/um/include/shared/skas/stub-data.h +++ b/arch/um/include/shared/skas/stub-data.h @@ -8,8 +8,6 @@ #ifndef __STUB_DATA_H #define __STUB_DATA_H -#include <time.h> - struct stub_data { unsigned long offset; int fd; diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 4c9861b421fd..f02596e9931d 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -89,8 +89,8 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end, offset = uml_reserved - uml_physmem; map_size = len - offset; if(map_size <= 0) { - printf("Too few physical memory! Needed=%d, given=%d\n", - offset, len); + os_warn("Too few physical memory! Needed=%lu, given=%lu\n", + offset, len); exit(1); } @@ -99,9 +99,9 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end, err = os_map_memory((void *) uml_reserved, physmem_fd, offset, map_size, 1, 1, 1); if (err < 0) { - printf("setup_physmem - mapping %ld bytes of memory at 0x%p " - "failed - errno = %d\n", map_size, - (void *) uml_reserved, err); + os_warn("setup_physmem - mapping %ld bytes of memory at 0x%p " + "failed - errno = %d\n", map_size, + (void *) uml_reserved, err); exit(1); } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 59158871b9fc..4e6fcb32620f 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -183,6 +183,16 @@ void fatal_sigsegv(void) os_dump_core(); } +/** + * segv_handler() - the SIGSEGV handler + * @sig: the signal number + * @unused_si: the signal info struct; unused in this handler + * @regs: the ptrace register information + * + * The handler first extracts the faultinfo from the UML ptrace regs struct. + * If the userfault did not happen in an UML userspace process, bad_segv is called. + * Otherwise the signal did happen in a cloned userspace process, handle it. + */ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) { struct faultinfo * fi = UPT_FAULTINFO(regs); diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 7b5640117325..f433690b9b37 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -34,7 +34,7 @@ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 }; static void __init add_arg(char *arg) { if (strlen(command_line) + strlen(arg) + 1 > COMMAND_LINE_SIZE) { - printf("add_arg: Too many command line arguments!\n"); + os_warn("add_arg: Too many command line arguments!\n"); exit(1); } if (strlen(command_line) > 0) @@ -120,6 +120,7 @@ static const char *usage_string = static int __init uml_version_setup(char *line, int *add) { + /* Explicitly use printf() to show version in stdout */ printf("%s\n", init_utsname()->release); exit(0); @@ -148,8 +149,8 @@ __uml_setup("root=", uml_root_setup, static int __init no_skas_debug_setup(char *line, int *add) { - printf("'debug' is not necessary to gdb UML in skas mode - run \n"); - printf("'gdb linux'\n"); + os_warn("'debug' is not necessary to gdb UML in skas mode - run\n"); + os_warn("'gdb linux'\n"); return 0; } @@ -165,6 +166,7 @@ static int __init Usage(char *line, int *add) printf(usage_string, init_utsname()->release); p = &__uml_help_start; + /* Explicitly use printf() to show help in stdout */ while (p < &__uml_help_end) { printf("%s", *p); p++; @@ -283,8 +285,8 @@ int __init linux_main(int argc, char **argv) diff = UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end); if (diff > 1024 * 1024) { - printf("Adding %ld bytes to physical memory to account for " - "exec-shield gap\n", diff); + os_info("Adding %ld bytes to physical memory to account for " + "exec-shield gap\n", diff); physmem_size += UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end); } @@ -324,8 +326,8 @@ int __init linux_main(int argc, char **argv) end_vm = start_vm + virtmem_size; if (virtmem_size < physmem_size) - printf("Kernel virtual memory size shrunk to %lu bytes\n", - virtmem_size); + os_info("Kernel virtual memory size shrunk to %lu bytes\n", + virtmem_size); os_flush_stdout(); diff --git a/arch/um/kernel/umid.c b/arch/um/kernel/umid.c index f6cc3bd61781..10bf4aca529f 100644 --- a/arch/um/kernel/umid.c +++ b/arch/um/kernel/umid.c @@ -16,14 +16,14 @@ static int __init set_umid_arg(char *name, int *add) int err; if (umid_inited) { - printf("umid already set\n"); + os_warn("umid already set\n"); return 0; } *add = 0; err = set_umid(name); if (err == -EEXIST) - printf("umid '%s' already in use\n", name); + os_warn("umid '%s' already in use\n", name); else if (!err) umid_inited = 1; diff --git a/arch/um/os-Linux/execvp.c b/arch/um/os-Linux/execvp.c index 8fb25ca07c46..84a0777c2a45 100644 --- a/arch/um/os-Linux/execvp.c +++ b/arch/um/os-Linux/execvp.c @@ -136,7 +136,7 @@ int main(int argc, char**argv) int ret; argc--; if (!argc) { - fprintf(stderr, "Not enough arguments\n"); + os_warn("Not enough arguments\n"); return 1; } argv++; diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index 9d499de87e63..5f970ece5ac3 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -74,8 +74,8 @@ static void install_fatal_handler(int sig) action.sa_restorer = NULL; action.sa_handler = last_ditch_exit; if (sigaction(sig, &action, NULL) < 0) { - printf("failed to install handler for signal %d - errno = %d\n", - sig, errno); + os_warn("failed to install handler for signal %d " + "- errno = %d\n", sig, errno); exit(1); } } @@ -175,7 +175,7 @@ int __init main(int argc, char **argv, char **envp) /* disable SIGIO for the fds and set SIGIO to be ignored */ err = deactivate_all_fds(); if (err) - printf("deactivate_all_fds failed, errno = %d\n", -err); + os_warn("deactivate_all_fds failed, errno = %d\n", -err); /* * Let any pending signals fire now. This ensures @@ -184,14 +184,13 @@ int __init main(int argc, char **argv, char **envp) */ unblock_signals(); + os_info("\n"); /* Reboot */ if (ret) { - printf("\n"); execvp(new_argv[0], new_argv); perror("Failed to exec kernel"); ret = 1; } - printf("\n"); return uml_exitcode; } diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 8b1767668515..e162a95ad7dd 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -25,13 +25,13 @@ static int __init check_tmpfs(const char *dir) { struct statfs st; - printf("Checking if %s is on tmpfs...", dir); + os_info("Checking if %s is on tmpfs...", dir); if (statfs(dir, &st) < 0) { - printf("%s\n", strerror(errno)); + os_info("%s\n", strerror(errno)); } else if (st.f_type != TMPFS_MAGIC) { - printf("no\n"); + os_info("no\n"); } else { - printf("OK\n"); + os_info("OK\n"); return 0; } return -1; @@ -61,18 +61,18 @@ static char * __init choose_tempdir(void) int i; const char *dir; - printf("Checking environment variables for a tempdir..."); + os_info("Checking environment variables for a tempdir..."); for (i = 0; vars[i]; i++) { dir = getenv(vars[i]); if ((dir != NULL) && (*dir != '\0')) { - printf("%s\n", dir); + os_info("%s\n", dir); if (check_tmpfs(dir) >= 0) goto done; else goto warn; } } - printf("none found\n"); + os_info("none found\n"); for (i = 0; tmpfs_dirs[i]; i++) { dir = tmpfs_dirs[i]; @@ -82,7 +82,7 @@ static char * __init choose_tempdir(void) dir = fallback_dir; warn: - printf("Warning: tempdir %s is not on tmpfs\n", dir); + os_warn("Warning: tempdir %s is not on tmpfs\n", dir); done: /* Make a copy since getenv results may not remain valid forever. */ return strdup(dir); @@ -100,7 +100,7 @@ static int __init make_tempfile(const char *template) if (tempdir == NULL) { tempdir = choose_tempdir(); if (tempdir == NULL) { - fprintf(stderr, "Failed to choose tempdir: %s\n", + os_warn("Failed to choose tempdir: %s\n", strerror(errno)); return -1; } @@ -125,7 +125,7 @@ static int __init make_tempfile(const char *template) strcat(tempname, template); fd = mkstemp(tempname); if (fd < 0) { - fprintf(stderr, "open - cannot create %s: %s\n", tempname, + os_warn("open - cannot create %s: %s\n", tempname, strerror(errno)); goto out; } @@ -194,16 +194,16 @@ void __init check_tmpexec(void) addr = mmap(NULL, UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE, fd, 0); - printf("Checking PROT_EXEC mmap in %s...", tempdir); + os_info("Checking PROT_EXEC mmap in %s...", tempdir); if (addr == MAP_FAILED) { err = errno; - printf("%s\n", strerror(err)); + os_warn("%s\n", strerror(err)); close(fd); if (err == EPERM) - printf("%s must be not mounted noexec\n", tempdir); + os_warn("%s must be not mounted noexec\n", tempdir); exit(1); } - printf("OK\n"); + os_info("OK\n"); munmap(addr, UM_KERN_PAGE_SIZE); close(fd); diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 03b3c4cc7735..819d68656673 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -108,7 +108,7 @@ static void get_skas_faultinfo(int pid, struct faultinfo *fi) wait_stub_done(pid); /* - * faultinfo is prepared by the stub-segv-handler at start of + * faultinfo is prepared by the stub_segv_handler at start of * the stub stack page. We just have to copy it. */ memcpy(fi, (void *)current_stub_stack(), sizeof(*fi)); @@ -175,6 +175,21 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, extern char __syscall_stub_start[]; +/** + * userspace_tramp() - userspace trampoline + * @stack: pointer to the new userspace stack page, can be NULL, if? FIXME: + * + * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed. + * This function will run on a temporary stack page. + * It ptrace()'es itself, then + * Two pages are mapped into the userspace address space: + * - STUB_CODE (with EXEC), which contains the skas stub code + * - STUB_DATA (with R/W), which contains a data page that is used to transfer certain data between the UML userspace process and the UML kernel. + * Also for the userspace process a SIGSEGV handler is installed to catch pagefaults in the userspace process. + * And last the process stops itself to give control to the UML kernel for this userspace process. + * + * Return: Always zero, otherwise the current userspace process is ended with non null exit() call + */ static int userspace_tramp(void *stack) { void *addr; @@ -236,12 +251,24 @@ static int userspace_tramp(void *stack) int userspace_pid[NR_CPUS]; +/** + * start_userspace() - prepare a new userspace process + * @stub_stack: pointer to the stub stack. Can be NULL, if? FIXME: + * + * Setups a new temporary stack page that is used while userspace_tramp() runs + * Clones the kernel process into a new userspace process, with FDs only. + * + * Return: When positive: the process id of the new userspace process, + * when negative: an error number. + * FIXME: can PIDs become negative?! + */ int start_userspace(unsigned long stub_stack) { void *stack; unsigned long sp; int pid, status, n, flags, err; + /* setup a temporary stack page */ stack = mmap(NULL, UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); @@ -252,10 +279,12 @@ int start_userspace(unsigned long stub_stack) return err; } + /* set stack pointer to the end of the stack page, so it can grow downwards */ sp = (unsigned long) stack + UM_KERN_PAGE_SIZE - sizeof(void *); flags = CLONE_FILES | SIGCHLD; + /* clone into new userspace process */ pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack); if (pid < 0) { err = -errno; @@ -323,11 +352,17 @@ void userspace(struct uml_pt_regs *regs) * fail. In this case, there is nothing to do but * just kill the process. */ - if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) + if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) { + printk(UM_KERN_ERR "userspace - ptrace set regs " + "failed, errno = %d\n", errno); fatal_sigsegv(); + } - if (put_fp_registers(pid, regs->fp)) + if (put_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "userspace - ptrace set fp regs " + "failed, errno = %d\n", errno); fatal_sigsegv(); + } /* Now we set local_using_sysemu to be used for one loop */ local_using_sysemu = get_using_sysemu(); diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 22a358ef1b0c..b1b6b75c5b17 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -166,7 +166,7 @@ static void __init check_sysemu(void) unsigned long regs[MAX_REG_NR]; int pid, n, status, count=0; - non_fatal("Checking syscall emulation patch for ptrace..."); + os_info("Checking syscall emulation patch for ptrace..."); sysemu_supported = 0; pid = start_ptraced_child(); @@ -199,10 +199,10 @@ static void __init check_sysemu(void) goto fail_stopped; sysemu_supported = 1; - non_fatal("OK\n"); + os_info("OK\n"); set_using_sysemu(!force_sysemu_disabled); - non_fatal("Checking advanced syscall emulation patch for ptrace..."); + os_info("Checking advanced syscall emulation patch for ptrace..."); pid = start_ptraced_child(); if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0, @@ -244,7 +244,7 @@ static void __init check_sysemu(void) goto fail_stopped; sysemu_supported = 2; - non_fatal("OK\n"); + os_info("OK\n"); if (!force_sysemu_disabled) set_using_sysemu(sysemu_supported); @@ -260,7 +260,7 @@ static void __init check_ptrace(void) { int pid, syscall, n, status; - non_fatal("Checking that ptrace can change system call numbers..."); + os_info("Checking that ptrace can change system call numbers..."); pid = start_ptraced_child(); if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0, @@ -292,7 +292,7 @@ static void __init check_ptrace(void) } } stop_ptraced_child(pid, 0, 1); - non_fatal("OK\n"); + os_info("OK\n"); check_sysemu(); } @@ -308,15 +308,17 @@ static void __init check_coredump_limit(void) return; } - printf("Core dump limits :\n\tsoft - "); + os_info("Core dump limits :\n\tsoft - "); if (lim.rlim_cur == RLIM_INFINITY) - printf("NONE\n"); - else printf("%lu\n", lim.rlim_cur); + os_info("NONE\n"); + else + os_info("%llu\n", (unsigned long long)lim.rlim_cur); - printf("\thard - "); + os_info("\thard - "); if (lim.rlim_max == RLIM_INFINITY) - printf("NONE\n"); - else printf("%lu\n", lim.rlim_max); + os_info("NONE\n"); + else + os_info("%llu\n", (unsigned long long)lim.rlim_max); } void __init os_early_checks(void) @@ -349,7 +351,7 @@ int __init parse_iomem(char *str, int *add) driver = str; file = strchr(str,','); if (file == NULL) { - fprintf(stderr, "parse_iomem : failed to parse iomem\n"); + os_warn("parse_iomem : failed to parse iomem\n"); goto out; } *file = '\0'; diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index c1dc89261f67..998fbb445458 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -35,8 +35,9 @@ static int __init make_uml_dir(void) err = -ENOENT; if (home == NULL) { - printk(UM_KERN_ERR "make_uml_dir : no value in " - "environment for $HOME\n"); + printk(UM_KERN_ERR + "%s: no value in environment for $HOME\n", + __func__); goto err; } strlcpy(dir, home, sizeof(dir)); @@ -50,13 +51,15 @@ static int __init make_uml_dir(void) err = -ENOMEM; uml_dir = malloc(strlen(dir) + 1); if (uml_dir == NULL) { - printf("make_uml_dir : malloc failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s : malloc failed, errno = %d\n", + __func__, errno); goto err; } strcpy(uml_dir, dir); if ((mkdir(uml_dir, 0777) < 0) && (errno != EEXIST)) { - printf("Failed to mkdir '%s': %s\n", uml_dir, strerror(errno)); + printk(UM_KERN_ERR "Failed to mkdir '%s': %s\n", + uml_dir, strerror(errno)); err = -errno; goto err_free; } @@ -351,7 +354,7 @@ char *get_umid(void) static int __init set_uml_dir(char *name, int *add) { if (*name == '\0') { - printf("uml_dir can't be an empty string\n"); + os_warn("uml_dir can't be an empty string\n"); return 0; } @@ -362,7 +365,7 @@ static int __init set_uml_dir(char *name, int *add) uml_dir = malloc(strlen(name) + 2); if (uml_dir == NULL) { - printf("Failed to malloc uml_dir - error = %d\n", errno); + os_warn("Failed to malloc uml_dir - error = %d\n", errno); /* * Return 0 here because do_initcalls doesn't look at @@ -387,8 +390,8 @@ static void remove_umid_dir(void) sprintf(dir, "%s%s", uml_dir, umid); err = remove_files_and_dir(dir); if (err) - printf("remove_umid_dir - remove_files_and_dir failed with " - "err = %d\n", err); + os_warn("%s - remove_files_and_dir failed with err = %d\n", + __func__, err); } __uml_exitcall(remove_umid_dir); diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index faee55ef6d2f..8cc8b2617a67 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -13,6 +13,7 @@ #include <wait.h> #include <sys/mman.h> #include <sys/utsname.h> +#include <init.h> #include <os.h> void stack_protections(unsigned long address) @@ -152,3 +153,36 @@ void um_early_printk(const char *s, unsigned int n) { printf("%.*s", n, s); } + +static int quiet_info; + +static int __init quiet_cmd_param(char *str, int *add) +{ + quiet_info = 1; + return 0; +} + +__uml_setup("quiet", quiet_cmd_param, +"quiet\n" +" Turns off information messages during boot.\n\n"); + +void os_info(const char *fmt, ...) +{ + va_list list; + + if (quiet_info) + return; + + va_start(list, fmt); + vfprintf(stderr, fmt, list); + va_end(list); +} + +void os_warn(const char *fmt, ...) +{ + va_list list; + + va_start(list, fmt); + vfprintf(stderr, fmt, list); + va_end(list); +} diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index fc61739150e7..f960a043cdeb 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, static bool avx2_usable(void) { - if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI1) && boot_cpu_has(X86_FEATURE_BMI2)) return true; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2701e5f8145b..ca3c48c0872f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -286,6 +286,7 @@ #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ +#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 722d0e568863..fde36f189836 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -23,6 +23,7 @@ struct x86_exception { u16 error_code; bool nested_page_fault; u64 address; /* cr2 or nested page fault gpa */ + u8 async_page_fault; }; /* diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1588e9e3dc01..87ac4fba6d8e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -462,10 +462,12 @@ struct kvm_vcpu_hv_synic { DECLARE_BITMAP(auto_eoi_bitmap, 256); DECLARE_BITMAP(vec_bitmap, 256); bool active; + bool dont_zero_synic_pages; }; /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { + u32 vp_index; u64 hv_vapic; s64 runtime_offset; struct kvm_vcpu_hv_synic synic; @@ -549,6 +551,7 @@ struct kvm_vcpu_arch { bool reinject; u8 nr; u32 error_code; + u8 nested_apf; } exception; struct kvm_queued_interrupt { @@ -649,6 +652,9 @@ struct kvm_vcpu_arch { u64 msr_val; u32 id; bool send_user_only; + u32 host_apf_reason; + unsigned long nested_apf_token; + bool delivery_as_pf_vmexit; } apf; /* OSVW MSRs (AMD only) */ @@ -803,6 +809,7 @@ struct kvm_arch { int audit_point; #endif + bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; u32 bsp_vcpu_id; @@ -952,9 +959,7 @@ struct kvm_x86_ops { unsigned char *hypercall_addr); void (*set_irq)(struct kvm_vcpu *vcpu); void (*set_nmi)(struct kvm_vcpu *vcpu); - void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code, - bool reinject); + void (*queue_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 14824fc78f7e..58fffe79e417 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -83,7 +83,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 event_inj; u32 event_inj_err; u64 nested_cr3; - u64 lbr_ctl; + u64 virt_ext; u32 clean; u32 reserved_5; u64 next_rip; @@ -119,6 +119,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_ENABLE_SHIFT 31 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) +#define LBR_CTL_ENABLE_MASK BIT_ULL(0) +#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) + #define SVM_INTERRUPT_SHADOW_MASK 1 #define SVM_IOIO_STR_SHIFT 2 diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 476ea27f490b..30269dafec47 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -535,9 +535,6 @@ struct __large_struct { unsigned long buf[100]; }; #define __put_user(x, ptr) \ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user - /* * {get|put}_user_try and catch * diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index cff0bb6556f8..a965e5b0d328 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -67,6 +67,7 @@ struct kvm_clock_pairing { #define KVM_ASYNC_PF_ENABLED (1 << 0) #define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1) +#define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT (1 << 2) /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 43e10d6fdbed..71c17a5be983 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -330,7 +330,12 @@ static void kvm_guest_cpu_init(void) #ifdef CONFIG_PREEMPT pa |= KVM_ASYNC_PF_SEND_ALWAYS; #endif - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED); + pa |= KVM_ASYNC_PF_ENABLED; + + /* Async page fault support for L1 hypervisor is optional */ + if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN, + (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0) + wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index ebae57ac5902..2695a34fa1c5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -106,14 +106,27 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, return 0; } -static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id) +static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + if (vpidx < KVM_MAX_VCPUS) + vcpu = kvm_get_vcpu(kvm, vpidx); + if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx) + return vcpu; + kvm_for_each_vcpu(i, vcpu, kvm) + if (vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx) + return vcpu; + return NULL; +} + +static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu; struct kvm_vcpu_hv_synic *synic; - if (vcpu_id >= atomic_read(&kvm->online_vcpus)) - return NULL; - vcpu = kvm_get_vcpu(kvm, vcpu_id); + vcpu = get_vcpu_by_vpidx(kvm, vpidx); if (!vcpu) return NULL; synic = vcpu_to_synic(vcpu); @@ -221,7 +234,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, synic->version = data; break; case HV_X64_MSR_SIEFP: - if (data & HV_SYNIC_SIEFP_ENABLE) + if ((data & HV_SYNIC_SIEFP_ENABLE) && !host && + !synic->dont_zero_synic_pages) if (kvm_clear_guest(vcpu->kvm, data & PAGE_MASK, PAGE_SIZE)) { ret = 1; @@ -232,7 +246,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, synic_exit(synic, msr); break; case HV_X64_MSR_SIMP: - if (data & HV_SYNIC_SIMP_ENABLE) + if ((data & HV_SYNIC_SIMP_ENABLE) && !host && + !synic->dont_zero_synic_pages) if (kvm_clear_guest(vcpu->kvm, data & PAGE_MASK, PAGE_SIZE)) { ret = 1; @@ -318,11 +333,11 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) return ret; } -int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint) +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint) { struct kvm_vcpu_hv_synic *synic; - synic = synic_get(kvm, vcpu_id); + synic = synic_get(kvm, vpidx); if (!synic) return -EINVAL; @@ -341,11 +356,11 @@ void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) kvm_hv_notify_acked_sint(vcpu, i); } -static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi) +static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vpidx, u32 sint, int gsi) { struct kvm_vcpu_hv_synic *synic; - synic = synic_get(kvm, vcpu_id); + synic = synic_get(kvm, vpidx); if (!synic) return -EINVAL; @@ -687,14 +702,24 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) stimer_init(&hv_vcpu->stimer[i], i); } -int kvm_hv_activate_synic(struct kvm_vcpu *vcpu) +void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + + hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); +} + +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) { + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + /* * Hyper-V SynIC auto EOI SINT's are * not compatible with APICV, so deactivate APICV */ kvm_vcpu_deactivate_apicv(vcpu); - vcpu_to_synic(vcpu)->active = true; + synic->active = true; + synic->dont_zero_synic_pages = dont_zero_synic_pages; return 0; } @@ -978,6 +1003,11 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; switch (msr) { + case HV_X64_MSR_VP_INDEX: + if (!host) + return 1; + hv->vp_index = (u32)data; + break; case HV_X64_MSR_APIC_ASSIST_PAGE: { u64 gfn; unsigned long addr; @@ -1089,18 +1119,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; switch (msr) { - case HV_X64_MSR_VP_INDEX: { - int r; - struct kvm_vcpu *v; - - kvm_for_each_vcpu(r, v, vcpu->kvm) { - if (v == vcpu) { - data = r; - break; - } - } + case HV_X64_MSR_VP_INDEX: + data = hv->vp_index; break; - } case HV_X64_MSR_EOI: return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); case HV_X64_MSR_ICR: diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index cd1119538add..e637631a9574 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -56,9 +56,10 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu); void kvm_hv_irq_routing_update(struct kvm *kvm); int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); -int kvm_hv_activate_synic(struct kvm_vcpu *vcpu); +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index a78b445ce411..af192895b1fc 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -724,8 +724,10 @@ void kvm_free_pit(struct kvm *kvm) struct kvm_pit *pit = kvm->arch.vpit; if (pit) { + mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev); + mutex_unlock(&kvm->slots_lock); kvm_pit_set_reinject(pit, false); hrtimer_cancel(&pit->pit_state.timer); kthread_destroy_worker(pit->worker); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index aafd399cf8c6..9b1dd114956a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -46,6 +46,7 @@ #include <asm/io.h> #include <asm/vmx.h> #include <asm/kvm_page_track.h> +#include "trace.h" /* * When setting this variable to true it enables Two-Dimensional-Paging @@ -3748,7 +3749,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) kvm_event_needs_reinjection(vcpu))) return false; - if (is_guest_mode(vcpu)) + if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) return false; return kvm_x86_ops->interrupt_allowed(vcpu); @@ -3780,6 +3781,38 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, + u64 fault_address, char *insn, int insn_len, + bool need_unprotect) +{ + int r = 1; + + switch (vcpu->arch.apf.host_apf_reason) { + default: + trace_kvm_page_fault(fault_address, error_code); + + if (need_unprotect && kvm_event_needs_reinjection(vcpu)) + kvm_mmu_unprotect_page_virt(vcpu, fault_address); + r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, + insn_len); + break; + case KVM_PV_REASON_PAGE_NOT_PRESENT: + vcpu->arch.apf.host_apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wait(fault_address); + local_irq_enable(); + break; + case KVM_PV_REASON_PAGE_READY: + vcpu->arch.apf.host_apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wake(fault_address); + local_irq_enable(); + break; + } + return r; +} +EXPORT_SYMBOL_GPL(kvm_handle_page_fault); + static bool check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index a276834950c1..d7d248a000dd 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -77,6 +77,9 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); +int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, + u64 fault_address, char *insn, int insn_len, + bool need_unprotect); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 905ea6052517..4d8141e533c3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -194,7 +194,6 @@ struct vcpu_svm { unsigned int3_injected; unsigned long int3_rip; - u32 apf_reason; /* cached guest cpuid flags for faster access */ bool nrips_enabled : 1; @@ -277,6 +276,10 @@ static int avic; module_param(avic, int, S_IRUGO); #endif +/* enable/disable Virtual VMLOAD VMSAVE */ +static int vls = true; +module_param(vls, int, 0444); + /* AVIC VM ID bit masks and lock */ static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR); static DEFINE_SPINLOCK(avic_vm_id_lock); @@ -633,11 +636,13 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm_set_interrupt_shadow(vcpu, 0); } -static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code, - bool reinject) +static void svm_queue_exception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + unsigned nr = vcpu->arch.exception.nr; + bool has_error_code = vcpu->arch.exception.has_error_code; + bool reinject = vcpu->arch.exception.reinject; + u32 error_code = vcpu->arch.exception.error_code; /* * If we are within a nested VM we'd better #VMEXIT and let the guest @@ -947,7 +952,7 @@ static void svm_enable_lbrv(struct vcpu_svm *svm) { u32 *msrpm = svm->msrpm; - svm->vmcb->control.lbr_ctl = 1; + svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); @@ -958,7 +963,7 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) { u32 *msrpm = svm->msrpm; - svm->vmcb->control.lbr_ctl = 0; + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0); @@ -1093,6 +1098,16 @@ static __init int svm_hardware_setup(void) } } + if (vls) { + if (!npt_enabled || + !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) || + !IS_ENABLED(CONFIG_X86_64)) { + vls = false; + } else { + pr_info("Virtual VMLOAD VMSAVE supported\n"); + } + } + return 0; err: @@ -1280,6 +1295,16 @@ static void init_vmcb(struct vcpu_svm *svm) if (avic) avic_init_vmcb(svm); + /* + * If hardware supports Virtual VMLOAD VMSAVE then enable it + * in VMCB and clear intercepts to avoid #VMEXIT. + */ + if (vls) { + clr_intercept(svm, INTERCEPT_VMLOAD); + clr_intercept(svm, INTERCEPT_VMSAVE); + svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + } + mark_all_dirty(svm->vmcb); enable_gif(svm); @@ -2096,34 +2121,11 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) static int pf_interception(struct vcpu_svm *svm) { u64 fault_address = svm->vmcb->control.exit_info_2; - u64 error_code; - int r = 1; + u64 error_code = svm->vmcb->control.exit_info_1; - switch (svm->apf_reason) { - default: - error_code = svm->vmcb->control.exit_info_1; - - trace_kvm_page_fault(fault_address, error_code); - if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu)) - kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); - r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, + return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address, svm->vmcb->control.insn_bytes, - svm->vmcb->control.insn_len); - break; - case KVM_PV_REASON_PAGE_NOT_PRESENT: - svm->apf_reason = 0; - local_irq_disable(); - kvm_async_pf_task_wait(fault_address); - local_irq_enable(); - break; - case KVM_PV_REASON_PAGE_READY: - svm->apf_reason = 0; - local_irq_disable(); - kvm_async_pf_task_wake(fault_address); - local_irq_enable(); - break; - } - return r; + svm->vmcb->control.insn_len, !npt_enabled); } static int db_interception(struct vcpu_svm *svm) @@ -2267,7 +2269,7 @@ static int io_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ - int size, in, string; + int size, in, string, ret; unsigned port; ++svm->vcpu.stat.io_exits; @@ -2279,10 +2281,16 @@ static int io_interception(struct vcpu_svm *svm) port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; svm->next_rip = svm->vmcb->control.exit_info_2; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); - return in ? kvm_fast_pio_in(vcpu, size, port) - : kvm_fast_pio_out(vcpu, size, port); + /* + * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + if (in) + return kvm_fast_pio_in(vcpu, size, port) && ret; + else + return kvm_fast_pio_out(vcpu, size, port) && ret; } static int nmi_interception(struct vcpu_svm *svm) @@ -2415,15 +2423,19 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, if (!is_guest_mode(&svm->vcpu)) return 0; + vmexit = nested_svm_intercept(svm); + if (vmexit != NESTED_EXIT_DONE) + return 0; + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = error_code; - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - - vmexit = nested_svm_intercept(svm); - if (vmexit == NESTED_EXIT_DONE) - svm->nested.exit_required = true; + if (svm->vcpu.arch.exception.nested_apf) + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; + else + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + svm->nested.exit_required = true; return vmexit; } @@ -2598,7 +2610,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->apf_reason == 0) + if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) return NESTED_EXIT_HOST; break; default: @@ -2645,7 +2657,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && - svm->apf_reason != 0) + svm->vcpu.arch.exception.nested_apf != 0) vmexit = NESTED_EXIT_DONE; break; } @@ -2702,7 +2714,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr dst->event_inj = from->event_inj; dst->event_inj_err = from->event_inj_err; dst->nested_cr3 = from->nested_cr3; - dst->lbr_ctl = from->lbr_ctl; + dst->virt_ext = from->virt_ext; } static int nested_svm_vmexit(struct vcpu_svm *svm) @@ -3008,7 +3020,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) /* We don't want to see VMMCALLs from a nested guest */ clr_intercept(svm, INTERCEPT_VMMCALL); - svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl; + svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; @@ -3055,6 +3067,7 @@ static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; struct page *page; + int ret; if (nested_svm_check_permissions(svm)) return 1; @@ -3064,18 +3077,19 @@ static int vmload_interception(struct vcpu_svm *svm) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(nested_vmcb, svm->vmcb); nested_svm_unmap(page); - return 1; + return ret; } static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; struct page *page; + int ret; if (nested_svm_check_permissions(svm)) return 1; @@ -3085,12 +3099,12 @@ static int vmsave_interception(struct vcpu_svm *svm) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(svm->vmcb, nested_vmcb); nested_svm_unmap(page); - return 1; + return ret; } static int vmrun_interception(struct vcpu_svm *svm) @@ -3123,25 +3137,29 @@ failed: static int stgi_interception(struct vcpu_svm *svm) { + int ret; + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); enable_gif(svm); - return 1; + return ret; } static int clgi_interception(struct vcpu_svm *svm) { + int ret; + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); disable_gif(svm); @@ -3152,7 +3170,7 @@ static int clgi_interception(struct vcpu_svm *svm) mark_dirty(svm->vmcb, VMCB_INTR); } - return 1; + return ret; } static int invlpga_interception(struct vcpu_svm *svm) @@ -3166,8 +3184,7 @@ static int invlpga_interception(struct vcpu_svm *svm) kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); - return 1; + return kvm_skip_emulated_instruction(&svm->vcpu); } static int skinit_interception(struct vcpu_svm *svm) @@ -3190,7 +3207,7 @@ static int xsetbv_interception(struct vcpu_svm *svm) if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(&svm->vcpu); } return 1; @@ -3286,8 +3303,7 @@ static int invlpg_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); - skip_emulated_instruction(&svm->vcpu); - return 1; + return kvm_skip_emulated_instruction(&svm->vcpu); } static int emulate_on_interception(struct vcpu_svm *svm) @@ -3437,9 +3453,7 @@ static int dr_interception(struct vcpu_svm *svm) kvm_register_write(&svm->vcpu, reg, val); } - skip_emulated_instruction(&svm->vcpu); - - return 1; + return kvm_skip_emulated_instruction(&svm->vcpu); } static int cr8_write_interception(struct vcpu_svm *svm) @@ -3562,6 +3576,7 @@ static int rdmsr_interception(struct vcpu_svm *svm) if (svm_get_msr(&svm->vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(&svm->vcpu, 0); + return 1; } else { trace_kvm_msr_read(ecx, msr_info.data); @@ -3570,9 +3585,8 @@ static int rdmsr_interception(struct vcpu_svm *svm) kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, msr_info.data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(&svm->vcpu); } - return 1; } static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) @@ -3698,11 +3712,11 @@ static int wrmsr_interception(struct vcpu_svm *svm) if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); + return 1; } else { trace_kvm_msr_write(ecx, data); - skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(&svm->vcpu); } - return 1; } static int msr_interception(struct vcpu_svm *svm) @@ -3731,8 +3745,7 @@ static int pause_interception(struct vcpu_svm *svm) static int nop_interception(struct vcpu_svm *svm) { - skip_emulated_instruction(&(svm->vcpu)); - return 1; + return kvm_skip_emulated_instruction(&(svm->vcpu)); } static int monitor_interception(struct vcpu_svm *svm) @@ -4117,7 +4130,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar); pr_err("%-20s%08x\n", "event_inj:", control->event_inj); pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err); - pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl); + pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext); pr_err("%-20s%016llx\n", "next_rip:", control->next_rip); pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page); pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id); @@ -4965,7 +4978,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) - svm->apf_reason = kvm_read_and_reset_pf_reason(); + svm->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); if (npt_enabled) { vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f76efad248ab..84e62acf2dd8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2422,28 +2422,41 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. */ -static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) +static int nested_vmx_check_exception(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned int nr = vcpu->arch.exception.nr; - if (!(vmcs12->exception_bitmap & (1u << nr))) + if (!((vmcs12->exception_bitmap & (1u << nr)) || + (nr == PF_VECTOR && vcpu->arch.exception.nested_apf))) return 0; + if (vcpu->arch.exception.nested_apf) { + vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code); + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, + PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | + INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, + vcpu->arch.apf.nested_apf_token); + return 1; + } + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, vmcs_read32(VM_EXIT_INTR_INFO), vmcs_readl(EXIT_QUALIFICATION)); return 1; } -static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code, - bool reinject) +static void vmx_queue_exception(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned nr = vcpu->arch.exception.nr; + bool has_error_code = vcpu->arch.exception.has_error_code; + bool reinject = vcpu->arch.exception.reinject; + u32 error_code = vcpu->arch.exception.error_code; u32 intr_info = nr | INTR_INFO_VALID_MASK; if (!reinject && is_guest_mode(vcpu) && - nested_vmx_check_exception(vcpu, nr)) + nested_vmx_check_exception(vcpu)) return; if (has_error_code) { @@ -3764,6 +3777,25 @@ static void free_kvm_area(void) } } +enum vmcs_field_type { + VMCS_FIELD_TYPE_U16 = 0, + VMCS_FIELD_TYPE_U64 = 1, + VMCS_FIELD_TYPE_U32 = 2, + VMCS_FIELD_TYPE_NATURAL_WIDTH = 3 +}; + +static inline int vmcs_field_type(unsigned long field) +{ + if (0x1 & field) /* the *_HIGH fields are all 32 bit */ + return VMCS_FIELD_TYPE_U32; + return (field >> 13) & 0x3 ; +} + +static inline int vmcs_field_readonly(unsigned long field) +{ + return (((field >> 10) & 0x3) == 1); +} + static void init_vmcs_shadow_fields(void) { int i, j; @@ -3789,14 +3821,22 @@ static void init_vmcs_shadow_fields(void) /* shadowed fields guest access without vmexit */ for (i = 0; i < max_shadow_read_write_fields; i++) { - clear_bit(shadow_read_write_fields[i], - vmx_vmwrite_bitmap); - clear_bit(shadow_read_write_fields[i], - vmx_vmread_bitmap); + unsigned long field = shadow_read_write_fields[i]; + + clear_bit(field, vmx_vmwrite_bitmap); + clear_bit(field, vmx_vmread_bitmap); + if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) { + clear_bit(field + 1, vmx_vmwrite_bitmap); + clear_bit(field + 1, vmx_vmread_bitmap); + } + } + for (i = 0; i < max_shadow_read_only_fields; i++) { + unsigned long field = shadow_read_only_fields[i]; + + clear_bit(field, vmx_vmread_bitmap); + if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) + clear_bit(field + 1, vmx_vmread_bitmap); } - for (i = 0; i < max_shadow_read_only_fields; i++) - clear_bit(shadow_read_only_fields[i], - vmx_vmread_bitmap); } static __init int alloc_kvm_area(void) @@ -4634,6 +4674,11 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu) return true; } +static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu)); +} + static int init_rmode_tss(struct kvm *kvm) { gfn_t fn; @@ -5664,14 +5709,11 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_page_fault(intr_info)) { - /* EPT won't cause page fault directly */ - BUG_ON(enable_ept); cr2 = vmcs_readl(EXIT_QUALIFICATION); - trace_kvm_page_fault(cr2, error_code); - - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, cr2); - return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0); + /* EPT won't cause page fault directly */ + WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept); + return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0, + true); } ex_no = intr_info & INTR_INFO_VECTOR_MASK; @@ -7214,25 +7256,6 @@ static int handle_vmresume(struct kvm_vcpu *vcpu) return nested_vmx_run(vcpu, false); } -enum vmcs_field_type { - VMCS_FIELD_TYPE_U16 = 0, - VMCS_FIELD_TYPE_U64 = 1, - VMCS_FIELD_TYPE_U32 = 2, - VMCS_FIELD_TYPE_NATURAL_WIDTH = 3 -}; - -static inline int vmcs_field_type(unsigned long field) -{ - if (0x1 & field) /* the *_HIGH fields are all 32 bit */ - return VMCS_FIELD_TYPE_U32; - return (field >> 13) & 0x3 ; -} - -static inline int vmcs_field_readonly(unsigned long field) -{ - return (((field >> 10) & 0x3) == 1); -} - /* * Read a vmcs12 field. Since these can have varying lengths and we return * one type, we chose the biggest type (u64) and zero-extend the return value @@ -8014,7 +8037,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) if (is_nmi(intr_info)) return false; else if (is_page_fault(intr_info)) - return enable_ept; + return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept; else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) return false; @@ -8418,9 +8441,15 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 2; + vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason; + vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; + if (exit_reason == EXIT_REASON_EPT_MISCONFIG) { + vcpu->run->internal.ndata++; + vcpu->run->internal.data[3] = + vmcs_read64(GUEST_PHYSICAL_ADDRESS); + } return 0; } @@ -8611,17 +8640,24 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { - u32 exit_intr_info; + u32 exit_intr_info = 0; + u16 basic_exit_reason = (u16)vmx->exit_reason; - if (!(vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY - || vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI)) + if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY + || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI)) return; - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - exit_intr_info = vmx->exit_intr_info; + if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + vmx->exit_intr_info = exit_intr_info; + + /* if exit due to PF check for async PF */ + if (is_page_fault(exit_intr_info)) + vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); /* Handle machine checks before interrupts are enabled */ - if (is_machine_check(exit_intr_info)) + if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY || + is_machine_check(exit_intr_info)) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ @@ -9589,23 +9625,26 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL); } +static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return 0; + + if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) || + !page_address_valid(vcpu, vmcs12->io_bitmap_b)) + return -EINVAL; + + return 0; +} + static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int maxphyaddr; - u64 addr; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return 0; - if (vmcs12_read_any(vcpu, MSR_BITMAP, &addr)) { - WARN_ON(1); - return -EINVAL; - } - maxphyaddr = cpuid_maxphyaddr(vcpu); - - if (!PAGE_ALIGNED(vmcs12->msr_bitmap) || - ((addr + PAGE_SIZE) >> maxphyaddr)) + if (!page_address_valid(vcpu, vmcs12->msr_bitmap)) return -EINVAL; return 0; @@ -10293,6 +10332,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -10429,8 +10471,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) return 1; } - vmcs12->launch_state = 1; - /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet @@ -10804,6 +10844,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { + vmcs12->launch_state = 1; + /* vm_entry_intr_info_field is cleared on exit. Emulate this * instead of reading the real value. */ vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c7266f7766d..5b8f07889f6a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -134,8 +134,6 @@ module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, S_IRUGO); -static bool __read_mostly backwards_tsc_observed = false; - #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -452,7 +450,12 @@ EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; - vcpu->arch.cr2 = fault->address; + vcpu->arch.exception.nested_apf = + is_guest_mode(vcpu) && fault->async_page_fault; + if (vcpu->arch.exception.nested_apf) + vcpu->arch.apf.nested_apf_token = fault->address; + else + vcpu->arch.cr2 = fault->address; kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); } EXPORT_SYMBOL_GPL(kvm_inject_page_fault); @@ -1719,7 +1722,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) &ka->master_cycle_now); ka->use_master_clock = host_tsc_clocksource && vcpus_matched - && !backwards_tsc_observed + && !ka->backwards_tsc_observed && !ka->boot_vcpu_runs_old_kvmclock; if (ka->use_master_clock) @@ -2060,8 +2063,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; - /* Bits 2:5 are reserved, Should be zero */ - if (data & 0x3c) + /* Bits 3:5 are reserved, Should be zero */ + if (data & 0x38) return 1; vcpu->arch.apf.msr_val = data; @@ -2077,6 +2080,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); + vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; kvm_async_pf_wakeup_all(vcpu); return 0; } @@ -2661,6 +2665,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_HYPERV_SYNIC: + case KVM_CAP_HYPERV_SYNIC2: + case KVM_CAP_HYPERV_VP_INDEX: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -3384,10 +3390,14 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return -EINVAL; switch (cap->cap) { + case KVM_CAP_HYPERV_SYNIC2: + if (cap->args[0]) + return -EINVAL; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; - return kvm_hv_activate_synic(vcpu); + return kvm_hv_activate_synic(vcpu, cap->cap == + KVM_CAP_HYPERV_SYNIC2); default: return -EINVAL; } @@ -4188,9 +4198,15 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; r = 0; + /* + * TODO: userspace has to take care of races with VCPU_RUN, so + * kvm_gen_update_masterclock() can be cut down to locked + * pvclock_update_vm_gtod_copy(). + */ + kvm_gen_update_masterclock(kvm); now_ns = get_kvmclock_ns(kvm); kvm->arch.kvmclock_offset += user_ns.clock - now_ns; - kvm_gen_update_masterclock(kvm); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } case KVM_GET_CLOCK: { @@ -6347,10 +6363,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) kvm_update_dr7(vcpu); } - kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code, - vcpu->arch.exception.reinject); + kvm_x86_ops->queue_exception(vcpu); return 0; } @@ -7676,6 +7689,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) struct msr_data msr; struct kvm *kvm = vcpu->kvm; + kvm_hv_vcpu_postcreate(vcpu); + if (vcpu_load(vcpu)) return; msr.data = 0x0; @@ -7829,8 +7844,8 @@ int kvm_arch_hardware_enable(void) */ if (backwards_tsc) { u64 delta_cyc = max_tsc - local_tsc; - backwards_tsc_observed = true; list_for_each_entry(kvm, &vm_list, vm_list) { + kvm->arch.backwards_tsc_observed = true; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; vcpu->arch.last_host_tsc = local_tsc; @@ -8576,6 +8591,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, fault.error_code = 0; fault.nested_page_fault = false; fault.address = work->arch.token; + fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); } } @@ -8598,6 +8614,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, fault.error_code = 0; fault.nested_page_fault = false; fault.address = work->arch.token; + fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); } vcpu->arch.apf.halted = false; diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index 00f54a91bb4b..28775f55bde2 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -26,6 +26,7 @@ int save_i387_registers(int pid, unsigned long *fp_regs) int save_fp_registers(int pid, unsigned long *fp_regs) { +#ifdef PTRACE_GETREGSET struct iovec iov; if (have_xstate_support) { @@ -34,9 +35,9 @@ int save_fp_registers(int pid, unsigned long *fp_regs) if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) return -errno; return 0; - } else { + } else +#endif return save_i387_registers(pid, fp_regs); - } } int restore_i387_registers(int pid, unsigned long *fp_regs) @@ -48,6 +49,7 @@ int restore_i387_registers(int pid, unsigned long *fp_regs) int restore_fp_registers(int pid, unsigned long *fp_regs) { +#ifdef PTRACE_SETREGSET struct iovec iov; if (have_xstate_support) { @@ -56,9 +58,9 @@ int restore_fp_registers(int pid, unsigned long *fp_regs) if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) return -errno; return 0; - } else { + } else +#endif return restore_i387_registers(pid, fp_regs); - } } #ifdef __i386__ @@ -122,6 +124,7 @@ int put_fp_registers(int pid, unsigned long *regs) void arch_init_registers(int pid) { +#ifdef PTRACE_GETREGSET struct _xstate fp_regs; struct iovec iov; @@ -129,6 +132,7 @@ void arch_init_registers(int pid) iov.iov_len = sizeof(struct _xstate); if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) == 0) have_xstate_support = 1; +#endif } #endif diff --git a/arch/x86/um/setjmp_32.S b/arch/x86/um/setjmp_32.S index b766792c9933..39053192918d 100644 --- a/arch/x86/um/setjmp_32.S +++ b/arch/x86/um/setjmp_32.S @@ -16,9 +16,9 @@ .text .align 4 - .globl setjmp - .type setjmp, @function -setjmp: + .globl kernel_setjmp + .type kernel_setjmp, @function +kernel_setjmp: #ifdef _REGPARM movl %eax,%edx #else @@ -35,13 +35,13 @@ setjmp: movl %ecx,20(%edx) # Return address ret - .size setjmp,.-setjmp + .size kernel_setjmp,.-kernel_setjmp .text .align 4 - .globl longjmp - .type longjmp, @function -longjmp: + .globl kernel_longjmp + .type kernel_longjmp, @function +kernel_longjmp: #ifdef _REGPARM xchgl %eax,%edx #else @@ -55,4 +55,4 @@ longjmp: movl 16(%edx),%edi jmp *20(%edx) - .size longjmp,.-longjmp + .size kernel_longjmp,.-kernel_longjmp diff --git a/arch/x86/um/setjmp_64.S b/arch/x86/um/setjmp_64.S index 45f547b4043e..c56942e1a38c 100644 --- a/arch/x86/um/setjmp_64.S +++ b/arch/x86/um/setjmp_64.S @@ -18,9 +18,9 @@ .text .align 4 - .globl setjmp - .type setjmp, @function -setjmp: + .globl kernel_setjmp + .type kernel_setjmp, @function +kernel_setjmp: pop %rsi # Return address, and adjust the stack xorl %eax,%eax # Return value movq %rbx,(%rdi) @@ -34,13 +34,13 @@ setjmp: movq %rsi,56(%rdi) # Return address ret - .size setjmp,.-setjmp + .size kernel_setjmp,.-kernel_setjmp .text .align 4 - .globl longjmp - .type longjmp, @function -longjmp: + .globl kernel_longjmp + .type kernel_longjmp, @function +kernel_longjmp: movl %esi,%eax # Return value (int) movq (%rdi),%rbx movq 8(%rdi),%rsp @@ -51,4 +51,4 @@ longjmp: movq 48(%rdi),%r15 jmp *56(%rdi) - .size longjmp,.-longjmp + .size kernel_longjmp,.-kernel_longjmp diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index cb3c22370cf5..ae4cd58c0c7a 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -5,7 +5,7 @@ #include <sys/mman.h> #include <sys/user.h> #define __FRAME_OFFSETS -#include <asm/ptrace.h> +#include <linux/ptrace.h> #include <asm/types.h> #ifdef __i386__ @@ -50,7 +50,11 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else +#if defined(PTRACE_GETREGSET) && defined(PTRACE_SETREGSET) DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long)); +#else + DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); +#endif DEFINE_LONGS(HOST_BX, RBX); DEFINE_LONGS(HOST_CX, RCX); DEFINE_LONGS(HOST_DI, RDI); diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index c04efde775a5..2d716ebc5a5e 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -5,6 +5,7 @@ generic-y += dma-contiguous.h generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h +generic-y += fb.h generic-y += hardirq.h generic-y += irq_regs.h generic-y += irq_work.h diff --git a/arch/xtensa/include/asm/fb.h b/arch/xtensa/include/asm/fb.h deleted file mode 100644 index c7df38030992..000000000000 --- a/arch/xtensa/include/asm/fb.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_FB_H_ -#define _ASM_FB_H_ -#include <linux/fb.h> - -#define fb_pgprotect(...) do {} while (0) - -static inline int fb_is_primary_device(struct fb_info *info) -{ - return 0; -} - -#endif /* _ASM_FB_H_ */ diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h index 94c44abf15e4..60e0d6a45795 100644 --- a/arch/xtensa/include/asm/flat.h +++ b/arch/xtensa/include/asm/flat.h @@ -1,11 +1,22 @@ #ifndef __ASM_XTENSA_FLAT_H #define __ASM_XTENSA_FLAT_H +#include <asm/unaligned.h> + #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval ) put_unaligned(val, rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = get_unaligned((__force u32 *)rp); + return 0; +} +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + put_unaligned(addr, (__force u32 *)rp); + return 0; +} #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/certs/Makefile b/certs/Makefile index 4119bb376ea1..847361ce14d1 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -26,7 +26,7 @@ quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2)) targets += x509_certificate_list $(obj)/x509_certificate_list: scripts/extract-cert $(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(SYSTEM_TRUSTED_KEYS_FILENAME) FORCE $(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS)) -endif +endif # CONFIG_SYSTEM_TRUSTED_KEYRING clean-files := x509_certificate_list .x509.list @@ -87,7 +87,7 @@ $(obj)/x509.genkey: @echo >>$@ "keyUsage=digitalSignature" @echo >>$@ "subjectKeyIdentifier=hash" @echo >>$@ "authorityKeyIdentifier=keyid" -endif +endif # CONFIG_MODULE_SIG_KEY $(eval $(call config_filename,MODULE_SIG_KEY)) @@ -102,4 +102,4 @@ $(obj)/system_certificates.o: $(obj)/signing_key.x509 targets += signing_key.x509 $(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE $(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY)) -endif +endif # CONFIG_MODULE_SIG diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 3556d8eb54a7..92a3d540d920 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -287,7 +287,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern) goto unlock; sock_init_data(newsock, sk2); - sock_graft(sk2, newsock); + security_sock_graft(sk2, newsock); security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 854d428e2a2d..ddb01e9fa5b2 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -147,7 +147,7 @@ static unsigned int ec_storm_threshold __read_mostly = 8; module_param(ec_storm_threshold, uint, 0644); MODULE_PARM_DESC(ec_storm_threshold, "Maxim false GPE numbers not considered as GPE storm"); -static bool ec_freeze_events __read_mostly = true; +static bool ec_freeze_events __read_mostly = false; module_param(ec_freeze_events, bool, 0644); MODULE_PARM_DESC(ec_freeze_events, "Disabling event handling during suspend/resume"); @@ -1870,24 +1870,6 @@ error: } #ifdef CONFIG_PM_SLEEP -static int acpi_ec_suspend_noirq(struct device *dev) -{ - struct acpi_ec *ec = - acpi_driver_data(to_acpi_device(dev)); - - acpi_ec_enter_noirq(ec); - return 0; -} - -static int acpi_ec_resume_noirq(struct device *dev) -{ - struct acpi_ec *ec = - acpi_driver_data(to_acpi_device(dev)); - - acpi_ec_leave_noirq(ec); - return 0; -} - static int acpi_ec_suspend(struct device *dev) { struct acpi_ec *ec = @@ -1909,7 +1891,6 @@ static int acpi_ec_resume(struct device *dev) #endif static const struct dev_pm_ops acpi_ec_pm = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend_noirq, acpi_ec_resume_noirq) SET_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend, acpi_ec_resume) }; diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c index 830299a74b84..7c352cba0528 100644 --- a/drivers/acpi/irq.c +++ b/drivers/acpi/irq.c @@ -24,7 +24,7 @@ static struct fwnode_handle *acpi_gsi_domain_id; * * irq location updated with irq value [>0 on success, 0 on failure] * - * Returns: linux IRQ number on success (>0) + * Returns: 0 on success * -EINVAL on failure */ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) @@ -37,7 +37,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) * *irq == 0 means no mapping, that should * be reported as a failure */ - return (*irq > 0) ? *irq : -EINVAL; + return (*irq > 0) ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index bd86b809c848..b4fbb9929482 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -12,6 +12,7 @@ */ #include <linux/acpi.h> +#include <linux/dmi.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "../internal.h" @@ -20,6 +21,10 @@ * Some ACPI devices are hidden (status == 0x0) in recent BIOS-es because * some recent Windows drivers bind to one device but poke at multiple * devices at the same time, so the others get hidden. + * + * Some BIOS-es (temporarily) hide specific APCI devices to work around Windows + * driver bugs. We use DMI matching to match known cases of this. + * * We work around this by always reporting ACPI_STA_DEFAULT for these * devices. Note this MUST only be done for devices where this is safe. * @@ -31,14 +36,16 @@ struct always_present_id { struct acpi_device_id hid[2]; struct x86_cpu_id cpu_ids[2]; + struct dmi_system_id dmi_ids[2]; /* Optional */ const char *uid; }; #define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, } -#define ENTRY(hid, uid, cpu_models) { \ +#define ENTRY(hid, uid, cpu_models, dmi...) { \ { { hid, }, {} }, \ { cpu_models, {} }, \ + { { .matches = dmi }, {} }, \ uid, \ } @@ -47,13 +54,35 @@ static const struct always_present_id always_present_ids[] = { * Bay / Cherry Trail PWM directly poked by GPU driver in win10, * but Linux uses a separate PWM driver, harmless if not used. */ - ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1)), - ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT)), + ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1), {}), + ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}), /* * The INT0002 device is necessary to clear wakeup interrupt sources * on Cherry Trail devices, without it we get nobody cared IRQ msgs. */ - ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT)), + ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}), + /* + * On the Dell Venue 11 Pro 7130 the DSDT hides the touchscreen ACPI + * device until a certain time after _SB.PCI0.GFX0.LCD.LCD1._ON gets + * called has passed *and* _STA has been called at least 3 times since. + */ + ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"), + }), + /* + * The GPD win BIOS dated 20170320 has disabled the accelerometer, the + * drivers sometimes cause crashes under Windows and this is how the + * manufacturer has solved this :| Note that the the DMI data is less + * generic then it seems, a board_vendor of "AMI Corporation" is quite + * rare and a board_name of "Default String" also is rare. + */ + ENTRY("KIOX000A", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Default string"), + DMI_MATCH(DMI_PRODUCT_NAME, "Default string"), + DMI_MATCH(DMI_BIOS_DATE, "03/20/2017") + }), }; bool acpi_device_always_present(struct acpi_device *adev) @@ -76,6 +105,10 @@ bool acpi_device_always_present(struct acpi_device *adev) if (!x86_match_cpu(always_present_ids[i].cpu_ids)) continue; + if (always_present_ids[i].dmi_ids[0].matches[0].slot && + !dmi_check_system(always_present_ids[i].dmi_ids)) + continue; + if (old_status != ACPI_STA_DEFAULT) /* Log only once */ dev_info(&adev->dev, "Device [%s] is in always present list\n", diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 185a52581cfa..156ab57bca77 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -272,6 +272,8 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev, value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (!strcmp(buf, "any") || !strcmp(buf, "any\n")) value = PM_QOS_LATENCY_ANY; + else + return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; diff --git a/drivers/base/property.c b/drivers/base/property.c index 692007e5a94b..edf02c1b5845 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -253,10 +253,10 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname) { bool ret; - ret = fwnode_call_int_op(fwnode, property_present, propname); + ret = fwnode_call_bool_op(fwnode, property_present, propname); if (ret == false && !IS_ERR_OR_NULL(fwnode) && !IS_ERR_OR_NULL(fwnode->secondary)) - ret = fwnode_call_int_op(fwnode->secondary, property_present, + ret = fwnode_call_bool_op(fwnode->secondary, property_present, propname); return ret; } @@ -1027,7 +1027,7 @@ EXPORT_SYMBOL_GPL(fwnode_handle_put); */ bool fwnode_device_is_available(struct fwnode_handle *fwnode) { - return fwnode_call_int_op(fwnode, device_is_available); + return fwnode_call_bool_op(fwnode, device_is_available); } EXPORT_SYMBOL_GPL(fwnode_device_is_available); diff --git a/drivers/char/random.c b/drivers/char/random.c index 23cab7a8c1c1..afa3ce7d3e72 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -288,7 +288,6 @@ #define SEC_XFER_SIZE 512 #define EXTRACT_SIZE 10 -#define DEBUG_RANDOM_BOOT 0 #define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long)) @@ -437,6 +436,7 @@ static void _extract_crng(struct crng_state *crng, static void _crng_backtrack_protect(struct crng_state *crng, __u8 tmp[CHACHA20_BLOCK_SIZE], int used); static void process_random_ready_list(void); +static void _get_random_bytes(void *buf, int nbytes); /********************************************************************** * @@ -777,7 +777,7 @@ static void crng_initialize(struct crng_state *crng) _extract_entropy(&input_pool, &crng->state[4], sizeof(__u32) * 12, 0); else - get_random_bytes(&crng->state[4], sizeof(__u32) * 12); + _get_random_bytes(&crng->state[4], sizeof(__u32) * 12); for (i = 4; i < 16; i++) { if (!arch_get_random_seed_long(&rv) && !arch_get_random_long(&rv)) @@ -851,11 +851,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } } -static inline void crng_wait_ready(void) -{ - wait_event_interruptible(crng_init_wait, crng_ready()); -} - static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA20_BLOCK_SIZE]) { @@ -1477,22 +1472,44 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, return ret; } +#define warn_unseeded_randomness(previous) \ + _warn_unseeded_randomness(__func__, (void *) _RET_IP_, (previous)) + +static void _warn_unseeded_randomness(const char *func_name, void *caller, + void **previous) +{ +#ifdef CONFIG_WARN_ALL_UNSEEDED_RANDOM + const bool print_once = false; +#else + static bool print_once __read_mostly; +#endif + + if (print_once || + crng_ready() || + (previous && (caller == READ_ONCE(*previous)))) + return; + WRITE_ONCE(*previous, caller); +#ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM + print_once = true; +#endif + pr_notice("random: %s called from %pF with crng_init=%d\n", + func_name, caller, crng_init); +} + /* * This function is the exported kernel interface. It returns some * number of good random numbers, suitable for key generation, seeding * TCP sequence numbers, etc. It does not rely on the hardware random * number generator. For random bytes direct from the hardware RNG - * (when available), use get_random_bytes_arch(). + * (when available), use get_random_bytes_arch(). In order to ensure + * that the randomness provided by this function is okay, the function + * wait_for_random_bytes() should be called and return 0 at least once + * at any point prior. */ -void get_random_bytes(void *buf, int nbytes) +static void _get_random_bytes(void *buf, int nbytes) { __u8 tmp[CHACHA20_BLOCK_SIZE]; -#if DEBUG_RANDOM_BOOT > 0 - if (!crng_ready()) - printk(KERN_NOTICE "random: %pF get_random_bytes called " - "with crng_init = %d\n", (void *) _RET_IP_, crng_init); -#endif trace_get_random_bytes(nbytes, _RET_IP_); while (nbytes >= CHACHA20_BLOCK_SIZE) { @@ -1509,9 +1526,35 @@ void get_random_bytes(void *buf, int nbytes) crng_backtrack_protect(tmp, CHACHA20_BLOCK_SIZE); memzero_explicit(tmp, sizeof(tmp)); } + +void get_random_bytes(void *buf, int nbytes) +{ + static void *previous; + + warn_unseeded_randomness(&previous); + _get_random_bytes(buf, nbytes); +} EXPORT_SYMBOL(get_random_bytes); /* + * Wait for the urandom pool to be seeded and thus guaranteed to supply + * cryptographically secure random numbers. This applies to: the /dev/urandom + * device, the get_random_bytes function, and the get_random_{u32,u64,int,long} + * family of functions. Using any of these functions without first calling + * this function forfeits the guarantee of security. + * + * Returns: 0 if the urandom pool has been seeded. + * -ERESTARTSYS if the function was interrupted by a signal. + */ +int wait_for_random_bytes(void) +{ + if (likely(crng_ready())) + return 0; + return wait_event_interruptible(crng_init_wait, crng_ready()); +} +EXPORT_SYMBOL(wait_for_random_bytes); + +/* * Add a callback function that will be invoked when the nonblocking * pool is initialised. * @@ -1865,6 +1908,8 @@ const struct file_operations urandom_fops = { SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int, flags) { + int ret; + if (flags & ~(GRND_NONBLOCK|GRND_RANDOM)) return -EINVAL; @@ -1877,9 +1922,9 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, if (!crng_ready()) { if (flags & GRND_NONBLOCK) return -EAGAIN; - crng_wait_ready(); - if (signal_pending(current)) - return -ERESTARTSYS; + ret = wait_for_random_bytes(); + if (unlikely(ret)) + return ret; } return urandom_read(NULL, buf, count, NULL); } @@ -2040,15 +2085,19 @@ static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_ /* * Get a random word for internal kernel use only. The quality of the random * number is either as good as RDRAND or as good as /dev/urandom, with the - * goal of being quite fast and not depleting entropy. + * goal of being quite fast and not depleting entropy. In order to ensure + * that the randomness provided by this function is okay, the function + * wait_for_random_bytes() should be called and return 0 at least once + * at any point prior. */ static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); u64 get_random_u64(void) { u64 ret; - bool use_lock = READ_ONCE(crng_init) < 2; + bool use_lock; unsigned long flags = 0; struct batched_entropy *batch; + static void *previous; #if BITS_PER_LONG == 64 if (arch_get_random_long((unsigned long *)&ret)) @@ -2059,6 +2108,9 @@ u64 get_random_u64(void) return ret; #endif + warn_unseeded_randomness(&previous); + + use_lock = READ_ONCE(crng_init) < 2; batch = &get_cpu_var(batched_entropy_u64); if (use_lock) read_lock_irqsave(&batched_entropy_reset_lock, flags); @@ -2078,13 +2130,17 @@ static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32); u32 get_random_u32(void) { u32 ret; - bool use_lock = READ_ONCE(crng_init) < 2; + bool use_lock; unsigned long flags = 0; struct batched_entropy *batch; + static void *previous; if (arch_get_random_int(&ret)) return ret; + warn_unseeded_randomness(&previous); + + use_lock = READ_ONCE(crng_init) < 2; batch = &get_cpu_var(batched_entropy_u32); if (use_lock) read_lock_irqsave(&batched_entropy_reset_lock, flags); diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index d406b087553f..68ca2d9fcd73 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -221,6 +221,7 @@ config COMMON_CLK_VC5 source "drivers/clk/bcm/Kconfig" source "drivers/clk/hisilicon/Kconfig" +source "drivers/clk/imgtec/Kconfig" source "drivers/clk/keystone/Kconfig" source "drivers/clk/mediatek/Kconfig" source "drivers/clk/meson/Kconfig" diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 4f6a812342ed..cd376b3fb47a 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -60,6 +60,7 @@ obj-y += bcm/ obj-$(CONFIG_ARCH_BERLIN) += berlin/ obj-$(CONFIG_H8300) += h8300/ obj-$(CONFIG_ARCH_HISI) += hisilicon/ +obj-y += imgtec/ obj-$(CONFIG_ARCH_MXC) += imx/ obj-$(CONFIG_MACH_INGENIC) += ingenic/ obj-$(CONFIG_ARCH_KEYSTONE) += keystone/ diff --git a/drivers/clk/imgtec/Kconfig b/drivers/clk/imgtec/Kconfig new file mode 100644 index 000000000000..f6dcb748e9c4 --- /dev/null +++ b/drivers/clk/imgtec/Kconfig @@ -0,0 +1,9 @@ +config COMMON_CLK_BOSTON + bool "Clock driver for MIPS Boston boards" + depends on MIPS || COMPILE_TEST + select MFD_SYSCON + ---help--- + Enable this to support the system & CPU clocks on the MIPS Boston + development board from Imagination Technologies. These are simple + fixed rate clocks whose rate is determined by reading a platform + provided register. diff --git a/drivers/clk/imgtec/Makefile b/drivers/clk/imgtec/Makefile new file mode 100644 index 000000000000..ac779b8c22f2 --- /dev/null +++ b/drivers/clk/imgtec/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_COMMON_CLK_BOSTON) += clk-boston.o diff --git a/drivers/clk/imgtec/clk-boston.c b/drivers/clk/imgtec/clk-boston.c new file mode 100644 index 000000000000..f18f10351785 --- /dev/null +++ b/drivers/clk/imgtec/clk-boston.c @@ -0,0 +1,103 @@ +/* + * Copyright (C) 2016-2017 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * 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. + */ + +#define pr_fmt(fmt) "clk-boston: " fmt + +#include <linux/clk-provider.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/regmap.h> +#include <linux/slab.h> +#include <linux/mfd/syscon.h> + +#include <dt-bindings/clock/boston-clock.h> + +#define BOSTON_PLAT_MMCMDIV 0x30 +# define BOSTON_PLAT_MMCMDIV_CLK0DIV (0xff << 0) +# define BOSTON_PLAT_MMCMDIV_INPUT (0xff << 8) +# define BOSTON_PLAT_MMCMDIV_MUL (0xff << 16) +# define BOSTON_PLAT_MMCMDIV_CLK1DIV (0xff << 24) + +#define BOSTON_CLK_COUNT 3 + +static u32 ext_field(u32 val, u32 mask) +{ + return (val & mask) >> (ffs(mask) - 1); +} + +static void __init clk_boston_setup(struct device_node *np) +{ + unsigned long in_freq, cpu_freq, sys_freq; + uint mmcmdiv, mul, cpu_div, sys_div; + struct clk_hw_onecell_data *onecell; + struct regmap *regmap; + struct clk_hw *hw; + int err; + + regmap = syscon_node_to_regmap(np->parent); + if (IS_ERR(regmap)) { + pr_err("failed to find regmap\n"); + return; + } + + err = regmap_read(regmap, BOSTON_PLAT_MMCMDIV, &mmcmdiv); + if (err) { + pr_err("failed to read mmcm_div register: %d\n", err); + return; + } + + in_freq = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_INPUT) * 1000000; + mul = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_MUL); + + sys_div = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_CLK0DIV); + sys_freq = mult_frac(in_freq, mul, sys_div); + + cpu_div = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_CLK1DIV); + cpu_freq = mult_frac(in_freq, mul, cpu_div); + + onecell = kzalloc(sizeof(*onecell) + + (BOSTON_CLK_COUNT * sizeof(struct clk_hw *)), + GFP_KERNEL); + if (!onecell) + return; + + onecell->num = BOSTON_CLK_COUNT; + + hw = clk_hw_register_fixed_rate(NULL, "input", NULL, 0, in_freq); + if (IS_ERR(hw)) { + pr_err("failed to register input clock: %ld\n", PTR_ERR(hw)); + return; + } + onecell->hws[BOSTON_CLK_INPUT] = hw; + + hw = clk_hw_register_fixed_rate(NULL, "sys", "input", 0, sys_freq); + if (IS_ERR(hw)) { + pr_err("failed to register sys clock: %ld\n", PTR_ERR(hw)); + return; + } + onecell->hws[BOSTON_CLK_SYS] = hw; + + hw = clk_hw_register_fixed_rate(NULL, "cpu", "input", 0, cpu_freq); + if (IS_ERR(hw)) { + pr_err("failed to register cpu clock: %ld\n", PTR_ERR(hw)); + return; + } + onecell->hws[BOSTON_CLK_CPU] = hw; + + err = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, onecell); + if (err) + pr_err("failed to add DT provider: %d\n", err); +} + +/* + * Use CLK_OF_DECLARE so that this driver is probed early enough to provide the + * CPU frequency for use with the GIC or cop0 counters/timers. + */ +CLK_OF_DECLARE(clk_boston, "img,boston-clock", clk_boston_setup); diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c index 418042201e6d..ea6d62547b10 100644 --- a/drivers/cpufreq/arm_big_little.c +++ b/drivers/cpufreq/arm_big_little.c @@ -540,7 +540,7 @@ static void bL_cpufreq_ready(struct cpufreq_policy *policy) &power_coefficient); cdev[cur_cluster] = of_cpufreq_power_cooling_register(np, - policy->related_cpus, power_coefficient, NULL); + policy, power_coefficient, NULL); if (IS_ERR(cdev[cur_cluster])) { dev_err(cpu_dev, "running cpufreq without cooling device: %ld\n", diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index c943787d761e..fef3c2160691 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -326,7 +326,7 @@ static void cpufreq_ready(struct cpufreq_policy *policy) &power_coefficient); priv->cdev = of_cpufreq_power_cooling_register(np, - policy->related_cpus, power_coefficient, NULL); + policy, power_coefficient, NULL); if (IS_ERR(priv->cdev)) { dev_err(priv->cpu_dev, "running cpufreq without cooling device: %ld\n", diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index d362739a71f3..e75880eb037d 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -170,11 +170,10 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) unsigned int i = 0, count = 0, ret = -ENOMEM; struct cpufreq_stats *stats; unsigned int alloc_size; - struct cpufreq_frequency_table *pos, *table; + struct cpufreq_frequency_table *pos; - /* We need cpufreq table for creating stats table */ - table = policy->freq_table; - if (unlikely(!table)) + count = cpufreq_table_count_valid_entries(policy); + if (!count) return; /* stats already initialized */ @@ -185,10 +184,6 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) if (!stats) return; - /* Find total allocation size */ - cpufreq_for_each_valid_entry(pos, table) - count++; - alloc_size = count * sizeof(int) + count * sizeof(u64); alloc_size += count * count * sizeof(int); @@ -205,7 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) stats->max_state = count; /* Find valid-unique entries */ - cpufreq_for_each_valid_entry(pos, table) + cpufreq_for_each_valid_entry(pos, policy->freq_table) if (freq_table_get_index(stats, pos->frequency) == -1) stats->freq_table[i++] = pos->frequency; diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c index 3575b82210ba..4ee0431579c1 100644 --- a/drivers/cpufreq/dbx500-cpufreq.c +++ b/drivers/cpufreq/dbx500-cpufreq.c @@ -43,7 +43,7 @@ static int dbx500_cpufreq_exit(struct cpufreq_policy *policy) static void dbx500_cpufreq_ready(struct cpufreq_policy *policy) { - cdev = cpufreq_cooling_register(policy->cpus); + cdev = cpufreq_cooling_register(policy); if (IS_ERR(cdev)) pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev)); else diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index d6f323560da3..b7fb8b7c980d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -572,7 +572,7 @@ static int min_perf_pct_min(void) int turbo_pstate = cpu->pstate.turbo_pstate; return turbo_pstate ? - DIV_ROUND_UP(cpu->pstate.min_pstate * 100, turbo_pstate) : 0; + (cpu->pstate.min_pstate * 100 / turbo_pstate) : 0; } static s16 intel_pstate_get_epb(struct cpudata *cpu_data) diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index fd1886faf33a..f9f00fb4bc3a 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -320,9 +320,7 @@ static void mtk_cpufreq_ready(struct cpufreq_policy *policy) of_property_read_u32(np, DYNAMIC_POWER, &capacitance); info->cdev = of_cpufreq_power_cooling_register(np, - policy->related_cpus, - capacitance, - NULL); + policy, capacitance, NULL); if (IS_ERR(info->cdev)) { dev_err(info->cpu_dev, diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index e2ea433a5f9c..4ada55b8856e 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -278,8 +278,7 @@ static void qoriq_cpufreq_ready(struct cpufreq_policy *policy) struct device_node *np = of_get_cpu_node(policy->cpu, NULL); if (of_find_property(np, "#cooling-cells", NULL)) { - cpud->cdev = of_cpufreq_cooling_register(np, - policy->related_cpus); + cpud->cdev = of_cpufreq_cooling_register(np, policy); if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) { pr_err("cpu%d is not running as cooling device: %ld\n", diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index a9482023d7d3..dad4e5bad827 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -1204,7 +1204,9 @@ static int atmel_sha_finup(struct ahash_request *req) ctx->flags |= SHA_FLAGS_FINUP; err1 = atmel_sha_update(req); - if (err1 == -EINPROGRESS || err1 == -EBUSY) + if (err1 == -EINPROGRESS || + (err1 == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) return err1; /* diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index fde399c88779..0488b7f81dcf 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -882,10 +882,10 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err, { struct ablkcipher_request *req = context; struct ablkcipher_edesc *edesc; -#ifdef DEBUG struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req); int ivsize = crypto_ablkcipher_ivsize(ablkcipher); +#ifdef DEBUG dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); #endif @@ -904,6 +904,14 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err, #endif ablkcipher_unmap(jrdev, edesc, req); + + /* + * The crypto API expects us to set the IV (req->info) to the last + * ciphertext block. This is used e.g. by the CTS mode. + */ + scatterwalk_map_and_copy(req->info, req->dst, req->nbytes - ivsize, + ivsize, 0); + kfree(edesc); ablkcipher_request_complete(req, err); @@ -914,10 +922,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err, { struct ablkcipher_request *req = context; struct ablkcipher_edesc *edesc; -#ifdef DEBUG struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req); int ivsize = crypto_ablkcipher_ivsize(ablkcipher); +#ifdef DEBUG dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); #endif @@ -935,6 +943,14 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err, #endif ablkcipher_unmap(jrdev, edesc, req); + + /* + * The crypto API expects us to set the IV (req->info) to the last + * ciphertext block. + */ + scatterwalk_map_and_copy(req->info, req->src, req->nbytes - ivsize, + ivsize, 0); + kfree(edesc); ablkcipher_request_complete(req, err); diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 7c44c90ad593..910ec61cae09 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -396,7 +396,7 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in, ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result); if (!ret) { /* in progress */ - wait_for_completion_interruptible(&result.completion); + wait_for_completion(&result.completion); ret = result.err; #ifdef DEBUG print_hex_dump(KERN_ERR, diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index 1bb2816a9b4d..c425d4adaf2a 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -149,7 +149,7 @@ int gen_split_key(struct device *jrdev, u8 *key_out, ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result); if (!ret) { /* in progress */ - wait_for_completion_interruptible(&result.completion); + wait_for_completion(&result.completion); ret = result.err; #ifdef DEBUG print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ", diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c index 1b220f3ed017..df21d996db7e 100644 --- a/drivers/crypto/cavium/cpt/cptvf_algs.c +++ b/drivers/crypto/cavium/cpt/cptvf_algs.c @@ -222,17 +222,17 @@ static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc) return -EINPROGRESS; } -int cvm_encrypt(struct ablkcipher_request *req) +static int cvm_encrypt(struct ablkcipher_request *req) { return cvm_enc_dec(req, true); } -int cvm_decrypt(struct ablkcipher_request *req) +static int cvm_decrypt(struct ablkcipher_request *req) { return cvm_enc_dec(req, false); } -int cvm_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key, +static int cvm_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key, u32 keylen) { struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher); @@ -336,7 +336,7 @@ static int cvm_ecb_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key, return cvm_setkey(cipher, key, keylen, DES3_ECB); } -int cvm_enc_dec_init(struct crypto_tfm *tfm) +static int cvm_enc_dec_init(struct crypto_tfm *tfm) { struct cvm_enc_ctx *ctx = crypto_tfm_ctx(tfm); diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index cfc723a10610..0e8160701833 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -898,26 +898,20 @@ static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv) u8 *key; unsigned int keylen; - cipher = crypto_alloc_cipher("aes-generic", 0, 0); + cipher = ablkctx->aes_generic; memcpy(iv, req->info, AES_BLOCK_SIZE); - if (IS_ERR(cipher)) { - ret = -ENOMEM; - goto out; - } keylen = ablkctx->enckey_len / 2; key = ablkctx->key + keylen; ret = crypto_cipher_setkey(cipher, key, keylen); if (ret) - goto out1; + goto out; crypto_cipher_encrypt_one(cipher, iv, iv); for (i = 0; i < (reqctx->processed / AES_BLOCK_SIZE); i++) gf128mul_x_ble((le128 *)iv, (le128 *)iv); crypto_cipher_decrypt_one(cipher, iv, iv); -out1: - crypto_free_cipher(cipher); out: return ret; } @@ -1261,6 +1255,17 @@ static int chcr_cra_init(struct crypto_tfm *tfm) pr_err("failed to allocate fallback for %s\n", alg->cra_name); return PTR_ERR(ablkctx->sw_cipher); } + + if (get_cryptoalg_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_XTS) { + /* To update tweak*/ + ablkctx->aes_generic = crypto_alloc_cipher("aes-generic", 0, 0); + if (IS_ERR(ablkctx->aes_generic)) { + pr_err("failed to allocate aes cipher for tweak\n"); + return PTR_ERR(ablkctx->aes_generic); + } + } else + ablkctx->aes_generic = NULL; + tfm->crt_ablkcipher.reqsize = sizeof(struct chcr_blkcipher_req_ctx); return chcr_device_init(crypto_tfm_ctx(tfm)); } @@ -1291,6 +1296,8 @@ static void chcr_cra_exit(struct crypto_tfm *tfm) struct ablk_ctx *ablkctx = ABLK_CTX(ctx); crypto_free_skcipher(ablkctx->sw_cipher); + if (ablkctx->aes_generic) + crypto_free_cipher(ablkctx->aes_generic); } static int get_alg_config(struct algo_param *params, diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index a4f95b014b46..30af1ee17b87 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -155,6 +155,7 @@ struct ablk_ctx { struct crypto_skcipher *sw_cipher; + struct crypto_cipher *aes_generic; __be32 key_ctx_hdr; unsigned int enckey_len; unsigned char ciph_mode; diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 176976068bcd..77028c27593c 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -86,7 +86,7 @@ static struct attribute *dev_entries[] = { &dev_attr_set_freq.attr, NULL, }; -static struct attribute_group dev_attr_group = { +static const struct attribute_group dev_attr_group = { .name = "userspace", .attrs = dev_entries, }; diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c index 40a2499730fc..1b89ebbad02c 100644 --- a/drivers/devfreq/rk3399_dmc.c +++ b/drivers/devfreq/rk3399_dmc.c @@ -336,8 +336,9 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "Cannot get the dmc interrupt resource\n"); - return -EINVAL; + dev_err(&pdev->dev, + "Cannot get the dmc interrupt resource: %d\n", irq); + return irq; } data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL); if (!data) diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c index 214fff96fa4a..ae712159246f 100644 --- a/drivers/devfreq/tegra-devfreq.c +++ b/drivers/devfreq/tegra-devfreq.c @@ -688,9 +688,9 @@ static int tegra_devfreq_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(&pdev->dev, "Failed to get IRQ\n"); - return -ENODEV; + if (irq < 0) { + dev_err(&pdev->dev, "Failed to get IRQ: %d\n", irq); + return irq; } platform_set_drvdata(pdev, tegra); diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c index ec1ed94b2390..d34e5096887a 100644 --- a/drivers/gpu/drm/drm_dp_aux_dev.c +++ b/drivers/gpu/drm/drm_dp_aux_dev.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/uaccess.h> +#include <linux/uio.h> #include <drm/drm_dp_helper.h> #include <drm/drm_crtc.h> #include <drm/drmP.h> @@ -140,101 +141,83 @@ static loff_t auxdev_llseek(struct file *file, loff_t offset, int whence) return fixed_size_llseek(file, offset, whence, AUX_MAX_OFFSET); } -static ssize_t auxdev_read(struct file *file, char __user *buf, size_t count, - loff_t *offset) +static ssize_t auxdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { - size_t bytes_pending, num_bytes_processed = 0; - struct drm_dp_aux_dev *aux_dev = file->private_data; + struct drm_dp_aux_dev *aux_dev = iocb->ki_filp->private_data; + loff_t pos = iocb->ki_pos; ssize_t res = 0; if (!atomic_inc_not_zero(&aux_dev->usecount)) return -ENODEV; - bytes_pending = min((loff_t)count, AUX_MAX_OFFSET - (*offset)); - - if (!access_ok(VERIFY_WRITE, buf, bytes_pending)) { - res = -EFAULT; - goto out; - } + iov_iter_truncate(to, AUX_MAX_OFFSET - pos); - while (bytes_pending > 0) { - uint8_t localbuf[DP_AUX_MAX_PAYLOAD_BYTES]; - ssize_t todo = min_t(size_t, bytes_pending, sizeof(localbuf)); + while (iov_iter_count(to)) { + uint8_t buf[DP_AUX_MAX_PAYLOAD_BYTES]; + ssize_t todo = min(iov_iter_count(to), sizeof(buf)); if (signal_pending(current)) { - res = num_bytes_processed ? - num_bytes_processed : -ERESTARTSYS; - goto out; + res = -ERESTARTSYS; + break; } - res = drm_dp_dpcd_read(aux_dev->aux, *offset, localbuf, todo); - if (res <= 0) { - res = num_bytes_processed ? num_bytes_processed : res; - goto out; - } - if (__copy_to_user(buf + num_bytes_processed, localbuf, res)) { - res = num_bytes_processed ? - num_bytes_processed : -EFAULT; - goto out; + res = drm_dp_dpcd_read(aux_dev->aux, pos, buf, todo); + if (res <= 0) + break; + + if (copy_to_iter(buf, res, to) != res) { + res = -EFAULT; + break; } - bytes_pending -= res; - *offset += res; - num_bytes_processed += res; - res = num_bytes_processed; + + pos += res; } -out: + if (pos != iocb->ki_pos) + res = pos - iocb->ki_pos; + iocb->ki_pos = pos; + atomic_dec(&aux_dev->usecount); wake_up_atomic_t(&aux_dev->usecount); return res; } -static ssize_t auxdev_write(struct file *file, const char __user *buf, - size_t count, loff_t *offset) +static ssize_t auxdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { - size_t bytes_pending, num_bytes_processed = 0; - struct drm_dp_aux_dev *aux_dev = file->private_data; + struct drm_dp_aux_dev *aux_dev = iocb->ki_filp->private_data; + loff_t pos = iocb->ki_pos; ssize_t res = 0; if (!atomic_inc_not_zero(&aux_dev->usecount)) return -ENODEV; - bytes_pending = min((loff_t)count, AUX_MAX_OFFSET - *offset); - - if (!access_ok(VERIFY_READ, buf, bytes_pending)) { - res = -EFAULT; - goto out; - } + iov_iter_truncate(from, AUX_MAX_OFFSET - pos); - while (bytes_pending > 0) { - uint8_t localbuf[DP_AUX_MAX_PAYLOAD_BYTES]; - ssize_t todo = min_t(size_t, bytes_pending, sizeof(localbuf)); + while (iov_iter_count(from)) { + uint8_t buf[DP_AUX_MAX_PAYLOAD_BYTES]; + ssize_t todo = min(iov_iter_count(from), sizeof(buf)); if (signal_pending(current)) { - res = num_bytes_processed ? - num_bytes_processed : -ERESTARTSYS; - goto out; + res = -ERESTARTSYS; + break; } - if (__copy_from_user(localbuf, - buf + num_bytes_processed, todo)) { - res = num_bytes_processed ? - num_bytes_processed : -EFAULT; - goto out; + if (!copy_from_iter_full(buf, todo, from)) { + res = -EFAULT; + break; } - res = drm_dp_dpcd_write(aux_dev->aux, *offset, localbuf, todo); - if (res <= 0) { - res = num_bytes_processed ? num_bytes_processed : res; - goto out; - } - bytes_pending -= res; - *offset += res; - num_bytes_processed += res; - res = num_bytes_processed; + res = drm_dp_dpcd_write(aux_dev->aux, pos, buf, todo); + if (res <= 0) + break; + + pos += res; } -out: + if (pos != iocb->ki_pos) + res = pos - iocb->ki_pos; + iocb->ki_pos = pos; + atomic_dec(&aux_dev->usecount); wake_up_atomic_t(&aux_dev->usecount); return res; @@ -251,8 +234,8 @@ static int auxdev_release(struct inode *inode, struct file *file) static const struct file_operations auxdev_fops = { .owner = THIS_MODULE, .llseek = auxdev_llseek, - .read = auxdev_read, - .write = auxdev_write, + .read_iter = auxdev_read_iter, + .write_iter = auxdev_write_iter, .open = auxdev_open, .release = auxdev_release, }; diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index da3d362f21b1..a047b9af8369 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -48,6 +48,7 @@ struct gpio_button_data { spinlock_t lock; bool disabled; bool key_pressed; + bool suspended; }; struct gpio_keys_drvdata { @@ -396,8 +397,20 @@ static irqreturn_t gpio_keys_gpio_isr(int irq, void *dev_id) BUG_ON(irq != bdata->irq); - if (bdata->button->wakeup) + if (bdata->button->wakeup) { + const struct gpio_keys_button *button = bdata->button; + pm_stay_awake(bdata->input->dev.parent); + if (bdata->suspended && + (button->type == 0 || button->type == EV_KEY)) { + /* + * Simulate wakeup key press in case the key has + * already released by the time we got interrupt + * handler to run. + */ + input_report_key(bdata->input, button->code, 1); + } + } mod_delayed_work(system_wq, &bdata->work, @@ -855,6 +868,7 @@ static int __maybe_unused gpio_keys_suspend(struct device *dev) struct gpio_button_data *bdata = &ddata->data[i]; if (bdata->button->wakeup) enable_irq_wake(bdata->irq); + bdata->suspended = true; } } else { mutex_lock(&input->mutex); @@ -878,6 +892,7 @@ static int __maybe_unused gpio_keys_resume(struct device *dev) struct gpio_button_data *bdata = &ddata->data[i]; if (bdata->button->wakeup) disable_irq_wake(bdata->irq); + bdata->suspended = false; } } else { mutex_lock(&input->mutex); diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index eb770613a9bd..fa130e7b734c 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -17,6 +17,7 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/input.h> +#include <linux/input/mt.h> #include <linux/slab.h> #include <asm/xen/hypervisor.h> @@ -34,11 +35,14 @@ struct xenkbd_info { struct input_dev *kbd; struct input_dev *ptr; + struct input_dev *mtouch; struct xenkbd_page *page; int gref; int irq; struct xenbus_device *xbdev; char phys[32]; + /* current MT slot/contact ID we are injecting events in */ + int mtouch_cur_contact_id; }; enum { KPARAM_X, KPARAM_Y, KPARAM_CNT }; @@ -56,6 +60,112 @@ static void xenkbd_disconnect_backend(struct xenkbd_info *); * to do that. */ +static void xenkbd_handle_motion_event(struct xenkbd_info *info, + struct xenkbd_motion *motion) +{ + input_report_rel(info->ptr, REL_X, motion->rel_x); + input_report_rel(info->ptr, REL_Y, motion->rel_y); + if (motion->rel_z) + input_report_rel(info->ptr, REL_WHEEL, -motion->rel_z); + input_sync(info->ptr); +} + +static void xenkbd_handle_position_event(struct xenkbd_info *info, + struct xenkbd_position *pos) +{ + input_report_abs(info->ptr, ABS_X, pos->abs_x); + input_report_abs(info->ptr, ABS_Y, pos->abs_y); + if (pos->rel_z) + input_report_rel(info->ptr, REL_WHEEL, -pos->rel_z); + input_sync(info->ptr); +} + +static void xenkbd_handle_key_event(struct xenkbd_info *info, + struct xenkbd_key *key) +{ + struct input_dev *dev; + + if (test_bit(key->keycode, info->ptr->keybit)) { + dev = info->ptr; + } else if (test_bit(key->keycode, info->kbd->keybit)) { + dev = info->kbd; + } else { + pr_warn("unhandled keycode 0x%x\n", key->keycode); + return; + } + + input_report_key(dev, key->keycode, key->pressed); + input_sync(dev); +} + +static void xenkbd_handle_mt_event(struct xenkbd_info *info, + struct xenkbd_mtouch *mtouch) +{ + if (unlikely(!info->mtouch)) + return; + + if (mtouch->contact_id != info->mtouch_cur_contact_id) { + info->mtouch_cur_contact_id = mtouch->contact_id; + input_mt_slot(info->mtouch, mtouch->contact_id); + } + + switch (mtouch->event_type) { + case XENKBD_MT_EV_DOWN: + input_mt_report_slot_state(info->mtouch, MT_TOOL_FINGER, true); + /* fall through */ + + case XENKBD_MT_EV_MOTION: + input_report_abs(info->mtouch, ABS_MT_POSITION_X, + mtouch->u.pos.abs_x); + input_report_abs(info->mtouch, ABS_MT_POSITION_Y, + mtouch->u.pos.abs_y); + break; + + case XENKBD_MT_EV_SHAPE: + input_report_abs(info->mtouch, ABS_MT_TOUCH_MAJOR, + mtouch->u.shape.major); + input_report_abs(info->mtouch, ABS_MT_TOUCH_MINOR, + mtouch->u.shape.minor); + break; + + case XENKBD_MT_EV_ORIENT: + input_report_abs(info->mtouch, ABS_MT_ORIENTATION, + mtouch->u.orientation); + break; + + case XENKBD_MT_EV_UP: + input_mt_report_slot_state(info->mtouch, MT_TOOL_FINGER, false); + break; + + case XENKBD_MT_EV_SYN: + input_mt_sync_frame(info->mtouch); + input_sync(info->mtouch); + break; + } +} + +static void xenkbd_handle_event(struct xenkbd_info *info, + union xenkbd_in_event *event) +{ + switch (event->type) { + case XENKBD_TYPE_MOTION: + xenkbd_handle_motion_event(info, &event->motion); + break; + + case XENKBD_TYPE_KEY: + xenkbd_handle_key_event(info, &event->key); + break; + + case XENKBD_TYPE_POS: + xenkbd_handle_position_event(info, &event->pos); + break; + + case XENKBD_TYPE_MTOUCH: + xenkbd_handle_mt_event(info, &event->mtouch); + break; + } +} + static irqreturn_t input_handler(int rq, void *dev_id) { struct xenkbd_info *info = dev_id; @@ -66,44 +176,8 @@ static irqreturn_t input_handler(int rq, void *dev_id) if (prod == page->in_cons) return IRQ_HANDLED; rmb(); /* ensure we see ring contents up to prod */ - for (cons = page->in_cons; cons != prod; cons++) { - union xenkbd_in_event *event; - struct input_dev *dev; - event = &XENKBD_IN_RING_REF(page, cons); - - dev = info->ptr; - switch (event->type) { - case XENKBD_TYPE_MOTION: - input_report_rel(dev, REL_X, event->motion.rel_x); - input_report_rel(dev, REL_Y, event->motion.rel_y); - if (event->motion.rel_z) - input_report_rel(dev, REL_WHEEL, - -event->motion.rel_z); - break; - case XENKBD_TYPE_KEY: - dev = NULL; - if (test_bit(event->key.keycode, info->kbd->keybit)) - dev = info->kbd; - if (test_bit(event->key.keycode, info->ptr->keybit)) - dev = info->ptr; - if (dev) - input_report_key(dev, event->key.keycode, - event->key.pressed); - else - pr_warn("unhandled keycode 0x%x\n", - event->key.keycode); - break; - case XENKBD_TYPE_POS: - input_report_abs(dev, ABS_X, event->pos.abs_x); - input_report_abs(dev, ABS_Y, event->pos.abs_y); - if (event->pos.rel_z) - input_report_rel(dev, REL_WHEEL, - -event->pos.rel_z); - break; - } - if (dev) - input_sync(dev); - } + for (cons = page->in_cons; cons != prod; cons++) + xenkbd_handle_event(info, &XENKBD_IN_RING_REF(page, cons)); mb(); /* ensure we got ring contents */ page->in_cons = cons; notify_remote_via_irq(info->irq); @@ -115,9 +189,9 @@ static int xenkbd_probe(struct xenbus_device *dev, const struct xenbus_device_id *id) { int ret, i; - unsigned int abs; + unsigned int abs, touch; struct xenkbd_info *info; - struct input_dev *kbd, *ptr; + struct input_dev *kbd, *ptr, *mtouch; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { @@ -152,6 +226,17 @@ static int xenkbd_probe(struct xenbus_device *dev, } } + touch = xenbus_read_unsigned(dev->nodename, + XENKBD_FIELD_FEAT_MTOUCH, 0); + if (touch) { + ret = xenbus_write(XBT_NIL, dev->nodename, + XENKBD_FIELD_REQ_MTOUCH, "1"); + if (ret) { + pr_warn("xenkbd: can't request multi-touch"); + touch = 0; + } + } + /* keyboard */ kbd = input_allocate_device(); if (!kbd) @@ -208,6 +293,58 @@ static int xenkbd_probe(struct xenbus_device *dev, } info->ptr = ptr; + /* multi-touch device */ + if (touch) { + int num_cont, width, height; + + mtouch = input_allocate_device(); + if (!mtouch) + goto error_nomem; + + num_cont = xenbus_read_unsigned(info->xbdev->nodename, + XENKBD_FIELD_MT_NUM_CONTACTS, + 1); + width = xenbus_read_unsigned(info->xbdev->nodename, + XENKBD_FIELD_MT_WIDTH, + XENFB_WIDTH); + height = xenbus_read_unsigned(info->xbdev->nodename, + XENKBD_FIELD_MT_HEIGHT, + XENFB_HEIGHT); + + mtouch->name = "Xen Virtual Multi-touch"; + mtouch->phys = info->phys; + mtouch->id.bustype = BUS_PCI; + mtouch->id.vendor = 0x5853; + mtouch->id.product = 0xfffd; + + input_set_abs_params(mtouch, ABS_MT_TOUCH_MAJOR, + 0, 255, 0, 0); + input_set_abs_params(mtouch, ABS_MT_POSITION_X, + 0, width, 0, 0); + input_set_abs_params(mtouch, ABS_MT_POSITION_Y, + 0, height, 0, 0); + input_set_abs_params(mtouch, ABS_MT_PRESSURE, + 0, 255, 0, 0); + + ret = input_mt_init_slots(mtouch, num_cont, INPUT_MT_DIRECT); + if (ret) { + input_free_device(mtouch); + xenbus_dev_fatal(info->xbdev, ret, + "input_mt_init_slots"); + goto error; + } + + ret = input_register_device(mtouch); + if (ret) { + input_free_device(mtouch); + xenbus_dev_fatal(info->xbdev, ret, + "input_register_device(mtouch)"); + goto error; + } + info->mtouch_cur_contact_id = -1; + info->mtouch = mtouch; + } + ret = xenkbd_connect_backend(dev, info); if (ret < 0) goto error; @@ -240,6 +377,8 @@ static int xenkbd_remove(struct xenbus_device *dev) input_unregister_device(info->kbd); if (info->ptr) input_unregister_device(info->ptr); + if (info->mtouch) + input_unregister_device(info->mtouch); free_page((unsigned long)info->page); kfree(info); return 0; diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index c52da651269b..824f4c1c1f31 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -436,8 +436,10 @@ static int i8042_start(struct serio *serio) { struct i8042_port *port = serio->port_data; + spin_lock_irq(&i8042_lock); port->exists = true; - mb(); + spin_unlock_irq(&i8042_lock); + return 0; } @@ -450,16 +452,20 @@ static void i8042_stop(struct serio *serio) { struct i8042_port *port = serio->port_data; + spin_lock_irq(&i8042_lock); port->exists = false; + port->serio = NULL; + spin_unlock_irq(&i8042_lock); /* + * We need to make sure that interrupt handler finishes using + * our serio port before we return from this function. * We synchronize with both AUX and KBD IRQs because there is * a (very unlikely) chance that AUX IRQ is raised for KBD port * and vice versa. */ synchronize_irq(I8042_AUX_IRQ); synchronize_irq(I8042_KBD_IRQ); - port->serio = NULL; } /* @@ -576,7 +582,7 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id) spin_unlock_irqrestore(&i8042_lock, flags); - if (likely(port->exists && !filtered)) + if (likely(serio && !filtered)) serio_interrupt(serio, data, dfl); out: diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 0cfac2d39107..8ac59dc80f23 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -637,6 +637,9 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev, sizeof(num_of_cmds))) return -EFAULT; + if (!num_of_cmds) + return 0; + if (num_of_cmds > MMC_IOC_MAX_CMDS) return -EINVAL; @@ -1182,7 +1185,7 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) switch (mq_rq->drv_op) { case MMC_DRV_OP_IOCTL: - for (i = 0; i < mq_rq->ioc_count; i++) { + for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) { ret = __mmc_blk_ioctl_cmd(card, md, mq_rq->idata[i]); if (ret) break; @@ -2167,6 +2170,7 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) * from being accepted. */ card = md->queue.card; + blk_set_queue_dying(md->queue.queue); mmc_cleanup_queue(&md->queue); if (md->disk->flags & GENHD_FL_UP) { device_remove_file(disk_to_dev(md->disk), &md->force_ro); diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index cf66a3db71b8..ac678e9fb19a 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -45,6 +45,7 @@ #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/iosf_mbi.h> +#include <linux/pci.h> #endif #include "sdhci.h" @@ -134,6 +135,16 @@ static bool sdhci_acpi_byt(void) return x86_match_cpu(byt); } +static bool sdhci_acpi_cht(void) +{ + static const struct x86_cpu_id cht[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + {} + }; + + return x86_match_cpu(cht); +} + #define BYT_IOSF_SCCEP 0x63 #define BYT_IOSF_OCP_NETCTRL0 0x1078 #define BYT_IOSF_OCP_TIMEOUT_BASE GENMASK(10, 8) @@ -178,6 +189,45 @@ static bool sdhci_acpi_byt_defer(struct device *dev) return false; } +static bool sdhci_acpi_cht_pci_wifi(unsigned int vendor, unsigned int device, + unsigned int slot, unsigned int parent_slot) +{ + struct pci_dev *dev, *parent, *from = NULL; + + while (1) { + dev = pci_get_device(vendor, device, from); + pci_dev_put(from); + if (!dev) + break; + parent = pci_upstream_bridge(dev); + if (ACPI_COMPANION(&dev->dev) && PCI_SLOT(dev->devfn) == slot && + parent && PCI_SLOT(parent->devfn) == parent_slot && + !pci_upstream_bridge(parent)) { + pci_dev_put(dev); + return true; + } + from = dev; + } + + return false; +} + +/* + * GPDwin uses PCI wifi which conflicts with SDIO's use of + * acpi_device_fix_up_power() on child device nodes. Identifying GPDwin is + * problematic, but since SDIO is only used for wifi, the presence of the PCI + * wifi card in the expected slot with an ACPI companion node, is used to + * indicate that acpi_device_fix_up_power() should be avoided. + */ +static inline bool sdhci_acpi_no_fixup_child_power(const char *hid, + const char *uid) +{ + return sdhci_acpi_cht() && + !strcmp(hid, "80860F14") && + !strcmp(uid, "2") && + sdhci_acpi_cht_pci_wifi(0x14e4, 0x43ec, 0, 28); +} + #else static inline void sdhci_acpi_byt_setting(struct device *dev) @@ -189,6 +239,12 @@ static inline bool sdhci_acpi_byt_defer(struct device *dev) return false; } +static inline bool sdhci_acpi_no_fixup_child_power(const char *hid, + const char *uid) +{ + return false; +} + #endif static int bxt_get_cd(struct mmc_host *mmc) @@ -389,18 +445,20 @@ static int sdhci_acpi_probe(struct platform_device *pdev) if (acpi_bus_get_device(handle, &device)) return -ENODEV; + hid = acpi_device_hid(device); + uid = device->pnp.unique_id; + /* Power on the SDHCI controller and its children */ acpi_device_fix_up_power(device); - list_for_each_entry(child, &device->children, node) - if (child->status.present && child->status.enabled) - acpi_device_fix_up_power(child); + if (!sdhci_acpi_no_fixup_child_power(hid, uid)) { + list_for_each_entry(child, &device->children, node) + if (child->status.present && child->status.enabled) + acpi_device_fix_up_power(child); + } if (sdhci_acpi_byt_defer(dev)) return -EPROBE_DEFER; - hid = acpi_device_hid(device); - uid = device->pnp.unique_id; - iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!iomem) return -ENOMEM; diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 82b80d42f7ae..88a94355ac90 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -409,30 +409,29 @@ static void tmio_mmc_transfer_data(struct tmio_mmc_host *host, * Transfer the data */ if (host->pdata->flags & TMIO_MMC_32BIT_DATA_PORT) { - u8 data[4] = { }; + u32 data = 0; + u32 *buf32 = (u32 *)buf; if (is_read) - sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, (u32 *)buf, + sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, buf32, count >> 2); else - sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, (u32 *)buf, + sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, buf32, count >> 2); /* if count was multiple of 4 */ if (!(count & 0x3)) return; - buf8 = (u8 *)(buf + (count >> 2)); + buf32 += count >> 2; count %= 4; if (is_read) { - sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, - (u32 *)data, 1); - memcpy(buf8, data, count); + sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, &data, 1); + memcpy(buf32, &data, count); } else { - memcpy(data, buf8, count); - sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, - (u32 *)data, 1); + memcpy(&data, buf32, count); + sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, &data, 1); } return; diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 4daf3d0926a8..0250aa9ae2cb 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -418,6 +418,8 @@ static int ntb_netdev_probe(struct device *client_dev) if (!ndev) return -ENOMEM; + SET_NETDEV_DEV(ndev, client_dev); + dev = netdev_priv(ndev); dev->ndev = ndev; dev->pdev = pdev; diff --git a/drivers/ntb/hw/Kconfig b/drivers/ntb/hw/Kconfig index 7116472b4625..a89243c9fdd3 100644 --- a/drivers/ntb/hw/Kconfig +++ b/drivers/ntb/hw/Kconfig @@ -1,2 +1,3 @@ source "drivers/ntb/hw/amd/Kconfig" +source "drivers/ntb/hw/idt/Kconfig" source "drivers/ntb/hw/intel/Kconfig" diff --git a/drivers/ntb/hw/Makefile b/drivers/ntb/hw/Makefile index 532e0859b4a1..87332c3905f0 100644 --- a/drivers/ntb/hw/Makefile +++ b/drivers/ntb/hw/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_NTB_AMD) += amd/ +obj-$(CONFIG_NTB_IDT) += idt/ obj-$(CONFIG_NTB_INTEL) += intel/ diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 019a158e1128..f0788aae05c9 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2016 Advanced Micro Devices, Inc. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -13,6 +14,7 @@ * BSD LICENSE * * Copyright (C) 2016 Advanced Micro Devices, Inc. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -79,40 +81,42 @@ static int ndev_mw_to_bar(struct amd_ntb_dev *ndev, int idx) return 1 << idx; } -static int amd_ntb_mw_count(struct ntb_dev *ntb) +static int amd_ntb_mw_count(struct ntb_dev *ntb, int pidx) { + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + return ntb_ndev(ntb)->mw_count; } -static int amd_ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, - resource_size_t *size, - resource_size_t *align, - resource_size_t *align_size) +static int amd_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int idx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + bar = ndev_mw_to_bar(ndev, idx); if (bar < 0) return bar; - if (base) - *base = pci_resource_start(ndev->ntb.pdev, bar); - - if (size) - *size = pci_resource_len(ndev->ntb.pdev, bar); + if (addr_align) + *addr_align = SZ_4K; - if (align) - *align = SZ_4K; + if (size_align) + *size_align = 1; - if (align_size) - *align_size = 1; + if (size_max) + *size_max = pci_resource_len(ndev->ntb.pdev, bar); return 0; } -static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, +static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, dma_addr_t addr, resource_size_t size) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); @@ -122,11 +126,14 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, u64 base_addr, limit, reg_val; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + bar = ndev_mw_to_bar(ndev, idx); if (bar < 0) return bar; - mw_size = pci_resource_len(ndev->ntb.pdev, bar); + mw_size = pci_resource_len(ntb->pdev, bar); /* make sure the range fits in the usable mw size */ if (size > mw_size) @@ -135,7 +142,7 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, mmio = ndev->self_mmio; peer_mmio = ndev->peer_mmio; - base_addr = pci_resource_start(ndev->ntb.pdev, bar); + base_addr = pci_resource_start(ntb->pdev, bar); if (bar != 1) { xlat_reg = AMD_BAR23XLAT_OFFSET + ((bar - 2) << 2); @@ -212,7 +219,7 @@ static int amd_link_is_up(struct amd_ntb_dev *ndev) return 0; } -static int amd_ntb_link_is_up(struct ntb_dev *ntb, +static u64 amd_ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { @@ -225,7 +232,7 @@ static int amd_ntb_link_is_up(struct ntb_dev *ntb, if (width) *width = NTB_LNK_STA_WIDTH(ndev->lnk_sta); - dev_dbg(ndev_dev(ndev), "link is up.\n"); + dev_dbg(&ntb->pdev->dev, "link is up.\n"); ret = 1; } else { @@ -234,7 +241,7 @@ static int amd_ntb_link_is_up(struct ntb_dev *ntb, if (width) *width = NTB_WIDTH_NONE; - dev_dbg(ndev_dev(ndev), "link is down.\n"); + dev_dbg(&ntb->pdev->dev, "link is down.\n"); } return ret; @@ -254,7 +261,7 @@ static int amd_ntb_link_enable(struct ntb_dev *ntb, if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), "Enabling Link.\n"); + dev_dbg(&ntb->pdev->dev, "Enabling Link.\n"); ntb_ctl = readl(mmio + AMD_CNTL_OFFSET); ntb_ctl |= (PMM_REG_CTL | SMM_REG_CTL); @@ -275,7 +282,7 @@ static int amd_ntb_link_disable(struct ntb_dev *ntb) if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), "Enabling Link.\n"); + dev_dbg(&ntb->pdev->dev, "Enabling Link.\n"); ntb_ctl = readl(mmio + AMD_CNTL_OFFSET); ntb_ctl &= ~(PMM_REG_CTL | SMM_REG_CTL); @@ -284,6 +291,31 @@ static int amd_ntb_link_disable(struct ntb_dev *ntb) return 0; } +static int amd_ntb_peer_mw_count(struct ntb_dev *ntb) +{ + /* The same as for inbound MWs */ + return ntb_ndev(ntb)->mw_count; +} + +static int amd_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size) +{ + struct amd_ntb_dev *ndev = ntb_ndev(ntb); + int bar; + + bar = ndev_mw_to_bar(ndev, idx); + if (bar < 0) + return bar; + + if (base) + *base = pci_resource_start(ndev->ntb.pdev, bar); + + if (size) + *size = pci_resource_len(ndev->ntb.pdev, bar); + + return 0; +} + static u64 amd_ntb_db_valid_mask(struct ntb_dev *ntb) { return ntb_ndev(ntb)->db_valid_mask; @@ -400,30 +432,30 @@ static int amd_ntb_spad_write(struct ntb_dev *ntb, return 0; } -static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); void __iomem *mmio = ndev->self_mmio; u32 offset; - if (idx < 0 || idx >= ndev->spad_count) + if (sidx < 0 || sidx >= ndev->spad_count) return -EINVAL; - offset = ndev->peer_spad + (idx << 2); + offset = ndev->peer_spad + (sidx << 2); return readl(mmio + AMD_SPAD_OFFSET + offset); } -static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, - int idx, u32 val) +static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, + int sidx, u32 val) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); void __iomem *mmio = ndev->self_mmio; u32 offset; - if (idx < 0 || idx >= ndev->spad_count) + if (sidx < 0 || sidx >= ndev->spad_count) return -EINVAL; - offset = ndev->peer_spad + (idx << 2); + offset = ndev->peer_spad + (sidx << 2); writel(val, mmio + AMD_SPAD_OFFSET + offset); return 0; @@ -431,8 +463,10 @@ static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, static const struct ntb_dev_ops amd_ntb_ops = { .mw_count = amd_ntb_mw_count, - .mw_get_range = amd_ntb_mw_get_range, + .mw_get_align = amd_ntb_mw_get_align, .mw_set_trans = amd_ntb_mw_set_trans, + .peer_mw_count = amd_ntb_peer_mw_count, + .peer_mw_get_addr = amd_ntb_peer_mw_get_addr, .link_is_up = amd_ntb_link_is_up, .link_enable = amd_ntb_link_enable, .link_disable = amd_ntb_link_disable, @@ -466,18 +500,19 @@ static void amd_ack_smu(struct amd_ntb_dev *ndev, u32 bit) static void amd_handle_event(struct amd_ntb_dev *ndev, int vec) { void __iomem *mmio = ndev->self_mmio; + struct device *dev = &ndev->ntb.pdev->dev; u32 status; status = readl(mmio + AMD_INTSTAT_OFFSET); if (!(status & AMD_EVENT_INTMASK)) return; - dev_dbg(ndev_dev(ndev), "status = 0x%x and vec = %d\n", status, vec); + dev_dbg(dev, "status = 0x%x and vec = %d\n", status, vec); status &= AMD_EVENT_INTMASK; switch (status) { case AMD_PEER_FLUSH_EVENT: - dev_info(ndev_dev(ndev), "Flush is done.\n"); + dev_info(dev, "Flush is done.\n"); break; case AMD_PEER_RESET_EVENT: amd_ack_smu(ndev, AMD_PEER_RESET_EVENT); @@ -503,7 +538,7 @@ static void amd_handle_event(struct amd_ntb_dev *ndev, int vec) status = readl(mmio + AMD_PMESTAT_OFFSET); /* check if this is WAKEUP event */ if (status & 0x1) - dev_info(ndev_dev(ndev), "Wakeup is done.\n"); + dev_info(dev, "Wakeup is done.\n"); amd_ack_smu(ndev, AMD_PEER_D0_EVENT); @@ -512,14 +547,14 @@ static void amd_handle_event(struct amd_ntb_dev *ndev, int vec) AMD_LINK_HB_TIMEOUT); break; default: - dev_info(ndev_dev(ndev), "event status = 0x%x.\n", status); + dev_info(dev, "event status = 0x%x.\n", status); break; } } static irqreturn_t ndev_interrupt(struct amd_ntb_dev *ndev, int vec) { - dev_dbg(ndev_dev(ndev), "vec %d\n", vec); + dev_dbg(&ndev->ntb.pdev->dev, "vec %d\n", vec); if (vec > (AMD_DB_CNT - 1) || (ndev->msix_vec_count == 1)) amd_handle_event(ndev, vec); @@ -541,7 +576,7 @@ static irqreturn_t ndev_irq_isr(int irq, void *dev) { struct amd_ntb_dev *ndev = dev; - return ndev_interrupt(ndev, irq - ndev_pdev(ndev)->irq); + return ndev_interrupt(ndev, irq - ndev->ntb.pdev->irq); } static int ndev_init_isr(struct amd_ntb_dev *ndev, @@ -550,7 +585,7 @@ static int ndev_init_isr(struct amd_ntb_dev *ndev, struct pci_dev *pdev; int rc, i, msix_count, node; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; node = dev_to_node(&pdev->dev); @@ -592,7 +627,7 @@ static int ndev_init_isr(struct amd_ntb_dev *ndev, goto err_msix_request; } - dev_dbg(ndev_dev(ndev), "Using msix interrupts\n"); + dev_dbg(&pdev->dev, "Using msix interrupts\n"); ndev->db_count = msix_min; ndev->msix_vec_count = msix_max; return 0; @@ -619,7 +654,7 @@ err_msix_vec_alloc: if (rc) goto err_msi_request; - dev_dbg(ndev_dev(ndev), "Using msi interrupts\n"); + dev_dbg(&pdev->dev, "Using msi interrupts\n"); ndev->db_count = 1; ndev->msix_vec_count = 1; return 0; @@ -636,7 +671,7 @@ err_msi_enable: if (rc) goto err_intx_request; - dev_dbg(ndev_dev(ndev), "Using intx interrupts\n"); + dev_dbg(&pdev->dev, "Using intx interrupts\n"); ndev->db_count = 1; ndev->msix_vec_count = 1; return 0; @@ -651,7 +686,7 @@ static void ndev_deinit_isr(struct amd_ntb_dev *ndev) void __iomem *mmio = ndev->self_mmio; int i; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; /* Mask all doorbell interrupts */ ndev->db_mask = ndev->db_valid_mask; @@ -777,7 +812,8 @@ static void ndev_init_debugfs(struct amd_ntb_dev *ndev) ndev->debugfs_info = NULL; } else { ndev->debugfs_dir = - debugfs_create_dir(ndev_name(ndev), debugfs_dir); + debugfs_create_dir(pci_name(ndev->ntb.pdev), + debugfs_dir); if (!ndev->debugfs_dir) ndev->debugfs_info = NULL; else @@ -812,7 +848,7 @@ static int amd_poll_link(struct amd_ntb_dev *ndev) reg = readl(mmio + AMD_SIDEINFO_OFFSET); reg &= NTB_LIN_STA_ACTIVE_BIT; - dev_dbg(ndev_dev(ndev), "%s: reg_val = 0x%x.\n", __func__, reg); + dev_dbg(&ndev->ntb.pdev->dev, "%s: reg_val = 0x%x.\n", __func__, reg); if (reg == ndev->cntl_sta) return 0; @@ -894,7 +930,8 @@ static int amd_init_ntb(struct amd_ntb_dev *ndev) break; default: - dev_err(ndev_dev(ndev), "AMD NTB does not support B2B mode.\n"); + dev_err(&ndev->ntb.pdev->dev, + "AMD NTB does not support B2B mode.\n"); return -EINVAL; } @@ -923,10 +960,10 @@ static int amd_init_dev(struct amd_ntb_dev *ndev) struct pci_dev *pdev; int rc = 0; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; ndev->ntb.topo = amd_get_topo(ndev); - dev_dbg(ndev_dev(ndev), "AMD NTB topo is %s\n", + dev_dbg(&pdev->dev, "AMD NTB topo is %s\n", ntb_topo_string(ndev->ntb.topo)); rc = amd_init_ntb(ndev); @@ -935,7 +972,7 @@ static int amd_init_dev(struct amd_ntb_dev *ndev) rc = amd_init_isr(ndev); if (rc) { - dev_err(ndev_dev(ndev), "fail to init isr.\n"); + dev_err(&pdev->dev, "fail to init isr.\n"); return rc; } @@ -973,7 +1010,7 @@ static int amd_ntb_init_pci(struct amd_ntb_dev *ndev, rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA highmem\n"); } rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); @@ -981,7 +1018,7 @@ static int amd_ntb_init_pci(struct amd_ntb_dev *ndev, rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA consistent highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA consistent highmem\n"); } ndev->self_mmio = pci_iomap(pdev, 0, 0); @@ -1004,7 +1041,7 @@ err_pci_enable: static void amd_ntb_deinit_pci(struct amd_ntb_dev *ndev) { - struct pci_dev *pdev = ndev_pdev(ndev); + struct pci_dev *pdev = ndev->ntb.pdev; pci_iounmap(pdev, ndev->self_mmio); diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.h b/drivers/ntb/hw/amd/ntb_hw_amd.h index 13d73ed94a52..8f3617a46292 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.h +++ b/drivers/ntb/hw/amd/ntb_hw_amd.h @@ -211,9 +211,6 @@ struct amd_ntb_dev { struct dentry *debugfs_info; }; -#define ndev_pdev(ndev) ((ndev)->ntb.pdev) -#define ndev_name(ndev) pci_name(ndev_pdev(ndev)) -#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev) #define ntb_ndev(__ntb) container_of(__ntb, struct amd_ntb_dev, ntb) #define hb_ndev(__work) container_of(__work, struct amd_ntb_dev, hb_timer.work) diff --git a/drivers/ntb/hw/idt/Kconfig b/drivers/ntb/hw/idt/Kconfig new file mode 100644 index 000000000000..b360e5613b9f --- /dev/null +++ b/drivers/ntb/hw/idt/Kconfig @@ -0,0 +1,31 @@ +config NTB_IDT + tristate "IDT PCIe-switch Non-Transparent Bridge support" + depends on PCI + help + This driver supports NTB of cappable IDT PCIe-switches. + + Some of the pre-initializations must be made before IDT PCIe-switch + exposes it NT-functions correctly. It should be done by either proper + initialisation of EEPROM connected to master smbus of the switch or + by BIOS using slave-SMBus interface changing corresponding registers + value. Evidently it must be done before PCI bus enumeration is + finished in Linux kernel. + + First of all partitions must be activated and properly assigned to all + the ports with NT-functions intended to be activated (see SWPARTxCTL + and SWPORTxCTL registers). Then all NT-function BARs must be enabled + with chosen valid aperture. For memory windows related BARs the + aperture settings shall determine the maximum size of memory windows + accepted by a BAR. Note that BAR0 must map PCI configuration space + registers. + + It's worth to note, that since a part of this driver relies on the + BAR settings of peer NT-functions, the BAR setups can't be done over + kernel PCI fixups. That's why the alternative pre-initialization + techniques like BIOS using SMBus interface or EEPROM should be + utilized. Additionally if one needs to have temperature sensor + information printed to system log, the corresponding registers must + be initialized within BIOS/EEPROM as well. + + If unsure, say N. + diff --git a/drivers/ntb/hw/idt/Makefile b/drivers/ntb/hw/idt/Makefile new file mode 100644 index 000000000000..a102cf154be0 --- /dev/null +++ b/drivers/ntb/hw/idt/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_NTB_IDT) += ntb_hw_idt.o diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c new file mode 100644 index 000000000000..d44d7ef38fe8 --- /dev/null +++ b/drivers/ntb/hw/idt/ntb_hw_idt.c @@ -0,0 +1,2712 @@ +/* + * This file is provided under a GPLv2 license. When using or + * redistributing this file, you may do so under that license. + * + * GPL LICENSE SUMMARY + * + * Copyright (C) 2016 T-Platforms All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General + * Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, one can be found http://www.gnu.org/licenses/. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * IDT PCIe-switch NTB Linux driver + * + * Contact Information: + * Serge Semin <fancer.lancer@gmail.com>, <Sergey.Semin@t-platforms.ru> + */ + +#include <linux/stddef.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/sizes.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/spinlock.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/debugfs.h> +#include <linux/ntb.h> + +#include "ntb_hw_idt.h" + +#define NTB_NAME "ntb_hw_idt" +#define NTB_DESC "IDT PCI-E Non-Transparent Bridge Driver" +#define NTB_VER "2.0" +#define NTB_IRQNAME "ntb_irq_idt" + +MODULE_DESCRIPTION(NTB_DESC); +MODULE_VERSION(NTB_VER); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("T-platforms"); + +/* + * NT Endpoint registers table simplifying a loop access to the functionally + * related registers + */ +static const struct idt_ntb_regs ntdata_tbl = { + { {IDT_NT_BARSETUP0, IDT_NT_BARLIMIT0, + IDT_NT_BARLTBASE0, IDT_NT_BARUTBASE0}, + {IDT_NT_BARSETUP1, IDT_NT_BARLIMIT1, + IDT_NT_BARLTBASE1, IDT_NT_BARUTBASE1}, + {IDT_NT_BARSETUP2, IDT_NT_BARLIMIT2, + IDT_NT_BARLTBASE2, IDT_NT_BARUTBASE2}, + {IDT_NT_BARSETUP3, IDT_NT_BARLIMIT3, + IDT_NT_BARLTBASE3, IDT_NT_BARUTBASE3}, + {IDT_NT_BARSETUP4, IDT_NT_BARLIMIT4, + IDT_NT_BARLTBASE4, IDT_NT_BARUTBASE4}, + {IDT_NT_BARSETUP5, IDT_NT_BARLIMIT5, + IDT_NT_BARLTBASE5, IDT_NT_BARUTBASE5} }, + { {IDT_NT_INMSG0, IDT_NT_OUTMSG0, IDT_NT_INMSGSRC0}, + {IDT_NT_INMSG1, IDT_NT_OUTMSG1, IDT_NT_INMSGSRC1}, + {IDT_NT_INMSG2, IDT_NT_OUTMSG2, IDT_NT_INMSGSRC2}, + {IDT_NT_INMSG3, IDT_NT_OUTMSG3, IDT_NT_INMSGSRC3} } +}; + +/* + * NT Endpoint ports data table with the corresponding pcie command, link + * status, control and BAR-related registers + */ +static const struct idt_ntb_port portdata_tbl[IDT_MAX_NR_PORTS] = { +/*0*/ { IDT_SW_NTP0_PCIECMDSTS, IDT_SW_NTP0_PCIELCTLSTS, + IDT_SW_NTP0_NTCTL, + IDT_SW_SWPORT0CTL, IDT_SW_SWPORT0STS, + { {IDT_SW_NTP0_BARSETUP0, IDT_SW_NTP0_BARLIMIT0, + IDT_SW_NTP0_BARLTBASE0, IDT_SW_NTP0_BARUTBASE0}, + {IDT_SW_NTP0_BARSETUP1, IDT_SW_NTP0_BARLIMIT1, + IDT_SW_NTP0_BARLTBASE1, IDT_SW_NTP0_BARUTBASE1}, + {IDT_SW_NTP0_BARSETUP2, IDT_SW_NTP0_BARLIMIT2, + IDT_SW_NTP0_BARLTBASE2, IDT_SW_NTP0_BARUTBASE2}, + {IDT_SW_NTP0_BARSETUP3, IDT_SW_NTP0_BARLIMIT3, + IDT_SW_NTP0_BARLTBASE3, IDT_SW_NTP0_BARUTBASE3}, + {IDT_SW_NTP0_BARSETUP4, IDT_SW_NTP0_BARLIMIT4, + IDT_SW_NTP0_BARLTBASE4, IDT_SW_NTP0_BARUTBASE4}, + {IDT_SW_NTP0_BARSETUP5, IDT_SW_NTP0_BARLIMIT5, + IDT_SW_NTP0_BARLTBASE5, IDT_SW_NTP0_BARUTBASE5} } }, +/*1*/ {0}, +/*2*/ { IDT_SW_NTP2_PCIECMDSTS, IDT_SW_NTP2_PCIELCTLSTS, + IDT_SW_NTP2_NTCTL, + IDT_SW_SWPORT2CTL, IDT_SW_SWPORT2STS, + { {IDT_SW_NTP2_BARSETUP0, IDT_SW_NTP2_BARLIMIT0, + IDT_SW_NTP2_BARLTBASE0, IDT_SW_NTP2_BARUTBASE0}, + {IDT_SW_NTP2_BARSETUP1, IDT_SW_NTP2_BARLIMIT1, + IDT_SW_NTP2_BARLTBASE1, IDT_SW_NTP2_BARUTBASE1}, + {IDT_SW_NTP2_BARSETUP2, IDT_SW_NTP2_BARLIMIT2, + IDT_SW_NTP2_BARLTBASE2, IDT_SW_NTP2_BARUTBASE2}, + {IDT_SW_NTP2_BARSETUP3, IDT_SW_NTP2_BARLIMIT3, + IDT_SW_NTP2_BARLTBASE3, IDT_SW_NTP2_BARUTBASE3}, + {IDT_SW_NTP2_BARSETUP4, IDT_SW_NTP2_BARLIMIT4, + IDT_SW_NTP2_BARLTBASE4, IDT_SW_NTP2_BARUTBASE4}, + {IDT_SW_NTP2_BARSETUP5, IDT_SW_NTP2_BARLIMIT5, + IDT_SW_NTP2_BARLTBASE5, IDT_SW_NTP2_BARUTBASE5} } }, +/*3*/ {0}, +/*4*/ { IDT_SW_NTP4_PCIECMDSTS, IDT_SW_NTP4_PCIELCTLSTS, + IDT_SW_NTP4_NTCTL, + IDT_SW_SWPORT4CTL, IDT_SW_SWPORT4STS, + { {IDT_SW_NTP4_BARSETUP0, IDT_SW_NTP4_BARLIMIT0, + IDT_SW_NTP4_BARLTBASE0, IDT_SW_NTP4_BARUTBASE0}, + {IDT_SW_NTP4_BARSETUP1, IDT_SW_NTP4_BARLIMIT1, + IDT_SW_NTP4_BARLTBASE1, IDT_SW_NTP4_BARUTBASE1}, + {IDT_SW_NTP4_BARSETUP2, IDT_SW_NTP4_BARLIMIT2, + IDT_SW_NTP4_BARLTBASE2, IDT_SW_NTP4_BARUTBASE2}, + {IDT_SW_NTP4_BARSETUP3, IDT_SW_NTP4_BARLIMIT3, + IDT_SW_NTP4_BARLTBASE3, IDT_SW_NTP4_BARUTBASE3}, + {IDT_SW_NTP4_BARSETUP4, IDT_SW_NTP4_BARLIMIT4, + IDT_SW_NTP4_BARLTBASE4, IDT_SW_NTP4_BARUTBASE4}, + {IDT_SW_NTP4_BARSETUP5, IDT_SW_NTP4_BARLIMIT5, + IDT_SW_NTP4_BARLTBASE5, IDT_SW_NTP4_BARUTBASE5} } }, +/*5*/ {0}, +/*6*/ { IDT_SW_NTP6_PCIECMDSTS, IDT_SW_NTP6_PCIELCTLSTS, + IDT_SW_NTP6_NTCTL, + IDT_SW_SWPORT6CTL, IDT_SW_SWPORT6STS, + { {IDT_SW_NTP6_BARSETUP0, IDT_SW_NTP6_BARLIMIT0, + IDT_SW_NTP6_BARLTBASE0, IDT_SW_NTP6_BARUTBASE0}, + {IDT_SW_NTP6_BARSETUP1, IDT_SW_NTP6_BARLIMIT1, + IDT_SW_NTP6_BARLTBASE1, IDT_SW_NTP6_BARUTBASE1}, + {IDT_SW_NTP6_BARSETUP2, IDT_SW_NTP6_BARLIMIT2, + IDT_SW_NTP6_BARLTBASE2, IDT_SW_NTP6_BARUTBASE2}, + {IDT_SW_NTP6_BARSETUP3, IDT_SW_NTP6_BARLIMIT3, + IDT_SW_NTP6_BARLTBASE3, IDT_SW_NTP6_BARUTBASE3}, + {IDT_SW_NTP6_BARSETUP4, IDT_SW_NTP6_BARLIMIT4, + IDT_SW_NTP6_BARLTBASE4, IDT_SW_NTP6_BARUTBASE4}, + {IDT_SW_NTP6_BARSETUP5, IDT_SW_NTP6_BARLIMIT5, + IDT_SW_NTP6_BARLTBASE5, IDT_SW_NTP6_BARUTBASE5} } }, +/*7*/ {0}, +/*8*/ { IDT_SW_NTP8_PCIECMDSTS, IDT_SW_NTP8_PCIELCTLSTS, + IDT_SW_NTP8_NTCTL, + IDT_SW_SWPORT8CTL, IDT_SW_SWPORT8STS, + { {IDT_SW_NTP8_BARSETUP0, IDT_SW_NTP8_BARLIMIT0, + IDT_SW_NTP8_BARLTBASE0, IDT_SW_NTP8_BARUTBASE0}, + {IDT_SW_NTP8_BARSETUP1, IDT_SW_NTP8_BARLIMIT1, + IDT_SW_NTP8_BARLTBASE1, IDT_SW_NTP8_BARUTBASE1}, + {IDT_SW_NTP8_BARSETUP2, IDT_SW_NTP8_BARLIMIT2, + IDT_SW_NTP8_BARLTBASE2, IDT_SW_NTP8_BARUTBASE2}, + {IDT_SW_NTP8_BARSETUP3, IDT_SW_NTP8_BARLIMIT3, + IDT_SW_NTP8_BARLTBASE3, IDT_SW_NTP8_BARUTBASE3}, + {IDT_SW_NTP8_BARSETUP4, IDT_SW_NTP8_BARLIMIT4, + IDT_SW_NTP8_BARLTBASE4, IDT_SW_NTP8_BARUTBASE4}, + {IDT_SW_NTP8_BARSETUP5, IDT_SW_NTP8_BARLIMIT5, + IDT_SW_NTP8_BARLTBASE5, IDT_SW_NTP8_BARUTBASE5} } }, +/*9*/ {0}, +/*10*/ {0}, +/*11*/ {0}, +/*12*/ { IDT_SW_NTP12_PCIECMDSTS, IDT_SW_NTP12_PCIELCTLSTS, + IDT_SW_NTP12_NTCTL, + IDT_SW_SWPORT12CTL, IDT_SW_SWPORT12STS, + { {IDT_SW_NTP12_BARSETUP0, IDT_SW_NTP12_BARLIMIT0, + IDT_SW_NTP12_BARLTBASE0, IDT_SW_NTP12_BARUTBASE0}, + {IDT_SW_NTP12_BARSETUP1, IDT_SW_NTP12_BARLIMIT1, + IDT_SW_NTP12_BARLTBASE1, IDT_SW_NTP12_BARUTBASE1}, + {IDT_SW_NTP12_BARSETUP2, IDT_SW_NTP12_BARLIMIT2, + IDT_SW_NTP12_BARLTBASE2, IDT_SW_NTP12_BARUTBASE2}, + {IDT_SW_NTP12_BARSETUP3, IDT_SW_NTP12_BARLIMIT3, + IDT_SW_NTP12_BARLTBASE3, IDT_SW_NTP12_BARUTBASE3}, + {IDT_SW_NTP12_BARSETUP4, IDT_SW_NTP12_BARLIMIT4, + IDT_SW_NTP12_BARLTBASE4, IDT_SW_NTP12_BARUTBASE4}, + {IDT_SW_NTP12_BARSETUP5, IDT_SW_NTP12_BARLIMIT5, + IDT_SW_NTP12_BARLTBASE5, IDT_SW_NTP12_BARUTBASE5} } }, +/*13*/ {0}, +/*14*/ {0}, +/*15*/ {0}, +/*16*/ { IDT_SW_NTP16_PCIECMDSTS, IDT_SW_NTP16_PCIELCTLSTS, + IDT_SW_NTP16_NTCTL, + IDT_SW_SWPORT16CTL, IDT_SW_SWPORT16STS, + { {IDT_SW_NTP16_BARSETUP0, IDT_SW_NTP16_BARLIMIT0, + IDT_SW_NTP16_BARLTBASE0, IDT_SW_NTP16_BARUTBASE0}, + {IDT_SW_NTP16_BARSETUP1, IDT_SW_NTP16_BARLIMIT1, + IDT_SW_NTP16_BARLTBASE1, IDT_SW_NTP16_BARUTBASE1}, + {IDT_SW_NTP16_BARSETUP2, IDT_SW_NTP16_BARLIMIT2, + IDT_SW_NTP16_BARLTBASE2, IDT_SW_NTP16_BARUTBASE2}, + {IDT_SW_NTP16_BARSETUP3, IDT_SW_NTP16_BARLIMIT3, + IDT_SW_NTP16_BARLTBASE3, IDT_SW_NTP16_BARUTBASE3}, + {IDT_SW_NTP16_BARSETUP4, IDT_SW_NTP16_BARLIMIT4, + IDT_SW_NTP16_BARLTBASE4, IDT_SW_NTP16_BARUTBASE4}, + {IDT_SW_NTP16_BARSETUP5, IDT_SW_NTP16_BARLIMIT5, + IDT_SW_NTP16_BARLTBASE5, IDT_SW_NTP16_BARUTBASE5} } }, +/*17*/ {0}, +/*18*/ {0}, +/*19*/ {0}, +/*20*/ { IDT_SW_NTP20_PCIECMDSTS, IDT_SW_NTP20_PCIELCTLSTS, + IDT_SW_NTP20_NTCTL, + IDT_SW_SWPORT20CTL, IDT_SW_SWPORT20STS, + { {IDT_SW_NTP20_BARSETUP0, IDT_SW_NTP20_BARLIMIT0, + IDT_SW_NTP20_BARLTBASE0, IDT_SW_NTP20_BARUTBASE0}, + {IDT_SW_NTP20_BARSETUP1, IDT_SW_NTP20_BARLIMIT1, + IDT_SW_NTP20_BARLTBASE1, IDT_SW_NTP20_BARUTBASE1}, + {IDT_SW_NTP20_BARSETUP2, IDT_SW_NTP20_BARLIMIT2, + IDT_SW_NTP20_BARLTBASE2, IDT_SW_NTP20_BARUTBASE2}, + {IDT_SW_NTP20_BARSETUP3, IDT_SW_NTP20_BARLIMIT3, + IDT_SW_NTP20_BARLTBASE3, IDT_SW_NTP20_BARUTBASE3}, + {IDT_SW_NTP20_BARSETUP4, IDT_SW_NTP20_BARLIMIT4, + IDT_SW_NTP20_BARLTBASE4, IDT_SW_NTP20_BARUTBASE4}, + {IDT_SW_NTP20_BARSETUP5, IDT_SW_NTP20_BARLIMIT5, + IDT_SW_NTP20_BARLTBASE5, IDT_SW_NTP20_BARUTBASE5} } }, +/*21*/ {0}, +/*22*/ {0}, +/*23*/ {0} +}; + +/* + * IDT PCIe-switch partitions table with the corresponding control, status + * and messages control registers + */ +static const struct idt_ntb_part partdata_tbl[IDT_MAX_NR_PARTS] = { +/*0*/ { IDT_SW_SWPART0CTL, IDT_SW_SWPART0STS, + {IDT_SW_SWP0MSGCTL0, IDT_SW_SWP0MSGCTL1, + IDT_SW_SWP0MSGCTL2, IDT_SW_SWP0MSGCTL3} }, +/*1*/ { IDT_SW_SWPART1CTL, IDT_SW_SWPART1STS, + {IDT_SW_SWP1MSGCTL0, IDT_SW_SWP1MSGCTL1, + IDT_SW_SWP1MSGCTL2, IDT_SW_SWP1MSGCTL3} }, +/*2*/ { IDT_SW_SWPART2CTL, IDT_SW_SWPART2STS, + {IDT_SW_SWP2MSGCTL0, IDT_SW_SWP2MSGCTL1, + IDT_SW_SWP2MSGCTL2, IDT_SW_SWP2MSGCTL3} }, +/*3*/ { IDT_SW_SWPART3CTL, IDT_SW_SWPART3STS, + {IDT_SW_SWP3MSGCTL0, IDT_SW_SWP3MSGCTL1, + IDT_SW_SWP3MSGCTL2, IDT_SW_SWP3MSGCTL3} }, +/*4*/ { IDT_SW_SWPART4CTL, IDT_SW_SWPART4STS, + {IDT_SW_SWP4MSGCTL0, IDT_SW_SWP4MSGCTL1, + IDT_SW_SWP4MSGCTL2, IDT_SW_SWP4MSGCTL3} }, +/*5*/ { IDT_SW_SWPART5CTL, IDT_SW_SWPART5STS, + {IDT_SW_SWP5MSGCTL0, IDT_SW_SWP5MSGCTL1, + IDT_SW_SWP5MSGCTL2, IDT_SW_SWP5MSGCTL3} }, +/*6*/ { IDT_SW_SWPART6CTL, IDT_SW_SWPART6STS, + {IDT_SW_SWP6MSGCTL0, IDT_SW_SWP6MSGCTL1, + IDT_SW_SWP6MSGCTL2, IDT_SW_SWP6MSGCTL3} }, +/*7*/ { IDT_SW_SWPART7CTL, IDT_SW_SWPART7STS, + {IDT_SW_SWP7MSGCTL0, IDT_SW_SWP7MSGCTL1, + IDT_SW_SWP7MSGCTL2, IDT_SW_SWP7MSGCTL3} } +}; + +/* + * DebugFS directory to place the driver debug file + */ +static struct dentry *dbgfs_topdir; + +/*============================================================================= + * 1. IDT PCIe-switch registers IO-functions + * + * Beside ordinary configuration space registers IDT PCIe-switch expose + * global configuration registers, which are used to determine state of other + * device ports as well as being notified of some switch-related events. + * Additionally all the configuration space registers of all the IDT + * PCIe-switch functions are mapped to the Global Address space, so each + * function can determine a configuration of any other PCI-function. + * Functions declared in this chapter are created to encapsulate access + * to configuration and global registers, so the driver code just need to + * provide IDT NTB hardware descriptor and a register address. + *============================================================================= + */ + +/* + * idt_nt_write() - PCI configuration space registers write method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * @data: Value to write to the register + * + * IDT PCIe-switch registers are all Little endian. + */ +static void idt_nt_write(struct idt_ntb_dev *ndev, + const unsigned int reg, const u32 data) +{ + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_PCI_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return; + + /* Just write the value to the specified register */ + iowrite32(data, ndev->cfgspc + (ptrdiff_t)reg); +} + +/* + * idt_nt_read() - PCI configuration space registers read method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * + * IDT PCIe-switch Global configuration registers are all Little endian. + * + * Return: register value + */ +static u32 idt_nt_read(struct idt_ntb_dev *ndev, const unsigned int reg) +{ + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_PCI_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return ~0; + + /* Just read the value from the specified register */ + return ioread32(ndev->cfgspc + (ptrdiff_t)reg); +} + +/* + * idt_sw_write() - Global registers write method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * @data: Value to write to the register + * + * IDT PCIe-switch Global configuration registers are all Little endian. + */ +static void idt_sw_write(struct idt_ntb_dev *ndev, + const unsigned int reg, const u32 data) +{ + unsigned long irqflags; + + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_SW_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return; + + /* Lock GASA registers operations */ + spin_lock_irqsave(&ndev->gasa_lock, irqflags); + /* Set the global register address */ + iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR); + /* Put the new value of the register */ + iowrite32(data, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA); + /* Make sure the PCIe transactions are executed */ + mmiowb(); + /* Unlock GASA registers operations */ + spin_unlock_irqrestore(&ndev->gasa_lock, irqflags); +} + +/* + * idt_sw_read() - Global registers read method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * + * IDT PCIe-switch Global configuration registers are all Little endian. + * + * Return: register value + */ +static u32 idt_sw_read(struct idt_ntb_dev *ndev, const unsigned int reg) +{ + unsigned long irqflags; + u32 data; + + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_SW_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return ~0; + + /* Lock GASA registers operations */ + spin_lock_irqsave(&ndev->gasa_lock, irqflags); + /* Set the global register address */ + iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR); + /* Get the data of the register (read ops acts as MMIO barrier) */ + data = ioread32(ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA); + /* Unlock GASA registers operations */ + spin_unlock_irqrestore(&ndev->gasa_lock, irqflags); + + return data; +} + +/* + * idt_reg_set_bits() - set bits of a passed register + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to change bits of + * @reg_lock: Register access spin lock + * @valid_mask: Mask of valid bits + * @set_bits: Bitmask to set + * + * Helper method to check whether a passed bitfield is valid and set + * corresponding bits of a register. + * + * WARNING! Make sure the passed register isn't accessed over plane + * idt_nt_write() method (read method is ok to be used concurrently). + * + * Return: zero on success, negative error on invalid bitmask. + */ +static inline int idt_reg_set_bits(struct idt_ntb_dev *ndev, unsigned int reg, + spinlock_t *reg_lock, + u64 valid_mask, u64 set_bits) +{ + unsigned long irqflags; + u32 data; + + if (set_bits & ~(u64)valid_mask) + return -EINVAL; + + /* Lock access to the register unless the change is written back */ + spin_lock_irqsave(reg_lock, irqflags); + data = idt_nt_read(ndev, reg) | (u32)set_bits; + idt_nt_write(ndev, reg, data); + /* Unlock the register */ + spin_unlock_irqrestore(reg_lock, irqflags); + + return 0; +} + +/* + * idt_reg_clear_bits() - clear bits of a passed register + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to change bits of + * @reg_lock: Register access spin lock + * @set_bits: Bitmask to clear + * + * Helper method to check whether a passed bitfield is valid and clear + * corresponding bits of a register. + * + * NOTE! Invalid bits are always considered cleared so it's not an error + * to clear them over. + * + * WARNING! Make sure the passed register isn't accessed over plane + * idt_nt_write() method (read method is ok to use concurrently). + */ +static inline void idt_reg_clear_bits(struct idt_ntb_dev *ndev, + unsigned int reg, spinlock_t *reg_lock, + u64 clear_bits) +{ + unsigned long irqflags; + u32 data; + + /* Lock access to the register unless the change is written back */ + spin_lock_irqsave(reg_lock, irqflags); + data = idt_nt_read(ndev, reg) & ~(u32)clear_bits; + idt_nt_write(ndev, reg, data); + /* Unlock the register */ + spin_unlock_irqrestore(reg_lock, irqflags); +} + +/*=========================================================================== + * 2. Ports operations + * + * IDT PCIe-switches can have from 3 up to 8 ports with possible + * NT-functions enabled. So all the possible ports need to be scanned looking + * for NTB activated. NTB API will have enumerated only the ports with NTB. + *=========================================================================== + */ + +/* + * idt_scan_ports() - scan IDT PCIe-switch ports collecting info in the tables + * @ndev: Pointer to the PCI device descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_scan_ports(struct idt_ntb_dev *ndev) +{ + unsigned char pidx, port, part; + u32 data, portsts, partsts; + + /* Retrieve the local port number */ + data = idt_nt_read(ndev, IDT_NT_PCIELCAP); + ndev->port = GET_FIELD(PCIELCAP_PORTNUM, data); + + /* Retrieve the local partition number */ + portsts = idt_sw_read(ndev, portdata_tbl[ndev->port].sts); + ndev->part = GET_FIELD(SWPORTxSTS_SWPART, portsts); + + /* Initialize port/partition -> index tables with invalid values */ + memset(ndev->port_idx_map, -EINVAL, sizeof(ndev->port_idx_map)); + memset(ndev->part_idx_map, -EINVAL, sizeof(ndev->part_idx_map)); + + /* + * Walk over all the possible ports checking whether any of them has + * NT-function activated + */ + ndev->peer_cnt = 0; + for (pidx = 0; pidx < ndev->swcfg->port_cnt; pidx++) { + port = ndev->swcfg->ports[pidx]; + /* Skip local port */ + if (port == ndev->port) + continue; + + /* Read the port status register to get it partition */ + portsts = idt_sw_read(ndev, portdata_tbl[port].sts); + part = GET_FIELD(SWPORTxSTS_SWPART, portsts); + + /* Retrieve the partition status */ + partsts = idt_sw_read(ndev, partdata_tbl[part].sts); + /* Check if partition state is active and port has NTB */ + if (IS_FLD_SET(SWPARTxSTS_STATE, partsts, ACT) && + (IS_FLD_SET(SWPORTxSTS_MODE, portsts, NT) || + IS_FLD_SET(SWPORTxSTS_MODE, portsts, USNT) || + IS_FLD_SET(SWPORTxSTS_MODE, portsts, USNTDMA) || + IS_FLD_SET(SWPORTxSTS_MODE, portsts, NTDMA))) { + /* Save the port and partition numbers */ + ndev->peers[ndev->peer_cnt].port = port; + ndev->peers[ndev->peer_cnt].part = part; + /* Fill in the port/partition -> index tables */ + ndev->port_idx_map[port] = ndev->peer_cnt; + ndev->part_idx_map[part] = ndev->peer_cnt; + ndev->peer_cnt++; + } + } + + dev_dbg(&ndev->ntb.pdev->dev, "Local port: %hhu, num of peers: %hhu\n", + ndev->port, ndev->peer_cnt); + + /* It's useless to have this driver loaded if there is no any peer */ + if (ndev->peer_cnt == 0) { + dev_warn(&ndev->ntb.pdev->dev, "No active peer found\n"); + return -ENODEV; + } + + return 0; +} + +/* + * idt_ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Return: the local port number + */ +static int idt_ntb_port_number(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return ndev->port; +} + +/* + * idt_ntb_peer_port_count() - get the number of peer ports + * @ntb: NTB device context. + * + * Return the count of detected peer NT-functions. + * + * Return: number of peer ports + */ +static int idt_ntb_peer_port_count(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return ndev->peer_cnt; +} + +/* + * idt_ntb_peer_port_number() - get peer port by given index + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * Return: peer port or negative error + */ +static int idt_ntb_peer_port_number(struct ntb_dev *ntb, int pidx) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + /* Return the detected NT-function port number */ + return ndev->peers[pidx].port; +} + +/* + * idt_ntb_peer_port_idx() - get peer port index by given port number + * @ntb: NTB device context. + * @port: Peer port number. + * + * Internal port -> index table is pre-initialized with -EINVAL values, + * so we just need to return it value + * + * Return: peer NT-function port index or negative error + */ +static int idt_ntb_peer_port_idx(struct ntb_dev *ntb, int port) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (port < 0 || IDT_MAX_NR_PORTS <= port) + return -EINVAL; + + return ndev->port_idx_map[port]; +} + +/*=========================================================================== + * 3. Link status operations + * There is no any ready-to-use method to have peer ports notified if NTB + * link is set up or got down. Instead global signal can be used instead. + * In case if any one of ports changes local NTB link state, it sends + * global signal and clears corresponding global state bit. Then all the ports + * receive a notification of that, so to make client driver being aware of + * possible NTB link change. + * Additionally each of active NT-functions is subscribed to PCIe-link + * state changes of peer ports. + *=========================================================================== + */ + +static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev); + +/* + * idt_init_link() - Initialize NTB link state notification subsystem + * @ndev: IDT NTB hardware driver descriptor + * + * Function performs the basic initialization of some global registers + * needed to enable IRQ-based notifications of PCIe Link Up/Down and + * Global Signal events. + * NOTE Since it's not possible to determine when all the NTB peer drivers are + * unloaded as well as have those registers accessed concurrently, we must + * preinitialize them with the same value and leave it uncleared on local + * driver unload. + */ +static void idt_init_link(struct idt_ntb_dev *ndev) +{ + u32 part_mask, port_mask, se_mask; + unsigned char pidx; + + /* Initialize spin locker of Mapping Table access registers */ + spin_lock_init(&ndev->mtbl_lock); + + /* Walk over all detected peers collecting port and partition masks */ + port_mask = ~BIT(ndev->port); + part_mask = ~BIT(ndev->part); + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + port_mask &= ~BIT(ndev->peers[pidx].port); + part_mask &= ~BIT(ndev->peers[pidx].part); + } + + /* Clean the Link Up/Down and GLobal Signal status registers */ + idt_sw_write(ndev, IDT_SW_SELINKUPSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SELINKDNSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)-1); + + /* Unmask NT-activated partitions to receive Global Switch events */ + idt_sw_write(ndev, IDT_SW_SEPMSK, part_mask); + + /* Enable PCIe Link Up events of NT-activated ports */ + idt_sw_write(ndev, IDT_SW_SELINKUPMSK, port_mask); + + /* Enable PCIe Link Down events of NT-activated ports */ + idt_sw_write(ndev, IDT_SW_SELINKDNMSK, port_mask); + + /* Unmask NT-activated partitions to receive Global Signal events */ + idt_sw_write(ndev, IDT_SW_SEGSIGMSK, part_mask); + + /* Unmask Link Up/Down and Global Switch Events */ + se_mask = ~(IDT_SEMSK_LINKUP | IDT_SEMSK_LINKDN | IDT_SEMSK_GSIGNAL); + idt_sw_write(ndev, IDT_SW_SEMSK, se_mask); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB link status events initialized"); +} + +/* + * idt_deinit_link() - deinitialize link subsystem + * @ndev: IDT NTB hardware driver descriptor + * + * Just disable the link back. + */ +static void idt_deinit_link(struct idt_ntb_dev *ndev) +{ + /* Disable the link */ + idt_ntb_local_link_disable(ndev); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB link status events deinitialized"); +} + +/* + * idt_se_isr() - switch events ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * This driver doesn't support IDT PCIe-switch dynamic reconfigurations, + * Failover capability, etc, so switch events are utilized to notify of + * PCIe and NTB link events. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_se_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + u32 sests; + + /* Read Switch Events status */ + sests = idt_sw_read(ndev, IDT_SW_SESTS); + + /* Clean the Link Up/Down and Global Signal status registers */ + idt_sw_write(ndev, IDT_SW_SELINKUPSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SELINKDNSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)-1); + + /* Clean the corresponding interrupt bit */ + idt_nt_write(ndev, IDT_NT_NTINTSTS, IDT_NTINTSTS_SEVENT); + + dev_dbg(&ndev->ntb.pdev->dev, "SE IRQ detected %#08x (SESTS %#08x)", + ntint_sts, sests); + + /* Notify the client driver of possible link state change */ + ntb_link_event(&ndev->ntb); +} + +/* + * idt_ntb_local_link_enable() - enable the local NTB link. + * @ndev: IDT NTB hardware driver descriptor + * + * In order to enable the NTB link we need: + * - enable Completion TLPs translation + * - initialize mapping table to enable the Request ID translation + * - notify peers of NTB link state change + */ +static void idt_ntb_local_link_enable(struct idt_ntb_dev *ndev) +{ + u32 reqid, mtbldata = 0; + unsigned long irqflags; + + /* Enable the ID protection and Completion TLPs translation */ + idt_nt_write(ndev, IDT_NT_NTCTL, IDT_NTCTL_CPEN); + + /* Retrieve the current Requester ID (Bus:Device:Function) */ + reqid = idt_nt_read(ndev, IDT_NT_REQIDCAP); + + /* + * Set the corresponding NT Mapping table entry of port partition index + * with the data to perform the Request ID translation + */ + mtbldata = SET_FIELD(NTMTBLDATA_REQID, 0, reqid) | + SET_FIELD(NTMTBLDATA_PART, 0, ndev->part) | + IDT_NTMTBLDATA_VALID; + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); + idt_nt_write(ndev, IDT_NT_NTMTBLDATA, mtbldata); + mmiowb(); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + /* Notify the peers by setting and clearing the global signal bit */ + idt_nt_write(ndev, IDT_NT_NTGSIGNAL, IDT_NTGSIGNAL_SET); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)1 << ndev->part); +} + +/* + * idt_ntb_local_link_disable() - disable the local NTB link. + * @ndev: IDT NTB hardware driver descriptor + * + * In order to enable the NTB link we need: + * - disable Completion TLPs translation + * - clear corresponding mapping table entry + * - notify peers of NTB link state change + */ +static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev) +{ + unsigned long irqflags; + + /* Disable Completion TLPs translation */ + idt_nt_write(ndev, IDT_NT_NTCTL, 0); + + /* Clear the corresponding NT Mapping table entry */ + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); + idt_nt_write(ndev, IDT_NT_NTMTBLDATA, 0); + mmiowb(); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + /* Notify the peers by setting and clearing the global signal bit */ + idt_nt_write(ndev, IDT_NT_NTGSIGNAL, IDT_NTGSIGNAL_SET); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)1 << ndev->part); +} + +/* + * idt_ntb_local_link_is_up() - test wethter local NTB link is up + * @ndev: IDT NTB hardware driver descriptor + * + * Local link is up under the following conditions: + * - Bus mastering is enabled + * - NTCTL has Completion TLPs translation enabled + * - Mapping table permits Request TLPs translation + * NOTE: We don't need to check PCIe link state since it's obviously + * up while we are able to communicate with IDT PCIe-switch + * + * Return: true if link is up, otherwise false + */ +static bool idt_ntb_local_link_is_up(struct idt_ntb_dev *ndev) +{ + unsigned long irqflags; + u32 data; + + /* Read the local Bus Master Enable status */ + data = idt_nt_read(ndev, IDT_NT_PCICMDSTS); + if (!(data & IDT_PCICMDSTS_BME)) + return false; + + /* Read the local Completion TLPs translation enable status */ + data = idt_nt_read(ndev, IDT_NT_NTCTL); + if (!(data & IDT_NTCTL_CPEN)) + return false; + + /* Read Mapping table entry corresponding to the local partition */ + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); + data = idt_nt_read(ndev, IDT_NT_NTMTBLDATA); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + return !!(data & IDT_NTMTBLDATA_VALID); +} + +/* + * idt_ntb_peer_link_is_up() - test whether peer NTB link is up + * @ndev: IDT NTB hardware driver descriptor + * @pidx: Peer port index + * + * Peer link is up under the following conditions: + * - PCIe link is up + * - Bus mastering is enabled + * - NTCTL has Completion TLPs translation enabled + * - Mapping table permits Request TLPs translation + * + * Return: true if link is up, otherwise false + */ +static bool idt_ntb_peer_link_is_up(struct idt_ntb_dev *ndev, int pidx) +{ + unsigned long irqflags; + unsigned char port; + u32 data; + + /* Retrieve the device port number */ + port = ndev->peers[pidx].port; + + /* Check whether PCIe link is up */ + data = idt_sw_read(ndev, portdata_tbl[port].sts); + if (!(data & IDT_SWPORTxSTS_LINKUP)) + return false; + + /* Check whether bus mastering is enabled on the peer port */ + data = idt_sw_read(ndev, portdata_tbl[port].pcicmdsts); + if (!(data & IDT_PCICMDSTS_BME)) + return false; + + /* Check if Completion TLPs translation is enabled on the peer port */ + data = idt_sw_read(ndev, portdata_tbl[port].ntctl); + if (!(data & IDT_NTCTL_CPEN)) + return false; + + /* Read Mapping table entry corresponding to the peer partition */ + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->peers[pidx].part); + data = idt_nt_read(ndev, IDT_NT_NTMTBLDATA); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + return !!(data & IDT_NTMTBLDATA_VALID); +} + +/* + * idt_ntb_link_is_up() - get the current ntb link state (NTB API callback) + * @ntb: NTB device context. + * @speed: OUT - The link speed expressed as PCIe generation number. + * @width: OUT - The link width expressed as the number of PCIe lanes. + * + * Get the bitfield of NTB link states for all peer ports + * + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. + */ +static u64 idt_ntb_link_is_up(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + unsigned char pidx; + u64 status; + u32 data; + + /* Retrieve the local link speed and width */ + if (speed != NULL || width != NULL) { + data = idt_nt_read(ndev, IDT_NT_PCIELCTLSTS); + if (speed != NULL) + *speed = GET_FIELD(PCIELCTLSTS_CLS, data); + if (width != NULL) + *width = GET_FIELD(PCIELCTLSTS_NLW, data); + } + + /* If local NTB link isn't up then all the links are considered down */ + if (!idt_ntb_local_link_is_up(ndev)) + return 0; + + /* Collect all the peer ports link states into the bitfield */ + status = 0; + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + if (idt_ntb_peer_link_is_up(ndev, pidx)) + status |= ((u64)1 << pidx); + } + + return status; +} + +/* + * idt_ntb_link_enable() - enable local port ntb link (NTB API callback) + * @ntb: NTB device context. + * @max_speed: The maximum link speed expressed as PCIe generation number. + * @max_width: The maximum link width expressed as the number of PCIe lanes. + * + * Enable just local NTB link. PCIe link parameters are ignored. + * + * Return: always zero. + */ +static int idt_ntb_link_enable(struct ntb_dev *ntb, enum ntb_speed speed, + enum ntb_width width) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + /* Just enable the local NTB link */ + idt_ntb_local_link_enable(ndev); + + dev_dbg(&ndev->ntb.pdev->dev, "Local NTB link enabled"); + + return 0; +} + +/* + * idt_ntb_link_disable() - disable local port ntb link (NTB API callback) + * @ntb: NTB device context. + * + * Disable just local NTB link. + * + * Return: always zero. + */ +static int idt_ntb_link_disable(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + /* Just disable the local NTB link */ + idt_ntb_local_link_disable(ndev); + + dev_dbg(&ndev->ntb.pdev->dev, "Local NTB link disabled"); + + return 0; +} + +/*============================================================================= + * 4. Memory Window operations + * + * IDT PCIe-switches have two types of memory windows: MWs with direct + * address translation and MWs with LUT based translation. The first type of + * MWs is simple map of corresponding BAR address space to a memory space + * of specified target port. So it implemets just ont-to-one mapping. Lookup + * table in its turn can map one BAR address space to up to 24 different + * memory spaces of different ports. + * NT-functions BARs can be turned on to implement either direct or lookup + * table based address translations, so: + * BAR0 - NT configuration registers space/direct address translation + * BAR1 - direct address translation/upper address of BAR0x64 + * BAR2 - direct address translation/Lookup table with either 12 or 24 entries + * BAR3 - direct address translation/upper address of BAR2x64 + * BAR4 - direct address translation/Lookup table with either 12 or 24 entries + * BAR5 - direct address translation/upper address of BAR4x64 + * Additionally BAR2 and BAR4 can't have 24-entries LUT enabled at the same + * time. Since the BARs setup can be rather complicated this driver implements + * a scanning algorithm to have all the possible memory windows configuration + * covered. + * + * NOTE 1 BAR setup must be done before Linux kernel enumerated NT-function + * of any port, so this driver would have memory windows configurations fixed. + * In this way all initializations must be performed either by platform BIOS + * or using EEPROM connected to IDT PCIe-switch master SMBus. + * + * NOTE 2 This driver expects BAR0 mapping NT-function configuration space. + * Easy calculation can give us an upper boundary of 29 possible memory windows + * per each NT-function if all the BARs are of 32bit type. + *============================================================================= + */ + +/* + * idt_get_mw_count() - get memory window count + * @mw_type: Memory window type + * + * Return: number of memory windows with respect to the BAR type + */ +static inline unsigned char idt_get_mw_count(enum idt_mw_type mw_type) +{ + switch (mw_type) { + case IDT_MW_DIR: + return 1; + case IDT_MW_LUT12: + return 12; + case IDT_MW_LUT24: + return 24; + default: + break; + } + + return 0; +} + +/* + * idt_get_mw_name() - get memory window name + * @mw_type: Memory window type + * + * Return: pointer to a string with name + */ +static inline char *idt_get_mw_name(enum idt_mw_type mw_type) +{ + switch (mw_type) { + case IDT_MW_DIR: + return "DIR "; + case IDT_MW_LUT12: + return "LUT12"; + case IDT_MW_LUT24: + return "LUT24"; + default: + break; + } + + return "unknown"; +} + +/* + * idt_scan_mws() - scan memory windows of the port + * @ndev: IDT NTB hardware driver descriptor + * @port: Port to get number of memory windows for + * @mw_cnt: Out - number of memory windows + * + * It walks over BAR setup registers of the specified port and determines + * the memory windows parameters if any activated. + * + * Return: array of memory windows + */ +static struct idt_mw_cfg *idt_scan_mws(struct idt_ntb_dev *ndev, int port, + unsigned char *mw_cnt) +{ + struct idt_mw_cfg mws[IDT_MAX_NR_MWS], *ret_mws; + const struct idt_ntb_bar *bars; + enum idt_mw_type mw_type; + unsigned char widx, bidx, en_cnt; + bool bar_64bit = false; + int aprt_size; + u32 data; + + /* Retrieve the array of the BARs registers */ + bars = portdata_tbl[port].bars; + + /* Scan all the BARs belonging to the port */ + *mw_cnt = 0; + for (bidx = 0; bidx < IDT_BAR_CNT; bidx += 1 + bar_64bit) { + /* Read BARSETUP register value */ + data = idt_sw_read(ndev, bars[bidx].setup); + + /* Skip disabled BARs */ + if (!(data & IDT_BARSETUP_EN)) { + bar_64bit = false; + continue; + } + + /* Skip next BARSETUP if current one has 64bit addressing */ + bar_64bit = IS_FLD_SET(BARSETUP_TYPE, data, 64); + + /* Skip configuration space mapping BARs */ + if (data & IDT_BARSETUP_MODE_CFG) + continue; + + /* Retrieve MW type/entries count and aperture size */ + mw_type = GET_FIELD(BARSETUP_ATRAN, data); + en_cnt = idt_get_mw_count(mw_type); + aprt_size = (u64)1 << GET_FIELD(BARSETUP_SIZE, data); + + /* Save configurations of all available memory windows */ + for (widx = 0; widx < en_cnt; widx++, (*mw_cnt)++) { + /* + * IDT can expose a limited number of MWs, so it's bug + * to have more than the driver expects + */ + if (*mw_cnt >= IDT_MAX_NR_MWS) + return ERR_PTR(-EINVAL); + + /* Save basic MW info */ + mws[*mw_cnt].type = mw_type; + mws[*mw_cnt].bar = bidx; + mws[*mw_cnt].idx = widx; + /* It's always DWORD aligned */ + mws[*mw_cnt].addr_align = IDT_TRANS_ALIGN; + /* DIR and LUT approachs differently configure MWs */ + if (mw_type == IDT_MW_DIR) + mws[*mw_cnt].size_max = aprt_size; + else if (mw_type == IDT_MW_LUT12) + mws[*mw_cnt].size_max = aprt_size / 16; + else + mws[*mw_cnt].size_max = aprt_size / 32; + mws[*mw_cnt].size_align = (mw_type == IDT_MW_DIR) ? + IDT_DIR_SIZE_ALIGN : mws[*mw_cnt].size_max; + } + } + + /* Allocate memory for memory window descriptors */ + ret_mws = devm_kcalloc(&ndev->ntb.pdev->dev, *mw_cnt, + sizeof(*ret_mws), GFP_KERNEL); + if (IS_ERR_OR_NULL(ret_mws)) + return ERR_PTR(-ENOMEM); + + /* Copy the info of detected memory windows */ + memcpy(ret_mws, mws, (*mw_cnt)*sizeof(*ret_mws)); + + return ret_mws; +} + +/* + * idt_init_mws() - initialize memory windows subsystem + * @ndev: IDT NTB hardware driver descriptor + * + * Scan BAR setup registers of local and peer ports to determine the + * outbound and inbound memory windows parameters + * + * Return: zero on success, otherwise a negative error number + */ +static int idt_init_mws(struct idt_ntb_dev *ndev) +{ + struct idt_ntb_peer *peer; + unsigned char pidx; + + /* Scan memory windows of the local port */ + ndev->mws = idt_scan_mws(ndev, ndev->port, &ndev->mw_cnt); + if (IS_ERR(ndev->mws)) { + dev_err(&ndev->ntb.pdev->dev, + "Failed to scan mws of local port %hhu", ndev->port); + return PTR_ERR(ndev->mws); + } + + /* Scan memory windows of the peer ports */ + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + peer = &ndev->peers[pidx]; + peer->mws = idt_scan_mws(ndev, peer->port, &peer->mw_cnt); + if (IS_ERR(peer->mws)) { + dev_err(&ndev->ntb.pdev->dev, + "Failed to scan mws of port %hhu", peer->port); + return PTR_ERR(peer->mws); + } + } + + /* Initialize spin locker of the LUT registers */ + spin_lock_init(&ndev->lut_lock); + + dev_dbg(&ndev->ntb.pdev->dev, "Outbound and inbound MWs initialized"); + + return 0; +} + +/* + * idt_ntb_mw_count() - number of inbound memory windows (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * + * The value is returned for the specified peer, so generally speaking it can + * be different for different port depending on the IDT PCIe-switch + * initialization. + * + * Return: the number of memory windows. + */ +static int idt_ntb_mw_count(struct ntb_dev *ntb, int pidx) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + return ndev->peers[pidx].mw_cnt; +} + +/* + * idt_ntb_mw_get_align() - inbound memory window parameters (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * The peer memory window parameters have already been determined, so just + * return the corresponding values, which mustn't change within session. + * + * Return: Zero on success, otherwise a negative error number. + */ +static int idt_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + struct idt_ntb_peer *peer; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + peer = &ndev->peers[pidx]; + + if (widx < 0 || peer->mw_cnt <= widx) + return -EINVAL; + + if (addr_align != NULL) + *addr_align = peer->mws[widx].addr_align; + + if (size_align != NULL) + *size_align = peer->mws[widx].size_align; + + if (size_max != NULL) + *size_max = peer->mws[widx].size_max; + + return 0; +} + +/* + * idt_ntb_peer_mw_count() - number of outbound memory windows + * (NTB API callback) + * @ntb: NTB device context. + * + * Outbound memory windows parameters have been determined based on the + * BAR setup registers value, which are mostly constants within one session. + * + * Return: the number of memory windows. + */ +static int idt_ntb_peer_mw_count(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return ndev->mw_cnt; +} + +/* + * idt_ntb_peer_mw_get_addr() - get map address of an outbound memory window + * (NTB API callback) + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Return just parameters of BAR resources mapping. Size reflects just the size + * of the resource + * + * Return: Zero on success, otherwise a negative error number. + */ +static int idt_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (widx < 0 || ndev->mw_cnt <= widx) + return -EINVAL; + + /* Mapping address is just properly shifted BAR resource start */ + if (base != NULL) + *base = pci_resource_start(ntb->pdev, ndev->mws[widx].bar) + + ndev->mws[widx].idx * ndev->mws[widx].size_max; + + /* Mapping size has already been calculated at MWs scanning */ + if (size != NULL) + *size = ndev->mws[widx].size_max; + + return 0; +} + +/* + * idt_ntb_peer_mw_set_trans() - set a translation address of a memory window + * (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * The Direct address translation and LUT base translation is initialized a + * bit differenet. Although the parameters restriction are now determined by + * the same code. + * + * Return: Zero on success, otherwise an error number. + */ +static int idt_ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + struct idt_mw_cfg *mw_cfg; + u32 data = 0, lutoff = 0; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + if (widx < 0 || ndev->mw_cnt <= widx) + return -EINVAL; + + /* + * Retrieve the memory window config to make sure the passed arguments + * fit it restrictions + */ + mw_cfg = &ndev->mws[widx]; + if (!IS_ALIGNED(addr, mw_cfg->addr_align)) + return -EINVAL; + if (!IS_ALIGNED(size, mw_cfg->size_align) || size > mw_cfg->size_max) + return -EINVAL; + + /* DIR and LUT based translations are initialized differently */ + if (mw_cfg->type == IDT_MW_DIR) { + const struct idt_ntb_bar *bar = &ntdata_tbl.bars[mw_cfg->bar]; + u64 limit; + /* Set destination partition of translation */ + data = idt_nt_read(ndev, bar->setup); + data = SET_FIELD(BARSETUP_TPART, data, ndev->peers[pidx].part); + idt_nt_write(ndev, bar->setup, data); + /* Set translation base address */ + idt_nt_write(ndev, bar->ltbase, (u32)addr); + idt_nt_write(ndev, bar->utbase, (u32)(addr >> 32)); + /* Set the custom BAR aperture limit */ + limit = pci_resource_start(ntb->pdev, mw_cfg->bar) + size; + idt_nt_write(ndev, bar->limit, (u32)limit); + if (IS_FLD_SET(BARSETUP_TYPE, data, 64)) + idt_nt_write(ndev, (bar + 1)->limit, (limit >> 32)); + } else { + unsigned long irqflags; + /* Initialize corresponding LUT entry */ + lutoff = SET_FIELD(LUTOFFSET_INDEX, 0, mw_cfg->idx) | + SET_FIELD(LUTOFFSET_BAR, 0, mw_cfg->bar); + data = SET_FIELD(LUTUDATA_PART, 0, ndev->peers[pidx].part) | + IDT_LUTUDATA_VALID; + spin_lock_irqsave(&ndev->lut_lock, irqflags); + idt_nt_write(ndev, IDT_NT_LUTOFFSET, lutoff); + idt_nt_write(ndev, IDT_NT_LUTLDATA, (u32)addr); + idt_nt_write(ndev, IDT_NT_LUTMDATA, (u32)(addr >> 32)); + idt_nt_write(ndev, IDT_NT_LUTUDATA, data); + mmiowb(); + spin_unlock_irqrestore(&ndev->lut_lock, irqflags); + /* Limit address isn't specified since size is fixed for LUT */ + } + + return 0; +} + +/* + * idt_ntb_peer_mw_clear_trans() - clear the outbound MW translation address + * (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * It effectively disables the translation over the specified outbound MW. + * + * Return: Zero on success, otherwise an error number. + */ +static int idt_ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + struct idt_mw_cfg *mw_cfg; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + if (widx < 0 || ndev->mw_cnt <= widx) + return -EINVAL; + + mw_cfg = &ndev->mws[widx]; + + /* DIR and LUT based translations are initialized differently */ + if (mw_cfg->type == IDT_MW_DIR) { + const struct idt_ntb_bar *bar = &ntdata_tbl.bars[mw_cfg->bar]; + u32 data; + /* Read BARSETUP to check BAR type */ + data = idt_nt_read(ndev, bar->setup); + /* Disable translation by specifying zero BAR limit */ + idt_nt_write(ndev, bar->limit, 0); + if (IS_FLD_SET(BARSETUP_TYPE, data, 64)) + idt_nt_write(ndev, (bar + 1)->limit, 0); + } else { + unsigned long irqflags; + u32 lutoff; + /* Clear the corresponding LUT entry up */ + lutoff = SET_FIELD(LUTOFFSET_INDEX, 0, mw_cfg->idx) | + SET_FIELD(LUTOFFSET_BAR, 0, mw_cfg->bar); + spin_lock_irqsave(&ndev->lut_lock, irqflags); + idt_nt_write(ndev, IDT_NT_LUTOFFSET, lutoff); + idt_nt_write(ndev, IDT_NT_LUTLDATA, 0); + idt_nt_write(ndev, IDT_NT_LUTMDATA, 0); + idt_nt_write(ndev, IDT_NT_LUTUDATA, 0); + mmiowb(); + spin_unlock_irqrestore(&ndev->lut_lock, irqflags); + } + + return 0; +} + +/*============================================================================= + * 5. Doorbell operations + * + * Doorbell functionality of IDT PCIe-switches is pretty unusual. First of + * all there is global doorbell register which state can by changed by any + * NT-function of the IDT device in accordance with global permissions. These + * permissions configs are not supported by NTB API, so it must be done by + * either BIOS or EEPROM settings. In the same way the state of the global + * doorbell is reflected to the NT-functions local inbound doorbell registers. + * It can lead to situations when client driver sets some peer doorbell bits + * and get them bounced back to local inbound doorbell if permissions are + * granted. + * Secondly there is just one IRQ vector for Doorbell, Message, Temperature + * and Switch events, so if client driver left any of Doorbell bits set and + * some other event occurred, the driver will be notified of Doorbell event + * again. + *============================================================================= + */ + +/* + * idt_db_isr() - doorbell event ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * Doorbell event happans when DBELL bit of NTINTSTS switches from 0 to 1. + * It happens only when unmasked doorbell bits are set to ones on completely + * zeroed doorbell register. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_db_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + /* + * Doorbell IRQ status will be cleaned only when client + * driver unsets all the doorbell bits. + */ + dev_dbg(&ndev->ntb.pdev->dev, "DB IRQ detected %#08x", ntint_sts); + + /* Notify the client driver of possible doorbell state change */ + ntb_db_event(&ndev->ntb, 0); +} + +/* + * idt_ntb_db_valid_mask() - get a mask of doorbell bits supported by the ntb + * (NTB API callback) + * @ntb: NTB device context. + * + * IDT PCIe-switches expose just one Doorbell register of DWORD size. + * + * Return: A mask of doorbell bits supported by the ntb. + */ +static u64 idt_ntb_db_valid_mask(struct ntb_dev *ntb) +{ + return IDT_DBELL_MASK; +} + +/* + * idt_ntb_db_read() - read the local doorbell register (NTB API callback) + * @ntb: NTB device context. + * + * There is just on inbound doorbell register of each NT-function, so + * this method return it value. + * + * Return: The bits currently set in the local doorbell register. + */ +static u64 idt_ntb_db_read(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_nt_read(ndev, IDT_NT_INDBELLSTS); +} + +/* + * idt_ntb_db_clear() - clear bits in the local doorbell register + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits of inbound doorbell register by writing ones to it. + * + * NOTE! Invalid bits are always considered cleared so it's not an error + * to clear them over. + * + * Return: always zero as success. + */ +static int idt_ntb_db_clear(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_nt_write(ndev, IDT_NT_INDBELLSTS, (u32)db_bits); + + return 0; +} + +/* + * idt_ntb_db_read_mask() - read the local doorbell mask (NTB API callback) + * @ntb: NTB device context. + * + * Each inbound doorbell bit can be masked from generating IRQ by setting + * the corresponding bit in inbound doorbell mask. So this method returns + * the value of the register. + * + * Return: The bits currently set in the local doorbell mask register. + */ +static u64 idt_ntb_db_read_mask(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_nt_read(ndev, IDT_NT_INDBELLMSK); +} + +/* + * idt_ntb_db_set_mask() - set bits in the local doorbell mask + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell mask bits to set. + * + * The inbound doorbell register mask value must be read, then OR'ed with + * passed field and only then set back. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_db_set_mask(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_reg_set_bits(ndev, IDT_NT_INDBELLMSK, &ndev->db_mask_lock, + IDT_DBELL_MASK, db_bits); +} + +/* + * idt_ntb_db_clear_mask() - clear bits in the local doorbell mask + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * The method just clears the set bits up in accordance with the passed + * bitfield. IDT PCIe-switch shall generate an interrupt if there hasn't + * been any unmasked bit set before current unmasking. Otherwise IRQ won't + * be generated since there is only one IRQ vector for all doorbells. + * + * Return: always zero as success + */ +static int idt_ntb_db_clear_mask(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_reg_clear_bits(ndev, IDT_NT_INDBELLMSK, &ndev->db_mask_lock, + db_bits); + + return 0; +} + +/* + * idt_ntb_peer_db_set() - set bits in the peer doorbell register + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell bits to set. + * + * IDT PCIe-switches exposes local outbound doorbell register to change peer + * inbound doorbell register state. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (db_bits & ~(u64)IDT_DBELL_MASK) + return -EINVAL; + + idt_nt_write(ndev, IDT_NT_OUTDBELLSET, (u32)db_bits); + return 0; +} + +/*============================================================================= + * 6. Messaging operations + * + * Each NT-function of IDT PCIe-switch has four inbound and four outbound + * message registers. Each outbound message register can be connected to one or + * even more than one peer inbound message registers by setting global + * configurations. Since NTB API permits one-on-one message registers mapping + * only, the driver acts in according with that restriction. + *============================================================================= + */ + +/* + * idt_init_msg() - initialize messaging interface + * @ndev: IDT NTB hardware driver descriptor + * + * Just initialize the message registers routing tables locker. + */ +static void idt_init_msg(struct idt_ntb_dev *ndev) +{ + unsigned char midx; + + /* Init the messages routing table lockers */ + for (midx = 0; midx < IDT_MSG_CNT; midx++) + spin_lock_init(&ndev->msg_locks[midx]); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB Messaging initialized"); +} + +/* + * idt_msg_isr() - message event ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * Message event happens when MSG bit of NTINTSTS switches from 0 to 1. + * It happens only when unmasked message status bits are set to ones on + * completely zeroed message status register. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_msg_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + /* + * Message IRQ status will be cleaned only when client + * driver unsets all the message status bits. + */ + dev_dbg(&ndev->ntb.pdev->dev, "Message IRQ detected %#08x", ntint_sts); + + /* Notify the client driver of possible message status change */ + ntb_msg_event(&ndev->ntb); +} + +/* + * idt_ntb_msg_count() - get the number of message registers (NTB API callback) + * @ntb: NTB device context. + * + * IDT PCIe-switches support four message registers. + * + * Return: the number of message registers. + */ +static int idt_ntb_msg_count(struct ntb_dev *ntb) +{ + return IDT_MSG_CNT; +} + +/* + * idt_ntb_msg_inbits() - get a bitfield of inbound message registers status + * (NTB API callback) + * @ntb: NTB device context. + * + * NT message status register is shared between inbound and outbound message + * registers status + * + * Return: bitfield of inbound message registers. + */ +static u64 idt_ntb_msg_inbits(struct ntb_dev *ntb) +{ + return (u64)IDT_INMSG_MASK; +} + +/* + * idt_ntb_msg_outbits() - get a bitfield of outbound message registers status + * (NTB API callback) + * @ntb: NTB device context. + * + * NT message status register is shared between inbound and outbound message + * registers status + * + * Return: bitfield of outbound message registers. + */ +static u64 idt_ntb_msg_outbits(struct ntb_dev *ntb) +{ + return (u64)IDT_OUTMSG_MASK; +} + +/* + * idt_ntb_msg_read_sts() - read the message registers status (NTB API callback) + * @ntb: NTB device context. + * + * IDT PCIe-switches expose message status registers to notify drivers of + * incoming data and failures in case if peer message register isn't freed. + * + * Return: status bits of message registers + */ +static u64 idt_ntb_msg_read_sts(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_nt_read(ndev, IDT_NT_MSGSTS); +} + +/* + * idt_ntb_msg_clear_sts() - clear status bits of message registers + * (NTB API callback) + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register by writing ones. + * + * NOTE! Invalid bits are always considered cleared so it's not an error + * to clear them over. + * + * Return: always zero as success. + */ +static int idt_ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_nt_write(ndev, IDT_NT_MSGSTS, sts_bits); + + return 0; +} + +/* + * idt_ntb_msg_set_mask() - set mask of message register status bits + * (NTB API callback) + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message status bits from raising an IRQ. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_reg_set_bits(ndev, IDT_NT_MSGSTSMSK, &ndev->msg_mask_lock, + IDT_MSG_MASK, mask_bits); +} + +/* + * idt_ntb_msg_clear_mask() - clear message registers mask + * (NTB API callback) + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Clear mask of message status bits IRQs. + * + * Return: always zero as success. + */ +static int idt_ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_reg_clear_bits(ndev, IDT_NT_MSGSTSMSK, &ndev->msg_mask_lock, + mask_bits); + + return 0; +} + +/* + * idt_ntb_msg_read() - read message register with specified index + * (NTB API callback) + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register and source register. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (midx < 0 || IDT_MSG_CNT <= midx) + return -EINVAL; + + /* Retrieve source port index of the message */ + if (pidx != NULL) { + u32 srcpart; + + srcpart = idt_nt_read(ndev, ntdata_tbl.msgs[midx].src); + *pidx = ndev->part_idx_map[srcpart]; + + /* Sanity check partition index (for initial case) */ + if (*pidx == -EINVAL) + *pidx = 0; + } + + /* Retrieve data of the corresponding message register */ + if (msg != NULL) + *msg = idt_nt_read(ndev, ntdata_tbl.msgs[midx].in); + + return 0; +} + +/* + * idt_ntb_msg_write() - write data to the specified message register + * (NTB API callback) + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Just try to send data to a peer. Message status register should be + * checked by client driver. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, u32 msg) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + unsigned long irqflags; + u32 swpmsgctl = 0; + + if (midx < 0 || IDT_MSG_CNT <= midx) + return -EINVAL; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + /* Collect the routing information */ + swpmsgctl = SET_FIELD(SWPxMSGCTL_REG, 0, midx) | + SET_FIELD(SWPxMSGCTL_PART, 0, ndev->peers[pidx].part); + + /* Lock the messages routing table of the specified register */ + spin_lock_irqsave(&ndev->msg_locks[midx], irqflags); + /* Set the route and send the data */ + idt_sw_write(ndev, partdata_tbl[ndev->part].msgctl[midx], swpmsgctl); + idt_nt_write(ndev, ntdata_tbl.msgs[midx].out, msg); + mmiowb(); + /* Unlock the messages routing table */ + spin_unlock_irqrestore(&ndev->msg_locks[midx], irqflags); + + /* Client driver shall check the status register */ + return 0; +} + +/*============================================================================= + * 7. Temperature sensor operations + * + * IDT PCIe-switch has an embedded temperature sensor, which can be used to + * warn a user-space of possible chip overheating. Since workload temperature + * can be different on different platforms, temperature thresholds as well as + * general sensor settings must be setup in the framework of BIOS/EEPROM + * initializations. It includes the actual sensor enabling as well. + *============================================================================= + */ + +/* + * idt_read_temp() - read temperature from chip sensor + * @ntb: NTB device context. + * @val: OUT - integer value of temperature + * @frac: OUT - fraction + */ +static void idt_read_temp(struct idt_ntb_dev *ndev, unsigned char *val, + unsigned char *frac) +{ + u32 data; + + /* Read the data from TEMP field of the TMPSTS register */ + data = idt_sw_read(ndev, IDT_SW_TMPSTS); + data = GET_FIELD(TMPSTS_TEMP, data); + /* TEMP field has one fractional bit and seven integer bits */ + *val = data >> 1; + *frac = ((data & 0x1) ? 5 : 0); +} + +/* + * idt_temp_isr() - temperature sensor alarm events ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * It handles events of temperature crossing alarm thresholds. Since reading + * of TMPALARM register clears it up, the function doesn't analyze the + * read value, instead the current temperature value just warningly printed to + * log. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_temp_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + unsigned char val, frac; + + /* Read the current temperature value */ + idt_read_temp(ndev, &val, &frac); + + /* Read the temperature alarm to clean the alarm status out */ + /*(void)idt_sw_read(ndev, IDT_SW_TMPALARM);*/ + + /* Clean the corresponding interrupt bit */ + idt_nt_write(ndev, IDT_NT_NTINTSTS, IDT_NTINTSTS_TMPSENSOR); + + dev_dbg(&ndev->ntb.pdev->dev, + "Temp sensor IRQ detected %#08x", ntint_sts); + + /* Print temperature value to log */ + dev_warn(&ndev->ntb.pdev->dev, "Temperature %hhu.%hhu", val, frac); +} + +/*============================================================================= + * 8. ISRs related operations + * + * IDT PCIe-switch has strangely developed IRQ system. There is just one + * interrupt vector for doorbell and message registers. So the hardware driver + * can't determine actual source of IRQ if, for example, message event happened + * while any of unmasked doorbell is still set. The similar situation may be if + * switch or temperature sensor events pop up. The difference is that SEVENT + * and TMPSENSOR bits of NT interrupt status register can be cleaned by + * IRQ handler so a next interrupt request won't have false handling of + * corresponding events. + * The hardware driver has only bottom-half handler of the IRQ, since if any + * of events happened the device won't raise it again before the last one is + * handled by clearing of corresponding NTINTSTS bit. + *============================================================================= + */ + +static irqreturn_t idt_thread_isr(int irq, void *devid); + +/* + * idt_init_isr() - initialize PCIe interrupt handler + * @ndev: IDT NTB hardware driver descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_init_isr(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + u32 ntint_mask; + int ret; + + /* Allocate just one interrupt vector for the ISR */ + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI | PCI_IRQ_LEGACY); + if (ret != 1) { + dev_err(&pdev->dev, "Failed to allocate IRQ vector"); + return ret; + } + + /* Retrieve the IRQ vector */ + ret = pci_irq_vector(pdev, 0); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to get IRQ vector"); + goto err_free_vectors; + } + + /* Set the IRQ handler */ + ret = devm_request_threaded_irq(&pdev->dev, ret, NULL, idt_thread_isr, + IRQF_ONESHOT, NTB_IRQNAME, ndev); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to set MSI IRQ handler, %d", ret); + goto err_free_vectors; + } + + /* Unmask Message/Doorbell/SE/Temperature interrupts */ + ntint_mask = idt_nt_read(ndev, IDT_NT_NTINTMSK) & ~IDT_NTINTMSK_ALL; + idt_nt_write(ndev, IDT_NT_NTINTMSK, ntint_mask); + + /* From now on the interrupts are enabled */ + dev_dbg(&pdev->dev, "NTB interrupts initialized"); + + return 0; + +err_free_vectors: + pci_free_irq_vectors(pdev); + + return ret; +} + + +/* + * idt_deinit_ist() - deinitialize PCIe interrupt handler + * @ndev: IDT NTB hardware driver descriptor + * + * Disable corresponding interrupts and free allocated IRQ vectors. + */ +static void idt_deinit_isr(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + u32 ntint_mask; + + /* Mask interrupts back */ + ntint_mask = idt_nt_read(ndev, IDT_NT_NTINTMSK) | IDT_NTINTMSK_ALL; + idt_nt_write(ndev, IDT_NT_NTINTMSK, ntint_mask); + + /* Manually free IRQ otherwise PCI free irq vectors will fail */ + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 0), ndev); + + /* Free allocated IRQ vectors */ + pci_free_irq_vectors(pdev); + + dev_dbg(&pdev->dev, "NTB interrupts deinitialized"); +} + +/* + * idt_thread_isr() - NT function interrupts handler + * @irq: IRQ number + * @devid: Custom buffer + * + * It reads current NT interrupts state register and handles all the event + * it declares. + * The method is bottom-half routine of actual default PCIe IRQ handler. + */ +static irqreturn_t idt_thread_isr(int irq, void *devid) +{ + struct idt_ntb_dev *ndev = devid; + bool handled = false; + u32 ntint_sts; + + /* Read the NT interrupts status register */ + ntint_sts = idt_nt_read(ndev, IDT_NT_NTINTSTS); + + /* Handle messaging interrupts */ + if (ntint_sts & IDT_NTINTSTS_MSG) { + idt_msg_isr(ndev, ntint_sts); + handled = true; + } + + /* Handle doorbell interrupts */ + if (ntint_sts & IDT_NTINTSTS_DBELL) { + idt_db_isr(ndev, ntint_sts); + handled = true; + } + + /* Handle switch event interrupts */ + if (ntint_sts & IDT_NTINTSTS_SEVENT) { + idt_se_isr(ndev, ntint_sts); + handled = true; + } + + /* Handle temperature sensor interrupt */ + if (ntint_sts & IDT_NTINTSTS_TMPSENSOR) { + idt_temp_isr(ndev, ntint_sts); + handled = true; + } + + dev_dbg(&ndev->ntb.pdev->dev, "IDT IRQs 0x%08x handled", ntint_sts); + + return handled ? IRQ_HANDLED : IRQ_NONE; +} + +/*=========================================================================== + * 9. NTB hardware driver initialization + *=========================================================================== + */ + +/* + * NTB API operations + */ +static const struct ntb_dev_ops idt_ntb_ops = { + .port_number = idt_ntb_port_number, + .peer_port_count = idt_ntb_peer_port_count, + .peer_port_number = idt_ntb_peer_port_number, + .peer_port_idx = idt_ntb_peer_port_idx, + .link_is_up = idt_ntb_link_is_up, + .link_enable = idt_ntb_link_enable, + .link_disable = idt_ntb_link_disable, + .mw_count = idt_ntb_mw_count, + .mw_get_align = idt_ntb_mw_get_align, + .peer_mw_count = idt_ntb_peer_mw_count, + .peer_mw_get_addr = idt_ntb_peer_mw_get_addr, + .peer_mw_set_trans = idt_ntb_peer_mw_set_trans, + .peer_mw_clear_trans = idt_ntb_peer_mw_clear_trans, + .db_valid_mask = idt_ntb_db_valid_mask, + .db_read = idt_ntb_db_read, + .db_clear = idt_ntb_db_clear, + .db_read_mask = idt_ntb_db_read_mask, + .db_set_mask = idt_ntb_db_set_mask, + .db_clear_mask = idt_ntb_db_clear_mask, + .peer_db_set = idt_ntb_peer_db_set, + .msg_count = idt_ntb_msg_count, + .msg_inbits = idt_ntb_msg_inbits, + .msg_outbits = idt_ntb_msg_outbits, + .msg_read_sts = idt_ntb_msg_read_sts, + .msg_clear_sts = idt_ntb_msg_clear_sts, + .msg_set_mask = idt_ntb_msg_set_mask, + .msg_clear_mask = idt_ntb_msg_clear_mask, + .msg_read = idt_ntb_msg_read, + .msg_write = idt_ntb_msg_write +}; + +/* + * idt_register_device() - register IDT NTB device + * @ndev: IDT NTB hardware driver descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_register_device(struct idt_ntb_dev *ndev) +{ + int ret; + + /* Initialize the rest of NTB device structure and register it */ + ndev->ntb.ops = &idt_ntb_ops; + ndev->ntb.topo = NTB_TOPO_PRI; + + ret = ntb_register_device(&ndev->ntb); + if (ret != 0) { + dev_err(&ndev->ntb.pdev->dev, "Failed to register NTB device"); + return ret; + } + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device successfully registered"); + + return 0; +} + +/* + * idt_unregister_device() - unregister IDT NTB device + * @ndev: IDT NTB hardware driver descriptor + */ +static void idt_unregister_device(struct idt_ntb_dev *ndev) +{ + /* Just unregister the NTB device */ + ntb_unregister_device(&ndev->ntb); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device unregistered"); +} + +/*============================================================================= + * 10. DebugFS node initialization + *============================================================================= + */ + +static ssize_t idt_dbgfs_info_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *offp); + +/* + * Driver DebugFS info file operations + */ +static const struct file_operations idt_dbgfs_info_ops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = idt_dbgfs_info_read +}; + +/* + * idt_dbgfs_info_read() - DebugFS read info node callback + * @file: File node descriptor. + * @ubuf: User-space buffer to put data to + * @count: Size of the buffer + * @offp: Offset within the buffer + */ +static ssize_t idt_dbgfs_info_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *offp) +{ + struct idt_ntb_dev *ndev = filp->private_data; + unsigned char temp, frac, idx, pidx, cnt; + ssize_t ret = 0, off = 0; + unsigned long irqflags; + enum ntb_speed speed; + enum ntb_width width; + char *strbuf; + size_t size; + u32 data; + + /* Lets limit the buffer size the way the Intel/AMD drivers do */ + size = min_t(size_t, count, 0x1000U); + + /* Allocate the memory for the buffer */ + strbuf = kmalloc(size, GFP_KERNEL); + if (strbuf == NULL) + return -ENOMEM; + + /* Put the data into the string buffer */ + off += scnprintf(strbuf + off, size - off, + "\n\t\tIDT NTB device Information:\n\n"); + + /* General local device configurations */ + off += scnprintf(strbuf + off, size - off, + "Local Port %hhu, Partition %hhu\n", ndev->port, ndev->part); + + /* Peer ports information */ + off += scnprintf(strbuf + off, size - off, "Peers:\n"); + for (idx = 0; idx < ndev->peer_cnt; idx++) { + off += scnprintf(strbuf + off, size - off, + "\t%hhu. Port %hhu, Partition %hhu\n", + idx, ndev->peers[idx].port, ndev->peers[idx].part); + } + + /* Links status */ + data = idt_ntb_link_is_up(&ndev->ntb, &speed, &width); + off += scnprintf(strbuf + off, size - off, + "NTB link status\t- 0x%08x, ", data); + off += scnprintf(strbuf + off, size - off, "PCIe Gen %d x%d lanes\n", + speed, width); + + /* Mapping table entries */ + off += scnprintf(strbuf + off, size - off, "NTB Mapping Table:\n"); + for (idx = 0; idx < IDT_MTBL_ENTRY_CNT; idx++) { + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, idx); + data = idt_nt_read(ndev, IDT_NT_NTMTBLDATA); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + /* Print valid entries only */ + if (data & IDT_NTMTBLDATA_VALID) { + off += scnprintf(strbuf + off, size - off, + "\t%hhu. Partition %d, Requester ID 0x%04x\n", + idx, GET_FIELD(NTMTBLDATA_PART, data), + GET_FIELD(NTMTBLDATA_REQID, data)); + } + } + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Outbound memory windows information */ + off += scnprintf(strbuf + off, size - off, + "Outbound Memory Windows:\n"); + for (idx = 0; idx < ndev->mw_cnt; idx += cnt) { + data = ndev->mws[idx].type; + cnt = idt_get_mw_count(data); + + /* Print Memory Window information */ + if (data == IDT_MW_DIR) + off += scnprintf(strbuf + off, size - off, + "\t%hhu.\t", idx); + else + off += scnprintf(strbuf + off, size - off, + "\t%hhu-%hhu.\t", idx, idx + cnt - 1); + + off += scnprintf(strbuf + off, size - off, "%s BAR%hhu, ", + idt_get_mw_name(data), ndev->mws[idx].bar); + + off += scnprintf(strbuf + off, size - off, + "Address align 0x%08llx, ", ndev->mws[idx].addr_align); + + off += scnprintf(strbuf + off, size - off, + "Size align 0x%08llx, Size max %llu\n", + ndev->mws[idx].size_align, ndev->mws[idx].size_max); + } + + /* Inbound memory windows information */ + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + off += scnprintf(strbuf + off, size - off, + "Inbound Memory Windows for peer %hhu (Port %hhu):\n", + pidx, ndev->peers[pidx].port); + + /* Print Memory Windows information */ + for (idx = 0; idx < ndev->peers[pidx].mw_cnt; idx += cnt) { + data = ndev->peers[pidx].mws[idx].type; + cnt = idt_get_mw_count(data); + + if (data == IDT_MW_DIR) + off += scnprintf(strbuf + off, size - off, + "\t%hhu.\t", idx); + else + off += scnprintf(strbuf + off, size - off, + "\t%hhu-%hhu.\t", idx, idx + cnt - 1); + + off += scnprintf(strbuf + off, size - off, + "%s BAR%hhu, ", idt_get_mw_name(data), + ndev->peers[pidx].mws[idx].bar); + + off += scnprintf(strbuf + off, size - off, + "Address align 0x%08llx, ", + ndev->peers[pidx].mws[idx].addr_align); + + off += scnprintf(strbuf + off, size - off, + "Size align 0x%08llx, Size max %llu\n", + ndev->peers[pidx].mws[idx].size_align, + ndev->peers[pidx].mws[idx].size_max); + } + } + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Doorbell information */ + data = idt_sw_read(ndev, IDT_SW_GDBELLSTS); + off += scnprintf(strbuf + off, size - off, + "Global Doorbell state\t- 0x%08x\n", data); + data = idt_ntb_db_read(&ndev->ntb); + off += scnprintf(strbuf + off, size - off, + "Local Doorbell state\t- 0x%08x\n", data); + data = idt_nt_read(ndev, IDT_NT_INDBELLMSK); + off += scnprintf(strbuf + off, size - off, + "Local Doorbell mask\t- 0x%08x\n", data); + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Messaging information */ + off += scnprintf(strbuf + off, size - off, + "Message event valid\t- 0x%08x\n", IDT_MSG_MASK); + data = idt_ntb_msg_read_sts(&ndev->ntb); + off += scnprintf(strbuf + off, size - off, + "Message event status\t- 0x%08x\n", data); + data = idt_nt_read(ndev, IDT_NT_MSGSTSMSK); + off += scnprintf(strbuf + off, size - off, + "Message event mask\t- 0x%08x\n", data); + off += scnprintf(strbuf + off, size - off, + "Message data:\n"); + for (idx = 0; idx < IDT_MSG_CNT; idx++) { + int src; + (void)idt_ntb_msg_read(&ndev->ntb, idx, &src, &data); + off += scnprintf(strbuf + off, size - off, + "\t%hhu. 0x%08x from peer %hhu (Port %hhu)\n", + idx, data, src, ndev->peers[src].port); + } + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Current temperature */ + idt_read_temp(ndev, &temp, &frac); + off += scnprintf(strbuf + off, size - off, + "Switch temperature\t\t- %hhu.%hhuC\n", temp, frac); + + /* Copy the buffer to the User Space */ + ret = simple_read_from_buffer(ubuf, count, offp, strbuf, off); + kfree(strbuf); + + return ret; +} + +/* + * idt_init_dbgfs() - initialize DebugFS node + * @ndev: IDT NTB hardware driver descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_init_dbgfs(struct idt_ntb_dev *ndev) +{ + char devname[64]; + + /* If the top directory is not created then do nothing */ + if (IS_ERR_OR_NULL(dbgfs_topdir)) { + dev_info(&ndev->ntb.pdev->dev, "Top DebugFS directory absent"); + return PTR_ERR(dbgfs_topdir); + } + + /* Create the info file node */ + snprintf(devname, 64, "info:%s", pci_name(ndev->ntb.pdev)); + ndev->dbgfs_info = debugfs_create_file(devname, 0400, dbgfs_topdir, + ndev, &idt_dbgfs_info_ops); + if (IS_ERR(ndev->dbgfs_info)) { + dev_dbg(&ndev->ntb.pdev->dev, "Failed to create DebugFS node"); + return PTR_ERR(ndev->dbgfs_info); + } + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device DebugFS node created"); + + return 0; +} + +/* + * idt_deinit_dbgfs() - deinitialize DebugFS node + * @ndev: IDT NTB hardware driver descriptor + * + * Just discard the info node from DebugFS + */ +static void idt_deinit_dbgfs(struct idt_ntb_dev *ndev) +{ + debugfs_remove(ndev->dbgfs_info); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device DebugFS node discarded"); +} + +/*============================================================================= + * 11. Basic PCIe device initialization + *============================================================================= + */ + +/* + * idt_check_setup() - Check whether the IDT PCIe-swtich is properly + * pre-initialized + * @pdev: Pointer to the PCI device descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_check_setup(struct pci_dev *pdev) +{ + u32 data; + int ret; + + /* Read the BARSETUP0 */ + ret = pci_read_config_dword(pdev, IDT_NT_BARSETUP0, &data); + if (ret != 0) { + dev_err(&pdev->dev, + "Failed to read BARSETUP0 config register"); + return ret; + } + + /* Check whether the BAR0 register is enabled to be of config space */ + if (!(data & IDT_BARSETUP_EN) || !(data & IDT_BARSETUP_MODE_CFG)) { + dev_err(&pdev->dev, "BAR0 doesn't map config space"); + return -EINVAL; + } + + /* Configuration space BAR0 must have certain size */ + if ((data & IDT_BARSETUP_SIZE_MASK) != IDT_BARSETUP_SIZE_CFG) { + dev_err(&pdev->dev, "Invalid size of config space"); + return -EINVAL; + } + + dev_dbg(&pdev->dev, "NTB device pre-initialized correctly"); + + return 0; +} + +/* + * Create the IDT PCIe-switch driver descriptor + * @pdev: Pointer to the PCI device descriptor + * @id: IDT PCIe-device configuration + * + * It just allocates a memory for IDT PCIe-switch device structure and + * initializes some commonly used fields. + * + * No need of release method, since managed device resource is used for + * memory allocation. + * + * Return: pointer to the descriptor, otherwise a negative error number. + */ +static struct idt_ntb_dev *idt_create_dev(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct idt_ntb_dev *ndev; + + /* Allocate memory for the IDT PCIe-device descriptor */ + ndev = devm_kzalloc(&pdev->dev, sizeof(*ndev), GFP_KERNEL); + if (IS_ERR_OR_NULL(ndev)) { + dev_err(&pdev->dev, "Memory allocation failed for descriptor"); + return ERR_PTR(-ENOMEM); + } + + /* Save the IDT PCIe-switch ports configuration */ + ndev->swcfg = (struct idt_89hpes_cfg *)id->driver_data; + /* Save the PCI-device pointer inside the NTB device structure */ + ndev->ntb.pdev = pdev; + + /* Initialize spin locker of Doorbell, Message and GASA registers */ + spin_lock_init(&ndev->db_mask_lock); + spin_lock_init(&ndev->msg_mask_lock); + spin_lock_init(&ndev->gasa_lock); + + dev_info(&pdev->dev, "IDT %s discovered", ndev->swcfg->name); + + dev_dbg(&pdev->dev, "NTB device descriptor created"); + + return ndev; +} + +/* + * idt_init_pci() - initialize the basic PCI-related subsystem + * @ndev: Pointer to the IDT PCIe-switch driver descriptor + * + * Managed device resources will be freed automatically in case of failure or + * driver detachment. + * + * Return: zero on success, otherwise negative error number. + */ +static int idt_init_pci(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + int ret; + + /* Initialize the bit mask of DMA */ + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret != 0) { + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to set DMA bit mask\n"); + return ret; + } + dev_warn(&pdev->dev, "Cannot set DMA highmem bit mask\n"); + } + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret != 0) { + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (ret != 0) { + dev_err(&pdev->dev, + "Failed to set consistent DMA bit mask\n"); + return ret; + } + dev_warn(&pdev->dev, + "Cannot set consistent DMA highmem bit mask\n"); + } + + /* + * Enable the device advanced error reporting. It's not critical to + * have AER disabled in the kernel. + */ + ret = pci_enable_pcie_error_reporting(pdev); + if (ret != 0) + dev_warn(&pdev->dev, "PCIe AER capability disabled\n"); + else /* Cleanup uncorrectable error status before getting to init */ + pci_cleanup_aer_uncorrect_error_status(pdev); + + /* First enable the PCI device */ + ret = pcim_enable_device(pdev); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to enable PCIe device\n"); + goto err_disable_aer; + } + + /* + * Enable the bus mastering, which effectively enables MSI IRQs and + * Request TLPs translation + */ + pci_set_master(pdev); + + /* Request all BARs resources and map BAR0 only */ + ret = pcim_iomap_regions_request_all(pdev, 1, NTB_NAME); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to request resources\n"); + goto err_clear_master; + } + + /* Retrieve virtual address of BAR0 - PCI configuration space */ + ndev->cfgspc = pcim_iomap_table(pdev)[0]; + + /* Put the IDT driver data pointer to the PCI-device private pointer */ + pci_set_drvdata(pdev, ndev); + + dev_dbg(&pdev->dev, "NT-function PCIe interface initialized"); + + return 0; + +err_clear_master: + pci_clear_master(pdev); +err_disable_aer: + (void)pci_disable_pcie_error_reporting(pdev); + + return ret; +} + +/* + * idt_deinit_pci() - deinitialize the basic PCI-related subsystem + * @ndev: Pointer to the IDT PCIe-switch driver descriptor + * + * Managed resources will be freed on the driver detachment + */ +static void idt_deinit_pci(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + + /* Clean up the PCI-device private data pointer */ + pci_set_drvdata(pdev, NULL); + + /* Clear the bus master disabling the Request TLPs translation */ + pci_clear_master(pdev); + + /* Disable the AER capability */ + (void)pci_disable_pcie_error_reporting(pdev); + + dev_dbg(&pdev->dev, "NT-function PCIe interface cleared"); +} + +/*=========================================================================== + * 12. PCI bus callback functions + *=========================================================================== + */ + +/* + * idt_pci_probe() - PCI device probe callback + * @pdev: Pointer to PCI device structure + * @id: PCIe device custom descriptor + * + * Return: zero on success, otherwise negative error number + */ +static int idt_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct idt_ntb_dev *ndev; + int ret; + + /* Check whether IDT PCIe-switch is properly pre-initialized */ + ret = idt_check_setup(pdev); + if (ret != 0) + return ret; + + /* Allocate the memory for IDT NTB device data */ + ndev = idt_create_dev(pdev, id); + if (IS_ERR_OR_NULL(ndev)) + return PTR_ERR(ndev); + + /* Initialize the basic PCI subsystem of the device */ + ret = idt_init_pci(ndev); + if (ret != 0) + return ret; + + /* Scan ports of the IDT PCIe-switch */ + (void)idt_scan_ports(ndev); + + /* Initialize NTB link events subsystem */ + idt_init_link(ndev); + + /* Initialize MWs subsystem */ + ret = idt_init_mws(ndev); + if (ret != 0) + goto err_deinit_link; + + /* Initialize Messaging subsystem */ + idt_init_msg(ndev); + + /* Initialize IDT interrupts handler */ + ret = idt_init_isr(ndev); + if (ret != 0) + goto err_deinit_link; + + /* Register IDT NTB devices on the NTB bus */ + ret = idt_register_device(ndev); + if (ret != 0) + goto err_deinit_isr; + + /* Initialize DebugFS info node */ + (void)idt_init_dbgfs(ndev); + + /* IDT PCIe-switch NTB driver is finally initialized */ + dev_info(&pdev->dev, "IDT NTB device is ready"); + + /* May the force be with us... */ + return 0; + +err_deinit_isr: + idt_deinit_isr(ndev); +err_deinit_link: + idt_deinit_link(ndev); + idt_deinit_pci(ndev); + + return ret; +} + +/* + * idt_pci_probe() - PCI device remove callback + * @pdev: Pointer to PCI device structure + */ +static void idt_pci_remove(struct pci_dev *pdev) +{ + struct idt_ntb_dev *ndev = pci_get_drvdata(pdev); + + /* Deinit the DebugFS node */ + idt_deinit_dbgfs(ndev); + + /* Unregister NTB device */ + idt_unregister_device(ndev); + + /* Stop the interrupts handling */ + idt_deinit_isr(ndev); + + /* Deinitialize link event subsystem */ + idt_deinit_link(ndev); + + /* Deinit basic PCI subsystem */ + idt_deinit_pci(ndev); + + /* IDT PCIe-switch NTB driver is finally initialized */ + dev_info(&pdev->dev, "IDT NTB device is removed"); + + /* Sayonara... */ +} + +/* + * IDT PCIe-switch models ports configuration structures + */ +static struct idt_89hpes_cfg idt_89hpes24nt6ag2_config = { + .name = "89HPES24NT6AG2", + .port_cnt = 6, .ports = {0, 2, 4, 6, 8, 12} +}; +static struct idt_89hpes_cfg idt_89hpes32nt8ag2_config = { + .name = "89HPES32NT8AG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes32nt8bg2_config = { + .name = "89HPES32NT8BG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes12nt12g2_config = { + .name = "89HPES12NT12G2", + .port_cnt = 3, .ports = {0, 8, 16} +}; +static struct idt_89hpes_cfg idt_89hpes16nt16g2_config = { + .name = "89HPES16NT16G2", + .port_cnt = 4, .ports = {0, 8, 12, 16} +}; +static struct idt_89hpes_cfg idt_89hpes24nt24g2_config = { + .name = "89HPES24NT24G2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes32nt24ag2_config = { + .name = "89HPES32NT24AG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes32nt24bg2_config = { + .name = "89HPES32NT24BG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; + +/* + * PCI-ids table of the supported IDT PCIe-switch devices + */ +static const struct pci_device_id idt_pci_tbl[] = { + {IDT_PCI_DEVICE_IDS(89HPES24NT6AG2, idt_89hpes24nt6ag2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT8AG2, idt_89hpes32nt8ag2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT8BG2, idt_89hpes32nt8bg2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES12NT12G2, idt_89hpes12nt12g2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES16NT16G2, idt_89hpes16nt16g2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES24NT24G2, idt_89hpes24nt24g2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT24AG2, idt_89hpes32nt24ag2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT24BG2, idt_89hpes32nt24bg2_config)}, + {0} +}; +MODULE_DEVICE_TABLE(pci, idt_pci_tbl); + +/* + * IDT PCIe-switch NT-function device driver structure definition + */ +static struct pci_driver idt_pci_driver = { + .name = KBUILD_MODNAME, + .probe = idt_pci_probe, + .remove = idt_pci_remove, + .id_table = idt_pci_tbl, +}; + +static int __init idt_pci_driver_init(void) +{ + pr_info("%s %s\n", NTB_DESC, NTB_VER); + + /* Create the top DebugFS directory if the FS is initialized */ + if (debugfs_initialized()) + dbgfs_topdir = debugfs_create_dir(KBUILD_MODNAME, NULL); + + /* Register the NTB hardware driver to handle the PCI device */ + return pci_register_driver(&idt_pci_driver); +} +module_init(idt_pci_driver_init); + +static void __exit idt_pci_driver_exit(void) +{ + /* Unregister the NTB hardware driver */ + pci_unregister_driver(&idt_pci_driver); + + /* Discard the top DebugFS directory */ + debugfs_remove_recursive(dbgfs_topdir); +} +module_exit(idt_pci_driver_exit); + diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.h b/drivers/ntb/hw/idt/ntb_hw_idt.h new file mode 100644 index 000000000000..856fd182f6f4 --- /dev/null +++ b/drivers/ntb/hw/idt/ntb_hw_idt.h @@ -0,0 +1,1149 @@ +/* + * This file is provided under a GPLv2 license. When using or + * redistributing this file, you may do so under that license. + * + * GPL LICENSE SUMMARY + * + * Copyright (C) 2016 T-Platforms All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General + * Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, one can be found http://www.gnu.org/licenses/. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * IDT PCIe-switch NTB Linux driver + * + * Contact Information: + * Serge Semin <fancer.lancer@gmail.com>, <Sergey.Semin@t-platforms.ru> + */ + +#ifndef NTB_HW_IDT_H +#define NTB_HW_IDT_H + +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/interrupt.h> +#include <linux/spinlock.h> +#include <linux/ntb.h> + + +/* + * Macro is used to create the struct pci_device_id that matches + * the supported IDT PCIe-switches + * @devname: Capitalized name of the particular device + * @data: Variable passed to the driver of the particular device + */ +#define IDT_PCI_DEVICE_IDS(devname, data) \ + .vendor = PCI_VENDOR_ID_IDT, .device = PCI_DEVICE_ID_IDT_##devname, \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, \ + .class = (PCI_CLASS_BRIDGE_OTHER << 8), .class_mask = (0xFFFF00), \ + .driver_data = (kernel_ulong_t)&data + +/* + * IDT PCIe-switches device IDs + */ +#define PCI_DEVICE_ID_IDT_89HPES24NT6AG2 0x8091 +#define PCI_DEVICE_ID_IDT_89HPES32NT8AG2 0x808F +#define PCI_DEVICE_ID_IDT_89HPES32NT8BG2 0x8088 +#define PCI_DEVICE_ID_IDT_89HPES12NT12G2 0x8092 +#define PCI_DEVICE_ID_IDT_89HPES16NT16G2 0x8090 +#define PCI_DEVICE_ID_IDT_89HPES24NT24G2 0x808E +#define PCI_DEVICE_ID_IDT_89HPES32NT24AG2 0x808C +#define PCI_DEVICE_ID_IDT_89HPES32NT24BG2 0x808A + +/* + * NT-function Configuration Space registers + * NOTE 1) The IDT PCIe-switch internal data is little-endian + * so it must be taken into account in the driver + * internals. + * 2) Additionally the registers should be accessed either + * with byte-enables corresponding to their native size or + * the size of one DWORD + * + * So to simplify the driver code, there is only DWORD-sized read/write + * operations utilized. + */ +/* PCI Express Configuration Space */ +/* PCI Express command/status register (DWORD) */ +#define IDT_NT_PCICMDSTS 0x00004U +/* PCI Express Device Capabilities (DWORD) */ +#define IDT_NT_PCIEDCAP 0x00044U +/* PCI Express Device Control/Status (WORD+WORD) */ +#define IDT_NT_PCIEDCTLSTS 0x00048U +/* PCI Express Link Capabilities (DWORD) */ +#define IDT_NT_PCIELCAP 0x0004CU +/* PCI Express Link Control/Status (WORD+WORD) */ +#define IDT_NT_PCIELCTLSTS 0x00050U +/* PCI Express Device Capabilities 2 (DWORD) */ +#define IDT_NT_PCIEDCAP2 0x00064U +/* PCI Express Device Control 2 (WORD+WORD) */ +#define IDT_NT_PCIEDCTL2 0x00068U +/* PCI Power Management Control and Status (DWORD) */ +#define IDT_NT_PMCSR 0x000C4U +/*==========================================*/ +/* IDT Proprietary NT-port-specific registers */ +/* NT-function main control registers */ +/* NT Endpoint Control (DWORD) */ +#define IDT_NT_NTCTL 0x00400U +/* NT Endpoint Interrupt Status/Mask (DWORD) */ +#define IDT_NT_NTINTSTS 0x00404U +#define IDT_NT_NTINTMSK 0x00408U +/* NT Endpoint Signal Data (DWORD) */ +#define IDT_NT_NTSDATA 0x0040CU +/* NT Endpoint Global Signal (DWORD) */ +#define IDT_NT_NTGSIGNAL 0x00410U +/* Internal Error Reporting Mask 0/1 (DWORD) */ +#define IDT_NT_NTIERRORMSK0 0x00414U +#define IDT_NT_NTIERRORMSK1 0x00418U +/* Doorbel registers */ +/* NT Outbound Doorbell Set (DWORD) */ +#define IDT_NT_OUTDBELLSET 0x00420U +/* NT Inbound Doorbell Status/Mask (DWORD) */ +#define IDT_NT_INDBELLSTS 0x00428U +#define IDT_NT_INDBELLMSK 0x0042CU +/* Message registers */ +/* Outbound Message N (DWORD) */ +#define IDT_NT_OUTMSG0 0x00430U +#define IDT_NT_OUTMSG1 0x00434U +#define IDT_NT_OUTMSG2 0x00438U +#define IDT_NT_OUTMSG3 0x0043CU +/* Inbound Message N (DWORD) */ +#define IDT_NT_INMSG0 0x00440U +#define IDT_NT_INMSG1 0x00444U +#define IDT_NT_INMSG2 0x00448U +#define IDT_NT_INMSG3 0x0044CU +/* Inbound Message Source N (DWORD) */ +#define IDT_NT_INMSGSRC0 0x00450U +#define IDT_NT_INMSGSRC1 0x00454U +#define IDT_NT_INMSGSRC2 0x00458U +#define IDT_NT_INMSGSRC3 0x0045CU +/* Message Status (DWORD) */ +#define IDT_NT_MSGSTS 0x00460U +/* Message Status Mask (DWORD) */ +#define IDT_NT_MSGSTSMSK 0x00464U +/* BAR-setup registers */ +/* BAR N Setup/Limit Address/Lower and Upper Translated Base Address (DWORD) */ +#define IDT_NT_BARSETUP0 0x00470U +#define IDT_NT_BARLIMIT0 0x00474U +#define IDT_NT_BARLTBASE0 0x00478U +#define IDT_NT_BARUTBASE0 0x0047CU +#define IDT_NT_BARSETUP1 0x00480U +#define IDT_NT_BARLIMIT1 0x00484U +#define IDT_NT_BARLTBASE1 0x00488U +#define IDT_NT_BARUTBASE1 0x0048CU +#define IDT_NT_BARSETUP2 0x00490U +#define IDT_NT_BARLIMIT2 0x00494U +#define IDT_NT_BARLTBASE2 0x00498U +#define IDT_NT_BARUTBASE2 0x0049CU +#define IDT_NT_BARSETUP3 0x004A0U +#define IDT_NT_BARLIMIT3 0x004A4U +#define IDT_NT_BARLTBASE3 0x004A8U +#define IDT_NT_BARUTBASE3 0x004ACU +#define IDT_NT_BARSETUP4 0x004B0U +#define IDT_NT_BARLIMIT4 0x004B4U +#define IDT_NT_BARLTBASE4 0x004B8U +#define IDT_NT_BARUTBASE4 0x004BCU +#define IDT_NT_BARSETUP5 0x004C0U +#define IDT_NT_BARLIMIT5 0x004C4U +#define IDT_NT_BARLTBASE5 0x004C8U +#define IDT_NT_BARUTBASE5 0x004CCU +/* NT mapping table registers */ +/* NT Mapping Table Address/Status/Data (DWORD) */ +#define IDT_NT_NTMTBLADDR 0x004D0U +#define IDT_NT_NTMTBLSTS 0x004D4U +#define IDT_NT_NTMTBLDATA 0x004D8U +/* Requester ID (Bus:Device:Function) Capture (DWORD) */ +#define IDT_NT_REQIDCAP 0x004DCU +/* Memory Windows Lookup table registers */ +/* Lookup Table Offset/Lower, Middle and Upper data (DWORD) */ +#define IDT_NT_LUTOFFSET 0x004E0U +#define IDT_NT_LUTLDATA 0x004E4U +#define IDT_NT_LUTMDATA 0x004E8U +#define IDT_NT_LUTUDATA 0x004ECU +/* NT Endpoint Uncorrectable/Correctable Errors Emulation registers (DWORD) */ +#define IDT_NT_NTUEEM 0x004F0U +#define IDT_NT_NTCEEM 0x004F4U +/* Global Address Space Access/Data registers (DWARD) */ +#define IDT_NT_GASAADDR 0x00FF8U +#define IDT_NT_GASADATA 0x00FFCU + +/* + * IDT PCIe-switch Global Configuration and Status registers + */ +/* Port N Configuration register in global space */ +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP0_PCIECMDSTS 0x01004U +#define IDT_SW_NTP0_PCIELCTLSTS 0x01050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP0_NTCTL 0x01400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP0_BARSETUP0 0x01470U +#define IDT_SW_NTP0_BARLIMIT0 0x01474U +#define IDT_SW_NTP0_BARLTBASE0 0x01478U +#define IDT_SW_NTP0_BARUTBASE0 0x0147CU +#define IDT_SW_NTP0_BARSETUP1 0x01480U +#define IDT_SW_NTP0_BARLIMIT1 0x01484U +#define IDT_SW_NTP0_BARLTBASE1 0x01488U +#define IDT_SW_NTP0_BARUTBASE1 0x0148CU +#define IDT_SW_NTP0_BARSETUP2 0x01490U +#define IDT_SW_NTP0_BARLIMIT2 0x01494U +#define IDT_SW_NTP0_BARLTBASE2 0x01498U +#define IDT_SW_NTP0_BARUTBASE2 0x0149CU +#define IDT_SW_NTP0_BARSETUP3 0x014A0U +#define IDT_SW_NTP0_BARLIMIT3 0x014A4U +#define IDT_SW_NTP0_BARLTBASE3 0x014A8U +#define IDT_SW_NTP0_BARUTBASE3 0x014ACU +#define IDT_SW_NTP0_BARSETUP4 0x014B0U +#define IDT_SW_NTP0_BARLIMIT4 0x014B4U +#define IDT_SW_NTP0_BARLTBASE4 0x014B8U +#define IDT_SW_NTP0_BARUTBASE4 0x014BCU +#define IDT_SW_NTP0_BARSETUP5 0x014C0U +#define IDT_SW_NTP0_BARLIMIT5 0x014C4U +#define IDT_SW_NTP0_BARLTBASE5 0x014C8U +#define IDT_SW_NTP0_BARUTBASE5 0x014CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP2_PCIECMDSTS 0x05004U +#define IDT_SW_NTP2_PCIELCTLSTS 0x05050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP2_NTCTL 0x05400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP2_BARSETUP0 0x05470U +#define IDT_SW_NTP2_BARLIMIT0 0x05474U +#define IDT_SW_NTP2_BARLTBASE0 0x05478U +#define IDT_SW_NTP2_BARUTBASE0 0x0547CU +#define IDT_SW_NTP2_BARSETUP1 0x05480U +#define IDT_SW_NTP2_BARLIMIT1 0x05484U +#define IDT_SW_NTP2_BARLTBASE1 0x05488U +#define IDT_SW_NTP2_BARUTBASE1 0x0548CU +#define IDT_SW_NTP2_BARSETUP2 0x05490U +#define IDT_SW_NTP2_BARLIMIT2 0x05494U +#define IDT_SW_NTP2_BARLTBASE2 0x05498U +#define IDT_SW_NTP2_BARUTBASE2 0x0549CU +#define IDT_SW_NTP2_BARSETUP3 0x054A0U +#define IDT_SW_NTP2_BARLIMIT3 0x054A4U +#define IDT_SW_NTP2_BARLTBASE3 0x054A8U +#define IDT_SW_NTP2_BARUTBASE3 0x054ACU +#define IDT_SW_NTP2_BARSETUP4 0x054B0U +#define IDT_SW_NTP2_BARLIMIT4 0x054B4U +#define IDT_SW_NTP2_BARLTBASE4 0x054B8U +#define IDT_SW_NTP2_BARUTBASE4 0x054BCU +#define IDT_SW_NTP2_BARSETUP5 0x054C0U +#define IDT_SW_NTP2_BARLIMIT5 0x054C4U +#define IDT_SW_NTP2_BARLTBASE5 0x054C8U +#define IDT_SW_NTP2_BARUTBASE5 0x054CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP4_PCIECMDSTS 0x09004U +#define IDT_SW_NTP4_PCIELCTLSTS 0x09050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP4_NTCTL 0x09400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP4_BARSETUP0 0x09470U +#define IDT_SW_NTP4_BARLIMIT0 0x09474U +#define IDT_SW_NTP4_BARLTBASE0 0x09478U +#define IDT_SW_NTP4_BARUTBASE0 0x0947CU +#define IDT_SW_NTP4_BARSETUP1 0x09480U +#define IDT_SW_NTP4_BARLIMIT1 0x09484U +#define IDT_SW_NTP4_BARLTBASE1 0x09488U +#define IDT_SW_NTP4_BARUTBASE1 0x0948CU +#define IDT_SW_NTP4_BARSETUP2 0x09490U +#define IDT_SW_NTP4_BARLIMIT2 0x09494U +#define IDT_SW_NTP4_BARLTBASE2 0x09498U +#define IDT_SW_NTP4_BARUTBASE2 0x0949CU +#define IDT_SW_NTP4_BARSETUP3 0x094A0U +#define IDT_SW_NTP4_BARLIMIT3 0x094A4U +#define IDT_SW_NTP4_BARLTBASE3 0x094A8U +#define IDT_SW_NTP4_BARUTBASE3 0x094ACU +#define IDT_SW_NTP4_BARSETUP4 0x094B0U +#define IDT_SW_NTP4_BARLIMIT4 0x094B4U +#define IDT_SW_NTP4_BARLTBASE4 0x094B8U +#define IDT_SW_NTP4_BARUTBASE4 0x094BCU +#define IDT_SW_NTP4_BARSETUP5 0x094C0U +#define IDT_SW_NTP4_BARLIMIT5 0x094C4U +#define IDT_SW_NTP4_BARLTBASE5 0x094C8U +#define IDT_SW_NTP4_BARUTBASE5 0x094CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP6_PCIECMDSTS 0x0D004U +#define IDT_SW_NTP6_PCIELCTLSTS 0x0D050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP6_NTCTL 0x0D400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP6_BARSETUP0 0x0D470U +#define IDT_SW_NTP6_BARLIMIT0 0x0D474U +#define IDT_SW_NTP6_BARLTBASE0 0x0D478U +#define IDT_SW_NTP6_BARUTBASE0 0x0D47CU +#define IDT_SW_NTP6_BARSETUP1 0x0D480U +#define IDT_SW_NTP6_BARLIMIT1 0x0D484U +#define IDT_SW_NTP6_BARLTBASE1 0x0D488U +#define IDT_SW_NTP6_BARUTBASE1 0x0D48CU +#define IDT_SW_NTP6_BARSETUP2 0x0D490U +#define IDT_SW_NTP6_BARLIMIT2 0x0D494U +#define IDT_SW_NTP6_BARLTBASE2 0x0D498U +#define IDT_SW_NTP6_BARUTBASE2 0x0D49CU +#define IDT_SW_NTP6_BARSETUP3 0x0D4A0U +#define IDT_SW_NTP6_BARLIMIT3 0x0D4A4U +#define IDT_SW_NTP6_BARLTBASE3 0x0D4A8U +#define IDT_SW_NTP6_BARUTBASE3 0x0D4ACU +#define IDT_SW_NTP6_BARSETUP4 0x0D4B0U +#define IDT_SW_NTP6_BARLIMIT4 0x0D4B4U +#define IDT_SW_NTP6_BARLTBASE4 0x0D4B8U +#define IDT_SW_NTP6_BARUTBASE4 0x0D4BCU +#define IDT_SW_NTP6_BARSETUP5 0x0D4C0U +#define IDT_SW_NTP6_BARLIMIT5 0x0D4C4U +#define IDT_SW_NTP6_BARLTBASE5 0x0D4C8U +#define IDT_SW_NTP6_BARUTBASE5 0x0D4CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP8_PCIECMDSTS 0x11004U +#define IDT_SW_NTP8_PCIELCTLSTS 0x11050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP8_NTCTL 0x11400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP8_BARSETUP0 0x11470U +#define IDT_SW_NTP8_BARLIMIT0 0x11474U +#define IDT_SW_NTP8_BARLTBASE0 0x11478U +#define IDT_SW_NTP8_BARUTBASE0 0x1147CU +#define IDT_SW_NTP8_BARSETUP1 0x11480U +#define IDT_SW_NTP8_BARLIMIT1 0x11484U +#define IDT_SW_NTP8_BARLTBASE1 0x11488U +#define IDT_SW_NTP8_BARUTBASE1 0x1148CU +#define IDT_SW_NTP8_BARSETUP2 0x11490U +#define IDT_SW_NTP8_BARLIMIT2 0x11494U +#define IDT_SW_NTP8_BARLTBASE2 0x11498U +#define IDT_SW_NTP8_BARUTBASE2 0x1149CU +#define IDT_SW_NTP8_BARSETUP3 0x114A0U +#define IDT_SW_NTP8_BARLIMIT3 0x114A4U +#define IDT_SW_NTP8_BARLTBASE3 0x114A8U +#define IDT_SW_NTP8_BARUTBASE3 0x114ACU +#define IDT_SW_NTP8_BARSETUP4 0x114B0U +#define IDT_SW_NTP8_BARLIMIT4 0x114B4U +#define IDT_SW_NTP8_BARLTBASE4 0x114B8U +#define IDT_SW_NTP8_BARUTBASE4 0x114BCU +#define IDT_SW_NTP8_BARSETUP5 0x114C0U +#define IDT_SW_NTP8_BARLIMIT5 0x114C4U +#define IDT_SW_NTP8_BARLTBASE5 0x114C8U +#define IDT_SW_NTP8_BARUTBASE5 0x114CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP12_PCIECMDSTS 0x19004U +#define IDT_SW_NTP12_PCIELCTLSTS 0x19050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP12_NTCTL 0x19400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP12_BARSETUP0 0x19470U +#define IDT_SW_NTP12_BARLIMIT0 0x19474U +#define IDT_SW_NTP12_BARLTBASE0 0x19478U +#define IDT_SW_NTP12_BARUTBASE0 0x1947CU +#define IDT_SW_NTP12_BARSETUP1 0x19480U +#define IDT_SW_NTP12_BARLIMIT1 0x19484U +#define IDT_SW_NTP12_BARLTBASE1 0x19488U +#define IDT_SW_NTP12_BARUTBASE1 0x1948CU +#define IDT_SW_NTP12_BARSETUP2 0x19490U +#define IDT_SW_NTP12_BARLIMIT2 0x19494U +#define IDT_SW_NTP12_BARLTBASE2 0x19498U +#define IDT_SW_NTP12_BARUTBASE2 0x1949CU +#define IDT_SW_NTP12_BARSETUP3 0x194A0U +#define IDT_SW_NTP12_BARLIMIT3 0x194A4U +#define IDT_SW_NTP12_BARLTBASE3 0x194A8U +#define IDT_SW_NTP12_BARUTBASE3 0x194ACU +#define IDT_SW_NTP12_BARSETUP4 0x194B0U +#define IDT_SW_NTP12_BARLIMIT4 0x194B4U +#define IDT_SW_NTP12_BARLTBASE4 0x194B8U +#define IDT_SW_NTP12_BARUTBASE4 0x194BCU +#define IDT_SW_NTP12_BARSETUP5 0x194C0U +#define IDT_SW_NTP12_BARLIMIT5 0x194C4U +#define IDT_SW_NTP12_BARLTBASE5 0x194C8U +#define IDT_SW_NTP12_BARUTBASE5 0x194CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP16_PCIECMDSTS 0x21004U +#define IDT_SW_NTP16_PCIELCTLSTS 0x21050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP16_NTCTL 0x21400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP16_BARSETUP0 0x21470U +#define IDT_SW_NTP16_BARLIMIT0 0x21474U +#define IDT_SW_NTP16_BARLTBASE0 0x21478U +#define IDT_SW_NTP16_BARUTBASE0 0x2147CU +#define IDT_SW_NTP16_BARSETUP1 0x21480U +#define IDT_SW_NTP16_BARLIMIT1 0x21484U +#define IDT_SW_NTP16_BARLTBASE1 0x21488U +#define IDT_SW_NTP16_BARUTBASE1 0x2148CU +#define IDT_SW_NTP16_BARSETUP2 0x21490U +#define IDT_SW_NTP16_BARLIMIT2 0x21494U +#define IDT_SW_NTP16_BARLTBASE2 0x21498U +#define IDT_SW_NTP16_BARUTBASE2 0x2149CU +#define IDT_SW_NTP16_BARSETUP3 0x214A0U +#define IDT_SW_NTP16_BARLIMIT3 0x214A4U +#define IDT_SW_NTP16_BARLTBASE3 0x214A8U +#define IDT_SW_NTP16_BARUTBASE3 0x214ACU +#define IDT_SW_NTP16_BARSETUP4 0x214B0U +#define IDT_SW_NTP16_BARLIMIT4 0x214B4U +#define IDT_SW_NTP16_BARLTBASE4 0x214B8U +#define IDT_SW_NTP16_BARUTBASE4 0x214BCU +#define IDT_SW_NTP16_BARSETUP5 0x214C0U +#define IDT_SW_NTP16_BARLIMIT5 0x214C4U +#define IDT_SW_NTP16_BARLTBASE5 0x214C8U +#define IDT_SW_NTP16_BARUTBASE5 0x214CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP20_PCIECMDSTS 0x29004U +#define IDT_SW_NTP20_PCIELCTLSTS 0x29050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP20_NTCTL 0x29400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP20_BARSETUP0 0x29470U +#define IDT_SW_NTP20_BARLIMIT0 0x29474U +#define IDT_SW_NTP20_BARLTBASE0 0x29478U +#define IDT_SW_NTP20_BARUTBASE0 0x2947CU +#define IDT_SW_NTP20_BARSETUP1 0x29480U +#define IDT_SW_NTP20_BARLIMIT1 0x29484U +#define IDT_SW_NTP20_BARLTBASE1 0x29488U +#define IDT_SW_NTP20_BARUTBASE1 0x2948CU +#define IDT_SW_NTP20_BARSETUP2 0x29490U +#define IDT_SW_NTP20_BARLIMIT2 0x29494U +#define IDT_SW_NTP20_BARLTBASE2 0x29498U +#define IDT_SW_NTP20_BARUTBASE2 0x2949CU +#define IDT_SW_NTP20_BARSETUP3 0x294A0U +#define IDT_SW_NTP20_BARLIMIT3 0x294A4U +#define IDT_SW_NTP20_BARLTBASE3 0x294A8U +#define IDT_SW_NTP20_BARUTBASE3 0x294ACU +#define IDT_SW_NTP20_BARSETUP4 0x294B0U +#define IDT_SW_NTP20_BARLIMIT4 0x294B4U +#define IDT_SW_NTP20_BARLTBASE4 0x294B8U +#define IDT_SW_NTP20_BARUTBASE4 0x294BCU +#define IDT_SW_NTP20_BARSETUP5 0x294C0U +#define IDT_SW_NTP20_BARLIMIT5 0x294C4U +#define IDT_SW_NTP20_BARLTBASE5 0x294C8U +#define IDT_SW_NTP20_BARUTBASE5 0x294CCU +/* IDT PCIe-switch control register (DWORD) */ +#define IDT_SW_CTL 0x3E000U +/* Boot Configuration Vector Status (DWORD) */ +#define IDT_SW_BCVSTS 0x3E004U +/* Port Clocking Mode (DWORD) */ +#define IDT_SW_PCLKMODE 0x3E008U +/* Reset Drain Delay (DWORD) */ +#define IDT_SW_RDRAINDELAY 0x3E080U +/* Port Operating Mode Change Drain Delay (DWORD) */ +#define IDT_SW_POMCDELAY 0x3E084U +/* Side Effect Delay (DWORD) */ +#define IDT_SW_SEDELAY 0x3E088U +/* Upstream Secondary Bus Reset Delay (DWORD) */ +#define IDT_SW_SSBRDELAY 0x3E08CU +/* Switch partition N Control/Status/Failover registers */ +#define IDT_SW_SWPART0CTL 0x3E100U +#define IDT_SW_SWPART0STS 0x3E104U +#define IDT_SW_SWPART0FCTL 0x3E108U +#define IDT_SW_SWPART1CTL 0x3E120U +#define IDT_SW_SWPART1STS 0x3E124U +#define IDT_SW_SWPART1FCTL 0x3E128U +#define IDT_SW_SWPART2CTL 0x3E140U +#define IDT_SW_SWPART2STS 0x3E144U +#define IDT_SW_SWPART2FCTL 0x3E148U +#define IDT_SW_SWPART3CTL 0x3E160U +#define IDT_SW_SWPART3STS 0x3E164U +#define IDT_SW_SWPART3FCTL 0x3E168U +#define IDT_SW_SWPART4CTL 0x3E180U +#define IDT_SW_SWPART4STS 0x3E184U +#define IDT_SW_SWPART4FCTL 0x3E188U +#define IDT_SW_SWPART5CTL 0x3E1A0U +#define IDT_SW_SWPART5STS 0x3E1A4U +#define IDT_SW_SWPART5FCTL 0x3E1A8U +#define IDT_SW_SWPART6CTL 0x3E1C0U +#define IDT_SW_SWPART6STS 0x3E1C4U +#define IDT_SW_SWPART6FCTL 0x3E1C8U +#define IDT_SW_SWPART7CTL 0x3E1E0U +#define IDT_SW_SWPART7STS 0x3E1E4U +#define IDT_SW_SWPART7FCTL 0x3E1E8U +/* Switch port N control and status registers */ +#define IDT_SW_SWPORT0CTL 0x3E200U +#define IDT_SW_SWPORT0STS 0x3E204U +#define IDT_SW_SWPORT0FCTL 0x3E208U +#define IDT_SW_SWPORT2CTL 0x3E240U +#define IDT_SW_SWPORT2STS 0x3E244U +#define IDT_SW_SWPORT2FCTL 0x3E248U +#define IDT_SW_SWPORT4CTL 0x3E280U +#define IDT_SW_SWPORT4STS 0x3E284U +#define IDT_SW_SWPORT4FCTL 0x3E288U +#define IDT_SW_SWPORT6CTL 0x3E2C0U +#define IDT_SW_SWPORT6STS 0x3E2C4U +#define IDT_SW_SWPORT6FCTL 0x3E2C8U +#define IDT_SW_SWPORT8CTL 0x3E300U +#define IDT_SW_SWPORT8STS 0x3E304U +#define IDT_SW_SWPORT8FCTL 0x3E308U +#define IDT_SW_SWPORT12CTL 0x3E380U +#define IDT_SW_SWPORT12STS 0x3E384U +#define IDT_SW_SWPORT12FCTL 0x3E388U +#define IDT_SW_SWPORT16CTL 0x3E400U +#define IDT_SW_SWPORT16STS 0x3E404U +#define IDT_SW_SWPORT16FCTL 0x3E408U +#define IDT_SW_SWPORT20CTL 0x3E480U +#define IDT_SW_SWPORT20STS 0x3E484U +#define IDT_SW_SWPORT20FCTL 0x3E488U +/* Switch Event registers */ +/* Switch Event Status/Mask/Partition mask (DWORD) */ +#define IDT_SW_SESTS 0x3EC00U +#define IDT_SW_SEMSK 0x3EC04U +#define IDT_SW_SEPMSK 0x3EC08U +/* Switch Event Link Up/Down Status/Mask (DWORD) */ +#define IDT_SW_SELINKUPSTS 0x3EC0CU +#define IDT_SW_SELINKUPMSK 0x3EC10U +#define IDT_SW_SELINKDNSTS 0x3EC14U +#define IDT_SW_SELINKDNMSK 0x3EC18U +/* Switch Event Fundamental Reset Status/Mask (DWORD) */ +#define IDT_SW_SEFRSTSTS 0x3EC1CU +#define IDT_SW_SEFRSTMSK 0x3EC20U +/* Switch Event Hot Reset Status/Mask (DWORD) */ +#define IDT_SW_SEHRSTSTS 0x3EC24U +#define IDT_SW_SEHRSTMSK 0x3EC28U +/* Switch Event Failover Mask (DWORD) */ +#define IDT_SW_SEFOVRMSK 0x3EC2CU +/* Switch Event Global Signal Status/Mask (DWORD) */ +#define IDT_SW_SEGSIGSTS 0x3EC30U +#define IDT_SW_SEGSIGMSK 0x3EC34U +/* NT Global Doorbell Status (DWORD) */ +#define IDT_SW_GDBELLSTS 0x3EC3CU +/* Switch partition N message M control (msgs routing table) (DWORD) */ +#define IDT_SW_SWP0MSGCTL0 0x3EE00U +#define IDT_SW_SWP1MSGCTL0 0x3EE04U +#define IDT_SW_SWP2MSGCTL0 0x3EE08U +#define IDT_SW_SWP3MSGCTL0 0x3EE0CU +#define IDT_SW_SWP4MSGCTL0 0x3EE10U +#define IDT_SW_SWP5MSGCTL0 0x3EE14U +#define IDT_SW_SWP6MSGCTL0 0x3EE18U +#define IDT_SW_SWP7MSGCTL0 0x3EE1CU +#define IDT_SW_SWP0MSGCTL1 0x3EE20U +#define IDT_SW_SWP1MSGCTL1 0x3EE24U +#define IDT_SW_SWP2MSGCTL1 0x3EE28U +#define IDT_SW_SWP3MSGCTL1 0x3EE2CU +#define IDT_SW_SWP4MSGCTL1 0x3EE30U +#define IDT_SW_SWP5MSGCTL1 0x3EE34U +#define IDT_SW_SWP6MSGCTL1 0x3EE38U +#define IDT_SW_SWP7MSGCTL1 0x3EE3CU +#define IDT_SW_SWP0MSGCTL2 0x3EE40U +#define IDT_SW_SWP1MSGCTL2 0x3EE44U +#define IDT_SW_SWP2MSGCTL2 0x3EE48U +#define IDT_SW_SWP3MSGCTL2 0x3EE4CU +#define IDT_SW_SWP4MSGCTL2 0x3EE50U +#define IDT_SW_SWP5MSGCTL2 0x3EE54U +#define IDT_SW_SWP6MSGCTL2 0x3EE58U +#define IDT_SW_SWP7MSGCTL2 0x3EE5CU +#define IDT_SW_SWP0MSGCTL3 0x3EE60U +#define IDT_SW_SWP1MSGCTL3 0x3EE64U +#define IDT_SW_SWP2MSGCTL3 0x3EE68U +#define IDT_SW_SWP3MSGCTL3 0x3EE6CU +#define IDT_SW_SWP4MSGCTL3 0x3EE70U +#define IDT_SW_SWP5MSGCTL3 0x3EE74U +#define IDT_SW_SWP6MSGCTL3 0x3EE78U +#define IDT_SW_SWP7MSGCTL3 0x3EE7CU +/* SMBus Status and Control registers (DWORD) */ +#define IDT_SW_SMBUSSTS 0x3F188U +#define IDT_SW_SMBUSCTL 0x3F18CU +/* Serial EEPROM Interface (DWORD) */ +#define IDT_SW_EEPROMINTF 0x3F190U +/* MBus I/O Expander Address N (DWORD) */ +#define IDT_SW_IOEXPADDR0 0x3F198U +#define IDT_SW_IOEXPADDR1 0x3F19CU +#define IDT_SW_IOEXPADDR2 0x3F1A0U +#define IDT_SW_IOEXPADDR3 0x3F1A4U +#define IDT_SW_IOEXPADDR4 0x3F1A8U +#define IDT_SW_IOEXPADDR5 0x3F1ACU +/* General Purpose Events Control and Status registers (DWORD) */ +#define IDT_SW_GPECTL 0x3F1B0U +#define IDT_SW_GPESTS 0x3F1B4U +/* Temperature sensor Control/Status/Alarm/Adjustment/Slope registers */ +#define IDT_SW_TMPCTL 0x3F1D4U +#define IDT_SW_TMPSTS 0x3F1D8U +#define IDT_SW_TMPALARM 0x3F1DCU +#define IDT_SW_TMPADJ 0x3F1E0U +#define IDT_SW_TSSLOPE 0x3F1E4U +/* SMBus Configuration Block header log (DWORD) */ +#define IDT_SW_SMBUSCBHL 0x3F1E8U + +/* + * Common registers related constants + * @IDT_REG_ALIGN: Registers alignment used in the driver + * @IDT_REG_PCI_MAX: Maximum PCI configuration space register value + * @IDT_REG_SW_MAX: Maximum global register value + */ +#define IDT_REG_ALIGN 4 +#define IDT_REG_PCI_MAX 0x00FFFU +#define IDT_REG_SW_MAX 0x3FFFFU + +/* + * PCICMDSTS register fields related constants + * @IDT_PCICMDSTS_IOAE: I/O access enable + * @IDT_PCICMDSTS_MAE: Memory access enable + * @IDT_PCICMDSTS_BME: Bus master enable + */ +#define IDT_PCICMDSTS_IOAE 0x00000001U +#define IDT_PCICMDSTS_MAE 0x00000002U +#define IDT_PCICMDSTS_BME 0x00000004U + +/* + * PCIEDCAP register fields related constants + * @IDT_PCIEDCAP_MPAYLOAD_MASK: Maximum payload size mask + * @IDT_PCIEDCAP_MPAYLOAD_FLD: Maximum payload size field offset + * @IDT_PCIEDCAP_MPAYLOAD_S128: Max supported payload size of 128 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S256: Max supported payload size of 256 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S512: Max supported payload size of 512 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S1024: Max supported payload size of 1024 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S2048: Max supported payload size of 2048 bytes + */ +#define IDT_PCIEDCAP_MPAYLOAD_MASK 0x00000007U +#define IDT_PCIEDCAP_MPAYLOAD_FLD 0 +#define IDT_PCIEDCAP_MPAYLOAD_S128 0x00000000U +#define IDT_PCIEDCAP_MPAYLOAD_S256 0x00000001U +#define IDT_PCIEDCAP_MPAYLOAD_S512 0x00000002U +#define IDT_PCIEDCAP_MPAYLOAD_S1024 0x00000003U +#define IDT_PCIEDCAP_MPAYLOAD_S2048 0x00000004U + +/* + * PCIEDCTLSTS registers fields related constants + * @IDT_PCIEDCTL_MPS_MASK: Maximum payload size mask + * @IDT_PCIEDCTL_MPS_FLD: MPS field offset + * @IDT_PCIEDCTL_MPS_S128: Max payload size of 128 bytes + * @IDT_PCIEDCTL_MPS_S256: Max payload size of 256 bytes + * @IDT_PCIEDCTL_MPS_S512: Max payload size of 512 bytes + * @IDT_PCIEDCTL_MPS_S1024: Max payload size of 1024 bytes + * @IDT_PCIEDCTL_MPS_S2048: Max payload size of 2048 bytes + * @IDT_PCIEDCTL_MPS_S4096: Max payload size of 4096 bytes + */ +#define IDT_PCIEDCTLSTS_MPS_MASK 0x000000E0U +#define IDT_PCIEDCTLSTS_MPS_FLD 5 +#define IDT_PCIEDCTLSTS_MPS_S128 0x00000000U +#define IDT_PCIEDCTLSTS_MPS_S256 0x00000020U +#define IDT_PCIEDCTLSTS_MPS_S512 0x00000040U +#define IDT_PCIEDCTLSTS_MPS_S1024 0x00000060U +#define IDT_PCIEDCTLSTS_MPS_S2048 0x00000080U +#define IDT_PCIEDCTLSTS_MPS_S4096 0x000000A0U + +/* + * PCIELCAP register fields related constants + * @IDT_PCIELCAP_PORTNUM_MASK: Port number field mask + * @IDT_PCIELCAP_PORTNUM_FLD: Port number field offset + */ +#define IDT_PCIELCAP_PORTNUM_MASK 0xFF000000U +#define IDT_PCIELCAP_PORTNUM_FLD 24 + +/* + * PCIELCTLSTS registers fields related constants + * @IDT_PCIELSTS_CLS_MASK: Current link speed mask + * @IDT_PCIELSTS_CLS_FLD: Current link speed field offset + * @IDT_PCIELSTS_NLW_MASK: Negotiated link width mask + * @IDT_PCIELSTS_NLW_FLD: Negotiated link width field offset + * @IDT_PCIELSTS_SCLK_COM: Common slot clock configuration + */ +#define IDT_PCIELCTLSTS_CLS_MASK 0x000F0000U +#define IDT_PCIELCTLSTS_CLS_FLD 16 +#define IDT_PCIELCTLSTS_NLW_MASK 0x03F00000U +#define IDT_PCIELCTLSTS_NLW_FLD 20 +#define IDT_PCIELCTLSTS_SCLK_COM 0x10000000U + +/* + * NTCTL register fields related constants + * @IDT_NTCTL_IDPROTDIS: ID Protection check disable (disable MTBL) + * @IDT_NTCTL_CPEN: Completion enable + * @IDT_NTCTL_RNS: Request no snoop processing (if MTBL disabled) + * @IDT_NTCTL_ATP: Address type processing (if MTBL disabled) + */ +#define IDT_NTCTL_IDPROTDIS 0x00000001U +#define IDT_NTCTL_CPEN 0x00000002U +#define IDT_NTCTL_RNS 0x00000004U +#define IDT_NTCTL_ATP 0x00000008U + +/* + * NTINTSTS register fields related constants + * @IDT_NTINTSTS_MSG: Message interrupt bit + * @IDT_NTINTSTS_DBELL: Doorbell interrupt bit + * @IDT_NTINTSTS_SEVENT: Switch Event interrupt bit + * @IDT_NTINTSTS_TMPSENSOR: Temperature sensor interrupt bit + */ +#define IDT_NTINTSTS_MSG 0x00000001U +#define IDT_NTINTSTS_DBELL 0x00000002U +#define IDT_NTINTSTS_SEVENT 0x00000008U +#define IDT_NTINTSTS_TMPSENSOR 0x00000080U + +/* + * NTINTMSK register fields related constants + * @IDT_NTINTMSK_MSG: Message interrupt mask bit + * @IDT_NTINTMSK_DBELL: Doorbell interrupt mask bit + * @IDT_NTINTMSK_SEVENT: Switch Event interrupt mask bit + * @IDT_NTINTMSK_TMPSENSOR: Temperature sensor interrupt mask bit + * @IDT_NTINTMSK_ALL: All the useful interrupts mask + */ +#define IDT_NTINTMSK_MSG 0x00000001U +#define IDT_NTINTMSK_DBELL 0x00000002U +#define IDT_NTINTMSK_SEVENT 0x00000008U +#define IDT_NTINTMSK_TMPSENSOR 0x00000080U +#define IDT_NTINTMSK_ALL \ + (IDT_NTINTMSK_MSG | IDT_NTINTMSK_DBELL | \ + IDT_NTINTMSK_SEVENT | IDT_NTINTMSK_TMPSENSOR) + +/* + * NTGSIGNAL register fields related constants + * @IDT_NTGSIGNAL_SET: Set global signal of the local partition + */ +#define IDT_NTGSIGNAL_SET 0x00000001U + +/* + * BARSETUP register fields related constants + * @IDT_BARSETUP_TYPE_MASK: Mask of the TYPE field + * @IDT_BARSETUP_TYPE_32: 32-bit addressing BAR + * @IDT_BARSETUP_TYPE_64: 64-bit addressing BAR + * @IDT_BARSETUP_PREF: Value of the BAR prefetchable field + * @IDT_BARSETUP_SIZE_MASK: Mask of the SIZE field + * @IDT_BARSETUP_SIZE_FLD: SIZE field offset + * @IDT_BARSETUP_SIZE_CFG: SIZE field value in case of config space MODE + * @IDT_BARSETUP_MODE_CFG: Configuration space BAR mode + * @IDT_BARSETUP_ATRAN_MASK: ATRAN field mask + * @IDT_BARSETUP_ATRAN_FLD: ATRAN field offset + * @IDT_BARSETUP_ATRAN_DIR: Direct address translation memory window + * @IDT_BARSETUP_ATRAN_LUT12: 12-entry lookup table + * @IDT_BARSETUP_ATRAN_LUT24: 24-entry lookup table + * @IDT_BARSETUP_TPART_MASK: TPART field mask + * @IDT_BARSETUP_TPART_FLD: TPART field offset + * @IDT_BARSETUP_EN: BAR enable bit + */ +#define IDT_BARSETUP_TYPE_MASK 0x00000006U +#define IDT_BARSETUP_TYPE_FLD 0 +#define IDT_BARSETUP_TYPE_32 0x00000000U +#define IDT_BARSETUP_TYPE_64 0x00000004U +#define IDT_BARSETUP_PREF 0x00000008U +#define IDT_BARSETUP_SIZE_MASK 0x000003F0U +#define IDT_BARSETUP_SIZE_FLD 4 +#define IDT_BARSETUP_SIZE_CFG 0x000000C0U +#define IDT_BARSETUP_MODE_CFG 0x00000400U +#define IDT_BARSETUP_ATRAN_MASK 0x00001800U +#define IDT_BARSETUP_ATRAN_FLD 11 +#define IDT_BARSETUP_ATRAN_DIR 0x00000000U +#define IDT_BARSETUP_ATRAN_LUT12 0x00000800U +#define IDT_BARSETUP_ATRAN_LUT24 0x00001000U +#define IDT_BARSETUP_TPART_MASK 0x0000E000U +#define IDT_BARSETUP_TPART_FLD 13 +#define IDT_BARSETUP_EN 0x80000000U + +/* + * NTMTBLDATA register fields related constants + * @IDT_NTMTBLDATA_VALID: Set the MTBL entry being valid + * @IDT_NTMTBLDATA_REQID_MASK: Bus:Device:Function field mask + * @IDT_NTMTBLDATA_REQID_FLD: Bus:Device:Function field offset + * @IDT_NTMTBLDATA_PART_MASK: Partition field mask + * @IDT_NTMTBLDATA_PART_FLD: Partition field offset + * @IDT_NTMTBLDATA_ATP_TRANS: Enable AT field translation on request TLPs + * @IDT_NTMTBLDATA_CNS_INV: Enable No Snoop attribute inversion of + * Completion TLPs + * @IDT_NTMTBLDATA_RNS_INV: Enable No Snoop attribute inversion of + * Request TLPs + */ +#define IDT_NTMTBLDATA_VALID 0x00000001U +#define IDT_NTMTBLDATA_REQID_MASK 0x0001FFFEU +#define IDT_NTMTBLDATA_REQID_FLD 1 +#define IDT_NTMTBLDATA_PART_MASK 0x000E0000U +#define IDT_NTMTBLDATA_PART_FLD 17 +#define IDT_NTMTBLDATA_ATP_TRANS 0x20000000U +#define IDT_NTMTBLDATA_CNS_INV 0x40000000U +#define IDT_NTMTBLDATA_RNS_INV 0x80000000U + +/* + * REQIDCAP register fields related constants + * @IDT_REQIDCAP_REQID_MASK: Request ID field mask + * @IDT_REQIDCAP_REQID_FLD: Request ID field offset + */ +#define IDT_REQIDCAP_REQID_MASK 0x0000FFFFU +#define IDT_REQIDCAP_REQID_FLD 0 + +/* + * LUTOFFSET register fields related constants + * @IDT_LUTOFFSET_INDEX_MASK: Lookup table index field mask + * @IDT_LUTOFFSET_INDEX_FLD: Lookup table index field offset + * @IDT_LUTOFFSET_BAR_MASK: Lookup table BAR select field mask + * @IDT_LUTOFFSET_BAR_FLD: Lookup table BAR select field offset + */ +#define IDT_LUTOFFSET_INDEX_MASK 0x0000001FU +#define IDT_LUTOFFSET_INDEX_FLD 0 +#define IDT_LUTOFFSET_BAR_MASK 0x00000700U +#define IDT_LUTOFFSET_BAR_FLD 8 + +/* + * LUTUDATA register fields related constants + * @IDT_LUTUDATA_PART_MASK: Partition field mask + * @IDT_LUTUDATA_PART_FLD: Partition field offset + * @IDT_LUTUDATA_VALID: Lookup table entry valid bit + */ +#define IDT_LUTUDATA_PART_MASK 0x0000000FU +#define IDT_LUTUDATA_PART_FLD 0 +#define IDT_LUTUDATA_VALID 0x80000000U + +/* + * SWPARTxSTS register fields related constants + * @IDT_SWPARTxSTS_SCI: Switch partition state change initiated + * @IDT_SWPARTxSTS_SCC: Switch partition state change completed + * @IDT_SWPARTxSTS_STATE_MASK: Switch partition state mask + * @IDT_SWPARTxSTS_STATE_FLD: Switch partition state field offset + * @IDT_SWPARTxSTS_STATE_DIS: Switch partition disabled + * @IDT_SWPARTxSTS_STATE_ACT: Switch partition enabled + * @IDT_SWPARTxSTS_STATE_RES: Switch partition in reset + * @IDT_SWPARTxSTS_US: Switch partition has upstream port + * @IDT_SWPARTxSTS_USID_MASK: Switch partition upstream port ID mask + * @IDT_SWPARTxSTS_USID_FLD: Switch partition upstream port ID field offset + * @IDT_SWPARTxSTS_NT: Upstream port has NT function + * @IDT_SWPARTxSTS_DMA: Upstream port has DMA function + */ +#define IDT_SWPARTxSTS_SCI 0x00000001U +#define IDT_SWPARTxSTS_SCC 0x00000002U +#define IDT_SWPARTxSTS_STATE_MASK 0x00000060U +#define IDT_SWPARTxSTS_STATE_FLD 5 +#define IDT_SWPARTxSTS_STATE_DIS 0x00000000U +#define IDT_SWPARTxSTS_STATE_ACT 0x00000020U +#define IDT_SWPARTxSTS_STATE_RES 0x00000060U +#define IDT_SWPARTxSTS_US 0x00000100U +#define IDT_SWPARTxSTS_USID_MASK 0x00003E00U +#define IDT_SWPARTxSTS_USID_FLD 9 +#define IDT_SWPARTxSTS_NT 0x00004000U +#define IDT_SWPARTxSTS_DMA 0x00008000U + +/* + * SWPORTxSTS register fields related constants + * @IDT_SWPORTxSTS_OMCI: Operation mode change initiated + * @IDT_SWPORTxSTS_OMCC: Operation mode change completed + * @IDT_SWPORTxSTS_LINKUP: Link up status + * @IDT_SWPORTxSTS_DS: Port lanes behave as downstream lanes + * @IDT_SWPORTxSTS_MODE_MASK: Port mode field mask + * @IDT_SWPORTxSTS_MODE_FLD: Port mode field offset + * @IDT_SWPORTxSTS_MODE_DIS: Port mode - disabled + * @IDT_SWPORTxSTS_MODE_DS: Port mode - downstream switch port + * @IDT_SWPORTxSTS_MODE_US: Port mode - upstream switch port + * @IDT_SWPORTxSTS_MODE_NT: Port mode - NT function + * @IDT_SWPORTxSTS_MODE_USNT: Port mode - upstream switch port with NTB + * @IDT_SWPORTxSTS_MODE_UNAT: Port mode - unattached + * @IDT_SWPORTxSTS_MODE_USDMA: Port mode - upstream switch port with DMA + * @IDT_SWPORTxSTS_MODE_USNTDMA:Port mode - upstream port with NTB and DMA + * @IDT_SWPORTxSTS_MODE_NTDMA: Port mode - NT function with DMA + * @IDT_SWPORTxSTS_SWPART_MASK: Port partition field mask + * @IDT_SWPORTxSTS_SWPART_FLD: Port partition field offset + * @IDT_SWPORTxSTS_DEVNUM_MASK: Port device number field mask + * @IDT_SWPORTxSTS_DEVNUM_FLD: Port device number field offset + */ +#define IDT_SWPORTxSTS_OMCI 0x00000001U +#define IDT_SWPORTxSTS_OMCC 0x00000002U +#define IDT_SWPORTxSTS_LINKUP 0x00000010U +#define IDT_SWPORTxSTS_DS 0x00000020U +#define IDT_SWPORTxSTS_MODE_MASK 0x000003C0U +#define IDT_SWPORTxSTS_MODE_FLD 6 +#define IDT_SWPORTxSTS_MODE_DIS 0x00000000U +#define IDT_SWPORTxSTS_MODE_DS 0x00000040U +#define IDT_SWPORTxSTS_MODE_US 0x00000080U +#define IDT_SWPORTxSTS_MODE_NT 0x000000C0U +#define IDT_SWPORTxSTS_MODE_USNT 0x00000100U +#define IDT_SWPORTxSTS_MODE_UNAT 0x00000140U +#define IDT_SWPORTxSTS_MODE_USDMA 0x00000180U +#define IDT_SWPORTxSTS_MODE_USNTDMA 0x000001C0U +#define IDT_SWPORTxSTS_MODE_NTDMA 0x00000200U +#define IDT_SWPORTxSTS_SWPART_MASK 0x00001C00U +#define IDT_SWPORTxSTS_SWPART_FLD 10 +#define IDT_SWPORTxSTS_DEVNUM_MASK 0x001F0000U +#define IDT_SWPORTxSTS_DEVNUM_FLD 16 + +/* + * SEMSK register fields related constants + * @IDT_SEMSK_LINKUP: Link Up event mask bit + * @IDT_SEMSK_LINKDN: Link Down event mask bit + * @IDT_SEMSK_GSIGNAL: Global Signal event mask bit + */ +#define IDT_SEMSK_LINKUP 0x00000001U +#define IDT_SEMSK_LINKDN 0x00000002U +#define IDT_SEMSK_GSIGNAL 0x00000020U + +/* + * SWPxMSGCTL register fields related constants + * @IDT_SWPxMSGCTL_REG_MASK: Register select field mask + * @IDT_SWPxMSGCTL_REG_FLD: Register select field offset + * @IDT_SWPxMSGCTL_PART_MASK: Partition select field mask + * @IDT_SWPxMSGCTL_PART_FLD: Partition select field offset + */ +#define IDT_SWPxMSGCTL_REG_MASK 0x00000003U +#define IDT_SWPxMSGCTL_REG_FLD 0 +#define IDT_SWPxMSGCTL_PART_MASK 0x00000070U +#define IDT_SWPxMSGCTL_PART_FLD 4 + +/* + * TMPSTS register fields related constants + * @IDT_TMPSTS_TEMP_MASK: Current temperature field mask + * @IDT_TMPSTS_TEMP_FLD: Current temperature field offset + */ +#define IDT_TMPSTS_TEMP_MASK 0x000000FFU +#define IDT_TMPSTS_TEMP_FLD 0 + +/* + * Helper macro to get/set the corresponding field value + * @GET_FIELD: Retrieve the value of the corresponding field + * @SET_FIELD: Set the specified field up + * @IS_FLD_SET: Check whether a field is set with value + */ +#define GET_FIELD(field, data) \ + (((u32)(data) & IDT_ ##field## _MASK) >> IDT_ ##field## _FLD) +#define SET_FIELD(field, data, value) \ + (((u32)(data) & ~IDT_ ##field## _MASK) | \ + ((u32)(value) << IDT_ ##field## _FLD)) +#define IS_FLD_SET(field, data, value) \ + (((u32)(data) & IDT_ ##field## _MASK) == IDT_ ##field## _ ##value) + +/* + * Useful registers masks: + * @IDT_DBELL_MASK: Doorbell bits mask + * @IDT_OUTMSG_MASK: Out messages status bits mask + * @IDT_INMSG_MASK: In messages status bits mask + * @IDT_MSG_MASK: Any message status bits mask + */ +#define IDT_DBELL_MASK ((u32)0xFFFFFFFFU) +#define IDT_OUTMSG_MASK ((u32)0x0000000FU) +#define IDT_INMSG_MASK ((u32)0x000F0000U) +#define IDT_MSG_MASK (IDT_INMSG_MASK | IDT_OUTMSG_MASK) + +/* + * Number of IDT NTB resources: + * @IDT_MSG_CNT: Number of Message registers + * @IDT_BAR_CNT: Number of BARs of each port + * @IDT_MTBL_ENTRY_CNT: Number mapping table entries + */ +#define IDT_MSG_CNT 4 +#define IDT_BAR_CNT 6 +#define IDT_MTBL_ENTRY_CNT 64 + +/* + * General IDT PCIe-switch constant + * @IDT_MAX_NR_PORTS: Maximum number of ports per IDT PCIe-switch + * @IDT_MAX_NR_PARTS: Maximum number of partitions per IDT PCIe-switch + * @IDT_MAX_NR_PEERS: Maximum number of NT-peers per IDT PCIe-switch + * @IDT_MAX_NR_MWS: Maximum number of Memory Widows + * @IDT_PCIE_REGSIZE: Size of the registers in bytes + * @IDT_TRANS_ALIGN: Alignment of translated base address + * @IDT_DIR_SIZE_ALIGN: Alignment of size setting for direct translated MWs. + * Even though the lower 10 bits are reserved, they are + * treated by IDT as one's so basically there is no any + * alignment of size limit for DIR address translation. + */ +#define IDT_MAX_NR_PORTS 24 +#define IDT_MAX_NR_PARTS 8 +#define IDT_MAX_NR_PEERS 8 +#define IDT_MAX_NR_MWS 29 +#define IDT_PCIE_REGSIZE 4 +#define IDT_TRANS_ALIGN 4 +#define IDT_DIR_SIZE_ALIGN 1 + +/* + * IDT Memory Windows type. Depending on the device settings, IDT supports + * Direct Address Translation MW registers and Lookup Table registers + * @IDT_MW_DIR: Direct address translation + * @IDT_MW_LUT12: 12-entry lookup table entry + * @IDT_MW_LUT24: 24-entry lookup table entry + * + * NOTE These values are exactly the same as one of the BARSETUP ATRAN field + */ +enum idt_mw_type { + IDT_MW_DIR = 0x0, + IDT_MW_LUT12 = 0x1, + IDT_MW_LUT24 = 0x2 +}; + +/* + * IDT PCIe-switch model private data + * @name: Device name + * @port_cnt: Total number of NT endpoint ports + * @ports: Port ids + */ +struct idt_89hpes_cfg { + char *name; + unsigned char port_cnt; + unsigned char ports[]; +}; + +/* + * Memory window configuration structure + * @type: Type of the memory window (direct address translation or lookup + * table) + * + * @bar: PCIe BAR the memory window referenced to + * @idx: Index of the memory window within the BAR + * + * @addr_align: Alignment of translated address + * @size_align: Alignment of memory window size + * @size_max: Maximum size of memory window + */ +struct idt_mw_cfg { + enum idt_mw_type type; + + unsigned char bar; + unsigned char idx; + + u64 addr_align; + u64 size_align; + u64 size_max; +}; + +/* + * Description structure of peer IDT NT-functions: + * @port: NT-function port + * @part: NT-function partition + * + * @mw_cnt: Number of memory windows supported by NT-function + * @mws: Array of memory windows descriptors + */ +struct idt_ntb_peer { + unsigned char port; + unsigned char part; + + unsigned char mw_cnt; + struct idt_mw_cfg *mws; +}; + +/* + * Description structure of local IDT NT-function: + * @ntb: Linux NTB-device description structure + * @swcfg: Pointer to the structure of local IDT PCIe-switch + * specific cofnfigurations + * + * @port: Local NT-function port + * @part: Local NT-function partition + * + * @peer_cnt: Number of peers with activated NTB-function + * @peers: Array of peers descripting structures + * @port_idx_map: Map of port number -> peer index + * @part_idx_map: Map of partition number -> peer index + * + * @mtbl_lock: Mapping table access lock + * + * @mw_cnt: Number of memory windows supported by NT-function + * @mws: Array of memory windows descriptors + * @lut_lock: Lookup table access lock + * + * @msg_locks: Message registers mapping table lockers + * + * @cfgspc: Virtual address of the memory mapped configuration + * space of the NT-function + * @db_mask_lock: Doorbell mask register lock + * @msg_mask_lock: Message mask register lock + * @gasa_lock: GASA registers access lock + * + * @dbgfs_info: DebugFS info node + */ +struct idt_ntb_dev { + struct ntb_dev ntb; + struct idt_89hpes_cfg *swcfg; + + unsigned char port; + unsigned char part; + + unsigned char peer_cnt; + struct idt_ntb_peer peers[IDT_MAX_NR_PEERS]; + char port_idx_map[IDT_MAX_NR_PORTS]; + char part_idx_map[IDT_MAX_NR_PARTS]; + + spinlock_t mtbl_lock; + + unsigned char mw_cnt; + struct idt_mw_cfg *mws; + spinlock_t lut_lock; + + spinlock_t msg_locks[IDT_MSG_CNT]; + + void __iomem *cfgspc; + spinlock_t db_mask_lock; + spinlock_t msg_mask_lock; + spinlock_t gasa_lock; + + struct dentry *dbgfs_info; +}; +#define to_ndev_ntb(__ntb) container_of(__ntb, struct idt_ntb_dev, ntb) + +/* + * Descriptor of the IDT PCIe-switch BAR resources + * @setup: BAR setup register + * @limit: BAR limit register + * @ltbase: Lower translated base address + * @utbase: Upper translated base address + */ +struct idt_ntb_bar { + unsigned int setup; + unsigned int limit; + unsigned int ltbase; + unsigned int utbase; +}; + +/* + * Descriptor of the IDT PCIe-switch message resources + * @in: Inbound message register + * @out: Outbound message register + * @src: Source of inbound message register + */ +struct idt_ntb_msg { + unsigned int in; + unsigned int out; + unsigned int src; +}; + +/* + * Descriptor of the IDT PCIe-switch NT-function specific parameters in the + * PCI Configuration Space + * @bars: BARs related registers + * @msgs: Messaging related registers + */ +struct idt_ntb_regs { + struct idt_ntb_bar bars[IDT_BAR_CNT]; + struct idt_ntb_msg msgs[IDT_MSG_CNT]; +}; + +/* + * Descriptor of the IDT PCIe-switch port specific parameters in the + * Global Configuration Space + * @pcicmdsts: PCI command/status register + * @pcielctlsts: PCIe link control/status + * + * @ctl: Port control register + * @sts: Port status register + * + * @bars: BARs related registers + */ +struct idt_ntb_port { + unsigned int pcicmdsts; + unsigned int pcielctlsts; + unsigned int ntctl; + + unsigned int ctl; + unsigned int sts; + + struct idt_ntb_bar bars[IDT_BAR_CNT]; +}; + +/* + * Descriptor of the IDT PCIe-switch partition specific parameters. + * @ctl: Partition control register in the Global Address Space + * @sts: Partition status register in the Global Address Space + * @msgctl: Messages control registers + */ +struct idt_ntb_part { + unsigned int ctl; + unsigned int sts; + unsigned int msgctl[IDT_MSG_CNT]; +}; + +#endif /* NTB_HW_IDT_H */ diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index 7b3b6fd63d7d..2557e2c05b90 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -6,6 +6,7 @@ * * Copyright(c) 2012 Intel Corporation. All rights reserved. * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -15,6 +16,7 @@ * * Copyright(c) 2012 Intel Corporation. All rights reserved. * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -270,12 +272,12 @@ static inline int ndev_db_addr(struct intel_ntb_dev *ndev, if (db_addr) { *db_addr = reg_addr + reg; - dev_dbg(ndev_dev(ndev), "Peer db addr %llx\n", *db_addr); + dev_dbg(&ndev->ntb.pdev->dev, "Peer db addr %llx\n", *db_addr); } if (db_size) { *db_size = ndev->reg->db_size; - dev_dbg(ndev_dev(ndev), "Peer db size %llx\n", *db_size); + dev_dbg(&ndev->ntb.pdev->dev, "Peer db size %llx\n", *db_size); } return 0; @@ -368,7 +370,8 @@ static inline int ndev_spad_addr(struct intel_ntb_dev *ndev, int idx, if (spad_addr) { *spad_addr = reg_addr + reg + (idx << 2); - dev_dbg(ndev_dev(ndev), "Peer spad addr %llx\n", *spad_addr); + dev_dbg(&ndev->ntb.pdev->dev, "Peer spad addr %llx\n", + *spad_addr); } return 0; @@ -409,7 +412,7 @@ static irqreturn_t ndev_interrupt(struct intel_ntb_dev *ndev, int vec) if ((ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD) && (vec == 31)) vec_mask |= ndev->db_link_mask; - dev_dbg(ndev_dev(ndev), "vec %d vec_mask %llx\n", vec, vec_mask); + dev_dbg(&ndev->ntb.pdev->dev, "vec %d vec_mask %llx\n", vec, vec_mask); ndev->last_ts = jiffies; @@ -428,7 +431,7 @@ static irqreturn_t ndev_vec_isr(int irq, void *dev) { struct intel_ntb_vec *nvec = dev; - dev_dbg(ndev_dev(nvec->ndev), "irq: %d nvec->num: %d\n", + dev_dbg(&nvec->ndev->ntb.pdev->dev, "irq: %d nvec->num: %d\n", irq, nvec->num); return ndev_interrupt(nvec->ndev, nvec->num); @@ -438,7 +441,7 @@ static irqreturn_t ndev_irq_isr(int irq, void *dev) { struct intel_ntb_dev *ndev = dev; - return ndev_interrupt(ndev, irq - ndev_pdev(ndev)->irq); + return ndev_interrupt(ndev, irq - ndev->ntb.pdev->irq); } static int ndev_init_isr(struct intel_ntb_dev *ndev, @@ -448,7 +451,7 @@ static int ndev_init_isr(struct intel_ntb_dev *ndev, struct pci_dev *pdev; int rc, i, msix_count, node; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; node = dev_to_node(&pdev->dev); @@ -487,7 +490,7 @@ static int ndev_init_isr(struct intel_ntb_dev *ndev, goto err_msix_request; } - dev_dbg(ndev_dev(ndev), "Using %d msix interrupts\n", msix_count); + dev_dbg(&pdev->dev, "Using %d msix interrupts\n", msix_count); ndev->db_vec_count = msix_count; ndev->db_vec_shift = msix_shift; return 0; @@ -515,7 +518,7 @@ err_msix_vec_alloc: if (rc) goto err_msi_request; - dev_dbg(ndev_dev(ndev), "Using msi interrupts\n"); + dev_dbg(&pdev->dev, "Using msi interrupts\n"); ndev->db_vec_count = 1; ndev->db_vec_shift = total_shift; return 0; @@ -533,7 +536,7 @@ err_msi_enable: if (rc) goto err_intx_request; - dev_dbg(ndev_dev(ndev), "Using intx interrupts\n"); + dev_dbg(&pdev->dev, "Using intx interrupts\n"); ndev->db_vec_count = 1; ndev->db_vec_shift = total_shift; return 0; @@ -547,7 +550,7 @@ static void ndev_deinit_isr(struct intel_ntb_dev *ndev) struct pci_dev *pdev; int i; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; /* Mask all doorbell interrupts */ ndev->db_mask = ndev->db_valid_mask; @@ -744,7 +747,7 @@ static ssize_t ndev_ntb_debugfs_read(struct file *filp, char __user *ubuf, union { u64 v64; u32 v32; u16 v16; u8 v8; } u; ndev = filp->private_data; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; mmio = ndev->self_mmio; buf_size = min(count, 0x800ul); @@ -1019,7 +1022,8 @@ static void ndev_init_debugfs(struct intel_ntb_dev *ndev) ndev->debugfs_info = NULL; } else { ndev->debugfs_dir = - debugfs_create_dir(ndev_name(ndev), debugfs_dir); + debugfs_create_dir(pci_name(ndev->ntb.pdev), + debugfs_dir); if (!ndev->debugfs_dir) ndev->debugfs_info = NULL; else @@ -1035,20 +1039,26 @@ static void ndev_deinit_debugfs(struct intel_ntb_dev *ndev) debugfs_remove_recursive(ndev->debugfs_dir); } -static int intel_ntb_mw_count(struct ntb_dev *ntb) +static int intel_ntb_mw_count(struct ntb_dev *ntb, int pidx) { + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + return ntb_ndev(ntb)->mw_count; } -static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, - resource_size_t *size, - resource_size_t *align, - resource_size_t *align_size) +static int intel_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int idx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); + resource_size_t bar_size, mw_size; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + if (idx >= ndev->b2b_idx && !ndev->b2b_off) idx += 1; @@ -1056,24 +1066,26 @@ static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx, if (bar < 0) return bar; - if (base) - *base = pci_resource_start(ndev->ntb.pdev, bar) + - (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + bar_size = pci_resource_len(ndev->ntb.pdev, bar); - if (size) - *size = pci_resource_len(ndev->ntb.pdev, bar) - - (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + if (idx == ndev->b2b_idx) + mw_size = bar_size - ndev->b2b_off; + else + mw_size = bar_size; + + if (addr_align) + *addr_align = pci_resource_len(ndev->ntb.pdev, bar); - if (align) - *align = pci_resource_len(ndev->ntb.pdev, bar); + if (size_align) + *size_align = 1; - if (align_size) - *align_size = 1; + if (size_max) + *size_max = mw_size; return 0; } -static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, +static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, dma_addr_t addr, resource_size_t size) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); @@ -1083,6 +1095,9 @@ static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, u64 base, limit, reg_val; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + if (idx >= ndev->b2b_idx && !ndev->b2b_off) idx += 1; @@ -1171,7 +1186,7 @@ static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, return 0; } -static int intel_ntb_link_is_up(struct ntb_dev *ntb, +static u64 intel_ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { @@ -1206,13 +1221,13 @@ static int intel_ntb_link_enable(struct ntb_dev *ntb, if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), + dev_dbg(&ntb->pdev->dev, "Enabling link with max_speed %d max_width %d\n", max_speed, max_width); if (max_speed != NTB_SPEED_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_speed %d\n", max_speed); + dev_dbg(&ntb->pdev->dev, "ignoring max_speed %d\n", max_speed); if (max_width != NTB_WIDTH_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_width %d\n", max_width); + dev_dbg(&ntb->pdev->dev, "ignoring max_width %d\n", max_width); ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl); ntb_ctl &= ~(NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK); @@ -1235,7 +1250,7 @@ static int intel_ntb_link_disable(struct ntb_dev *ntb) if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), "Disabling link\n"); + dev_dbg(&ntb->pdev->dev, "Disabling link\n"); /* Bring NTB link down */ ntb_cntl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl); @@ -1249,6 +1264,36 @@ static int intel_ntb_link_disable(struct ntb_dev *ntb) return 0; } +static int intel_ntb_peer_mw_count(struct ntb_dev *ntb) +{ + /* Numbers of inbound and outbound memory windows match */ + return ntb_ndev(ntb)->mw_count; +} + +static int intel_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size) +{ + struct intel_ntb_dev *ndev = ntb_ndev(ntb); + int bar; + + if (idx >= ndev->b2b_idx && !ndev->b2b_off) + idx += 1; + + bar = ndev_mw_to_bar(ndev, idx); + if (bar < 0) + return bar; + + if (base) + *base = pci_resource_start(ndev->ntb.pdev, bar) + + (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + + if (size) + *size = pci_resource_len(ndev->ntb.pdev, bar) - + (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + + return 0; +} + static int intel_ntb_db_is_unsafe(struct ntb_dev *ntb) { return ndev_ignore_unsafe(ntb_ndev(ntb), NTB_UNSAFE_DB); @@ -1366,30 +1411,30 @@ static int intel_ntb_spad_write(struct ntb_dev *ntb, ndev->self_reg->spad); } -static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); - return ndev_spad_addr(ndev, idx, spad_addr, ndev->peer_addr, + return ndev_spad_addr(ndev, sidx, spad_addr, ndev->peer_addr, ndev->peer_reg->spad); } -static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); - return ndev_spad_read(ndev, idx, + return ndev_spad_read(ndev, sidx, ndev->peer_mmio + ndev->peer_reg->spad); } -static int intel_ntb_peer_spad_write(struct ntb_dev *ntb, - int idx, u32 val) +static int intel_ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, + int sidx, u32 val) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); - return ndev_spad_write(ndev, idx, val, + return ndev_spad_write(ndev, sidx, val, ndev->peer_mmio + ndev->peer_reg->spad); } @@ -1442,30 +1487,33 @@ static int atom_link_is_err(struct intel_ntb_dev *ndev) static inline enum ntb_topo atom_ppd_topo(struct intel_ntb_dev *ndev, u32 ppd) { + struct device *dev = &ndev->ntb.pdev->dev; + switch (ppd & ATOM_PPD_TOPO_MASK) { case ATOM_PPD_TOPO_B2B_USD: - dev_dbg(ndev_dev(ndev), "PPD %d B2B USD\n", ppd); + dev_dbg(dev, "PPD %d B2B USD\n", ppd); return NTB_TOPO_B2B_USD; case ATOM_PPD_TOPO_B2B_DSD: - dev_dbg(ndev_dev(ndev), "PPD %d B2B DSD\n", ppd); + dev_dbg(dev, "PPD %d B2B DSD\n", ppd); return NTB_TOPO_B2B_DSD; case ATOM_PPD_TOPO_PRI_USD: case ATOM_PPD_TOPO_PRI_DSD: /* accept bogus PRI_DSD */ case ATOM_PPD_TOPO_SEC_USD: case ATOM_PPD_TOPO_SEC_DSD: /* accept bogus SEC_DSD */ - dev_dbg(ndev_dev(ndev), "PPD %d non B2B disabled\n", ppd); + dev_dbg(dev, "PPD %d non B2B disabled\n", ppd); return NTB_TOPO_NONE; } - dev_dbg(ndev_dev(ndev), "PPD %d invalid\n", ppd); + dev_dbg(dev, "PPD %d invalid\n", ppd); return NTB_TOPO_NONE; } static void atom_link_hb(struct work_struct *work) { struct intel_ntb_dev *ndev = hb_ndev(work); + struct device *dev = &ndev->ntb.pdev->dev; unsigned long poll_ts; void __iomem *mmio; u32 status32; @@ -1503,30 +1551,30 @@ static void atom_link_hb(struct work_struct *work) /* Clear AER Errors, write to clear */ status32 = ioread32(mmio + ATOM_ERRCORSTS_OFFSET); - dev_dbg(ndev_dev(ndev), "ERRCORSTS = %x\n", status32); + dev_dbg(dev, "ERRCORSTS = %x\n", status32); status32 &= PCI_ERR_COR_REP_ROLL; iowrite32(status32, mmio + ATOM_ERRCORSTS_OFFSET); /* Clear unexpected electrical idle event in LTSSM, write to clear */ status32 = ioread32(mmio + ATOM_LTSSMERRSTS0_OFFSET); - dev_dbg(ndev_dev(ndev), "LTSSMERRSTS0 = %x\n", status32); + dev_dbg(dev, "LTSSMERRSTS0 = %x\n", status32); status32 |= ATOM_LTSSMERRSTS0_UNEXPECTEDEI; iowrite32(status32, mmio + ATOM_LTSSMERRSTS0_OFFSET); /* Clear DeSkew Buffer error, write to clear */ status32 = ioread32(mmio + ATOM_DESKEWSTS_OFFSET); - dev_dbg(ndev_dev(ndev), "DESKEWSTS = %x\n", status32); + dev_dbg(dev, "DESKEWSTS = %x\n", status32); status32 |= ATOM_DESKEWSTS_DBERR; iowrite32(status32, mmio + ATOM_DESKEWSTS_OFFSET); status32 = ioread32(mmio + ATOM_IBSTERRRCRVSTS0_OFFSET); - dev_dbg(ndev_dev(ndev), "IBSTERRRCRVSTS0 = %x\n", status32); + dev_dbg(dev, "IBSTERRRCRVSTS0 = %x\n", status32); status32 &= ATOM_IBIST_ERR_OFLOW; iowrite32(status32, mmio + ATOM_IBSTERRRCRVSTS0_OFFSET); /* Releases the NTB state machine to allow the link to retrain */ status32 = ioread32(mmio + ATOM_LTSSMSTATEJMP_OFFSET); - dev_dbg(ndev_dev(ndev), "LTSSMSTATEJMP = %x\n", status32); + dev_dbg(dev, "LTSSMSTATEJMP = %x\n", status32); status32 &= ~ATOM_LTSSMSTATEJMP_FORCEDETECT; iowrite32(status32, mmio + ATOM_LTSSMSTATEJMP_OFFSET); @@ -1699,11 +1747,11 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, int b2b_bar; u8 bar_sz; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; mmio = ndev->self_mmio; if (ndev->b2b_idx == UINT_MAX) { - dev_dbg(ndev_dev(ndev), "not using b2b mw\n"); + dev_dbg(&pdev->dev, "not using b2b mw\n"); b2b_bar = 0; ndev->b2b_off = 0; } else { @@ -1711,24 +1759,21 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, if (b2b_bar < 0) return -EIO; - dev_dbg(ndev_dev(ndev), "using b2b mw bar %d\n", b2b_bar); + dev_dbg(&pdev->dev, "using b2b mw bar %d\n", b2b_bar); bar_size = pci_resource_len(ndev->ntb.pdev, b2b_bar); - dev_dbg(ndev_dev(ndev), "b2b bar size %#llx\n", bar_size); + dev_dbg(&pdev->dev, "b2b bar size %#llx\n", bar_size); if (b2b_mw_share && ((bar_size >> 1) >= XEON_B2B_MIN_SIZE)) { - dev_dbg(ndev_dev(ndev), - "b2b using first half of bar\n"); + dev_dbg(&pdev->dev, "b2b using first half of bar\n"); ndev->b2b_off = bar_size >> 1; } else if (bar_size >= XEON_B2B_MIN_SIZE) { - dev_dbg(ndev_dev(ndev), - "b2b using whole bar\n"); + dev_dbg(&pdev->dev, "b2b using whole bar\n"); ndev->b2b_off = 0; --ndev->mw_count; } else { - dev_dbg(ndev_dev(ndev), - "b2b bar size is too small\n"); + dev_dbg(&pdev->dev, "b2b bar size is too small\n"); return -EIO; } } @@ -1738,7 +1783,7 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, * except disable or halve the size of the b2b secondary bar. */ pci_read_config_byte(pdev, SKX_IMBAR1SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "IMBAR1SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "IMBAR1SZ %#x\n", bar_sz); if (b2b_bar == 1) { if (ndev->b2b_off) bar_sz -= 1; @@ -1748,10 +1793,10 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, pci_write_config_byte(pdev, SKX_EMBAR1SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, SKX_EMBAR1SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "EMBAR1SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "EMBAR1SZ %#x\n", bar_sz); pci_read_config_byte(pdev, SKX_IMBAR2SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "IMBAR2SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "IMBAR2SZ %#x\n", bar_sz); if (b2b_bar == 2) { if (ndev->b2b_off) bar_sz -= 1; @@ -1761,7 +1806,7 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, pci_write_config_byte(pdev, SKX_EMBAR2SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, SKX_EMBAR2SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "EMBAR2SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "EMBAR2SZ %#x\n", bar_sz); /* SBAR01 hit by first part of the b2b bar */ if (b2b_bar == 0) @@ -1777,12 +1822,12 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = addr->bar2_addr64 + (b2b_bar == 1 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + SKX_IMBAR1XLMT_OFFSET); bar_addr = ioread64(mmio + SKX_IMBAR1XLMT_OFFSET); - dev_dbg(ndev_dev(ndev), "IMBAR1XLMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "IMBAR1XLMT %#018llx\n", bar_addr); bar_addr = addr->bar4_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + SKX_IMBAR2XLMT_OFFSET); bar_addr = ioread64(mmio + SKX_IMBAR2XLMT_OFFSET); - dev_dbg(ndev_dev(ndev), "IMBAR2XLMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "IMBAR2XLMT %#018llx\n", bar_addr); /* zero incoming translation addrs */ iowrite64(0, mmio + SKX_IMBAR1XBASE_OFFSET); @@ -1852,7 +1897,7 @@ static int skx_init_dev(struct intel_ntb_dev *ndev) u8 ppd; int rc; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; ndev->reg = &skx_reg; @@ -1861,7 +1906,7 @@ static int skx_init_dev(struct intel_ntb_dev *ndev) return -EIO; ndev->ntb.topo = xeon_ppd_topo(ndev, ppd); - dev_dbg(ndev_dev(ndev), "ppd %#x topo %s\n", ppd, + dev_dbg(&pdev->dev, "ppd %#x topo %s\n", ppd, ntb_topo_string(ndev->ntb.topo)); if (ndev->ntb.topo == NTB_TOPO_NONE) return -EINVAL; @@ -1885,14 +1930,14 @@ static int intel_ntb3_link_enable(struct ntb_dev *ntb, ndev = container_of(ntb, struct intel_ntb_dev, ntb); - dev_dbg(ndev_dev(ndev), + dev_dbg(&ntb->pdev->dev, "Enabling link with max_speed %d max_width %d\n", max_speed, max_width); if (max_speed != NTB_SPEED_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_speed %d\n", max_speed); + dev_dbg(&ntb->pdev->dev, "ignoring max_speed %d\n", max_speed); if (max_width != NTB_WIDTH_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_width %d\n", max_width); + dev_dbg(&ntb->pdev->dev, "ignoring max_width %d\n", max_width); ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl); ntb_ctl &= ~(NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK); @@ -1902,7 +1947,7 @@ static int intel_ntb3_link_enable(struct ntb_dev *ntb, return 0; } -static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, +static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, dma_addr_t addr, resource_size_t size) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); @@ -1912,6 +1957,9 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, u64 base, limit, reg_val; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + if (idx >= ndev->b2b_idx && !ndev->b2b_off) idx += 1; @@ -1953,7 +2001,7 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, return -EIO; } - dev_dbg(ndev_dev(ndev), "BAR %d IMBARXBASE: %#Lx\n", bar, reg_val); + dev_dbg(&ntb->pdev->dev, "BAR %d IMBARXBASE: %#Lx\n", bar, reg_val); /* set and verify setting the limit */ iowrite64(limit, mmio + limit_reg); @@ -1964,7 +2012,7 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, return -EIO; } - dev_dbg(ndev_dev(ndev), "BAR %d IMBARXLMT: %#Lx\n", bar, reg_val); + dev_dbg(&ntb->pdev->dev, "BAR %d IMBARXLMT: %#Lx\n", bar, reg_val); /* setup the EP */ limit_reg = ndev->xlat_reg->bar2_limit + (idx * 0x10) + 0x4000; @@ -1985,7 +2033,7 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, return -EIO; } - dev_dbg(ndev_dev(ndev), "BAR %d EMBARXLMT: %#Lx\n", bar, reg_val); + dev_dbg(&ntb->pdev->dev, "BAR %d EMBARXLMT: %#Lx\n", bar, reg_val); return 0; } @@ -2092,7 +2140,7 @@ static inline enum ntb_topo xeon_ppd_topo(struct intel_ntb_dev *ndev, u8 ppd) static inline int xeon_ppd_bar4_split(struct intel_ntb_dev *ndev, u8 ppd) { if (ppd & XEON_PPD_SPLIT_BAR_MASK) { - dev_dbg(ndev_dev(ndev), "PPD %d split bar\n", ppd); + dev_dbg(&ndev->ntb.pdev->dev, "PPD %d split bar\n", ppd); return 1; } return 0; @@ -2122,11 +2170,11 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, int b2b_bar; u8 bar_sz; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; mmio = ndev->self_mmio; if (ndev->b2b_idx == UINT_MAX) { - dev_dbg(ndev_dev(ndev), "not using b2b mw\n"); + dev_dbg(&pdev->dev, "not using b2b mw\n"); b2b_bar = 0; ndev->b2b_off = 0; } else { @@ -2134,24 +2182,21 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, if (b2b_bar < 0) return -EIO; - dev_dbg(ndev_dev(ndev), "using b2b mw bar %d\n", b2b_bar); + dev_dbg(&pdev->dev, "using b2b mw bar %d\n", b2b_bar); bar_size = pci_resource_len(ndev->ntb.pdev, b2b_bar); - dev_dbg(ndev_dev(ndev), "b2b bar size %#llx\n", bar_size); + dev_dbg(&pdev->dev, "b2b bar size %#llx\n", bar_size); if (b2b_mw_share && XEON_B2B_MIN_SIZE <= bar_size >> 1) { - dev_dbg(ndev_dev(ndev), - "b2b using first half of bar\n"); + dev_dbg(&pdev->dev, "b2b using first half of bar\n"); ndev->b2b_off = bar_size >> 1; } else if (XEON_B2B_MIN_SIZE <= bar_size) { - dev_dbg(ndev_dev(ndev), - "b2b using whole bar\n"); + dev_dbg(&pdev->dev, "b2b using whole bar\n"); ndev->b2b_off = 0; --ndev->mw_count; } else { - dev_dbg(ndev_dev(ndev), - "b2b bar size is too small\n"); + dev_dbg(&pdev->dev, "b2b bar size is too small\n"); return -EIO; } } @@ -2163,7 +2208,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, * offsets are not in a consistent order (bar5sz comes after ppd, odd). */ pci_read_config_byte(pdev, XEON_PBAR23SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR23SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR23SZ %#x\n", bar_sz); if (b2b_bar == 2) { if (ndev->b2b_off) bar_sz -= 1; @@ -2172,11 +2217,11 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR23SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR23SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR23SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR23SZ %#x\n", bar_sz); if (!ndev->bar4_split) { pci_read_config_byte(pdev, XEON_PBAR45SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR45SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR45SZ %#x\n", bar_sz); if (b2b_bar == 4) { if (ndev->b2b_off) bar_sz -= 1; @@ -2185,10 +2230,10 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR45SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR45SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR45SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR45SZ %#x\n", bar_sz); } else { pci_read_config_byte(pdev, XEON_PBAR4SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR4SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR4SZ %#x\n", bar_sz); if (b2b_bar == 4) { if (ndev->b2b_off) bar_sz -= 1; @@ -2197,10 +2242,10 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR4SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR4SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR4SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR4SZ %#x\n", bar_sz); pci_read_config_byte(pdev, XEON_PBAR5SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR5SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR5SZ %#x\n", bar_sz); if (b2b_bar == 5) { if (ndev->b2b_off) bar_sz -= 1; @@ -2209,7 +2254,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR5SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR5SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR5SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR5SZ %#x\n", bar_sz); } /* SBAR01 hit by first part of the b2b bar */ @@ -2226,7 +2271,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, else return -EIO; - dev_dbg(ndev_dev(ndev), "SBAR01 %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR01 %#018llx\n", bar_addr); iowrite64(bar_addr, mmio + XEON_SBAR0BASE_OFFSET); /* Other SBAR are normally hit by the PBAR xlat, except for b2b bar. @@ -2237,26 +2282,26 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = addr->bar2_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR23BASE_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR23BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR23 %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR23 %#018llx\n", bar_addr); if (!ndev->bar4_split) { bar_addr = addr->bar4_addr64 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR45BASE_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR45BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR45 %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR45 %#018llx\n", bar_addr); } else { bar_addr = addr->bar4_addr32 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR4BASE_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR4BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR4 %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR4 %#010llx\n", bar_addr); bar_addr = addr->bar5_addr32 + (b2b_bar == 5 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR5BASE_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR5BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR5 %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR5 %#010llx\n", bar_addr); } /* setup incoming bar limits == base addrs (zero length windows) */ @@ -2264,26 +2309,26 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = addr->bar2_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR23LMT_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR23LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR23LMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR23LMT %#018llx\n", bar_addr); if (!ndev->bar4_split) { bar_addr = addr->bar4_addr64 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR45LMT_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR45LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR45LMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR45LMT %#018llx\n", bar_addr); } else { bar_addr = addr->bar4_addr32 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR4LMT_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR4LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR4LMT %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR4LMT %#010llx\n", bar_addr); bar_addr = addr->bar5_addr32 + (b2b_bar == 5 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR5LMT_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR5LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR5LMT %#05llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR5LMT %#05llx\n", bar_addr); } /* zero incoming translation addrs */ @@ -2309,23 +2354,23 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = peer_addr->bar2_addr64; iowrite64(bar_addr, mmio + XEON_PBAR23XLAT_OFFSET); bar_addr = ioread64(mmio + XEON_PBAR23XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR23XLAT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR23XLAT %#018llx\n", bar_addr); if (!ndev->bar4_split) { bar_addr = peer_addr->bar4_addr64; iowrite64(bar_addr, mmio + XEON_PBAR45XLAT_OFFSET); bar_addr = ioread64(mmio + XEON_PBAR45XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR45XLAT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR45XLAT %#018llx\n", bar_addr); } else { bar_addr = peer_addr->bar4_addr32; iowrite32(bar_addr, mmio + XEON_PBAR4XLAT_OFFSET); bar_addr = ioread32(mmio + XEON_PBAR4XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR4XLAT %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR4XLAT %#010llx\n", bar_addr); bar_addr = peer_addr->bar5_addr32; iowrite32(bar_addr, mmio + XEON_PBAR5XLAT_OFFSET); bar_addr = ioread32(mmio + XEON_PBAR5XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR5XLAT %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR5XLAT %#010llx\n", bar_addr); } /* set the translation offset for b2b registers */ @@ -2343,7 +2388,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, return -EIO; /* B2B_XLAT_OFFSET is 64bit, but can only take 32bit writes */ - dev_dbg(ndev_dev(ndev), "B2BXLAT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "B2BXLAT %#018llx\n", bar_addr); iowrite32(bar_addr, mmio + XEON_B2B_XLAT_OFFSETL); iowrite32(bar_addr >> 32, mmio + XEON_B2B_XLAT_OFFSETU); @@ -2362,6 +2407,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, static int xeon_init_ntb(struct intel_ntb_dev *ndev) { + struct device *dev = &ndev->ntb.pdev->dev; int rc; u32 ntb_ctl; @@ -2377,7 +2423,7 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev) switch (ndev->ntb.topo) { case NTB_TOPO_PRI: if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) { - dev_err(ndev_dev(ndev), "NTB Primary config disabled\n"); + dev_err(dev, "NTB Primary config disabled\n"); return -EINVAL; } @@ -2395,7 +2441,7 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev) case NTB_TOPO_SEC: if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) { - dev_err(ndev_dev(ndev), "NTB Secondary config disabled\n"); + dev_err(dev, "NTB Secondary config disabled\n"); return -EINVAL; } /* use half the spads for the peer */ @@ -2420,18 +2466,17 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev) ndev->b2b_idx = b2b_mw_idx; if (ndev->b2b_idx >= ndev->mw_count) { - dev_dbg(ndev_dev(ndev), + dev_dbg(dev, "b2b_mw_idx %d invalid for mw_count %u\n", b2b_mw_idx, ndev->mw_count); return -EINVAL; } - dev_dbg(ndev_dev(ndev), - "setting up b2b mw idx %d means %d\n", + dev_dbg(dev, "setting up b2b mw idx %d means %d\n", b2b_mw_idx, ndev->b2b_idx); } else if (ndev->hwerr_flags & NTB_HWERR_B2BDOORBELL_BIT14) { - dev_warn(ndev_dev(ndev), "Reduce doorbell count by 1\n"); + dev_warn(dev, "Reduce doorbell count by 1\n"); ndev->db_count -= 1; } @@ -2472,7 +2517,7 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev) u8 ppd; int rc, mem; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; switch (pdev->device) { /* There is a Xeon hardware errata related to writes to SDOORBELL or @@ -2548,14 +2593,14 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev) return -EIO; ndev->ntb.topo = xeon_ppd_topo(ndev, ppd); - dev_dbg(ndev_dev(ndev), "ppd %#x topo %s\n", ppd, + dev_dbg(&pdev->dev, "ppd %#x topo %s\n", ppd, ntb_topo_string(ndev->ntb.topo)); if (ndev->ntb.topo == NTB_TOPO_NONE) return -EINVAL; if (ndev->ntb.topo != NTB_TOPO_SEC) { ndev->bar4_split = xeon_ppd_bar4_split(ndev, ppd); - dev_dbg(ndev_dev(ndev), "ppd %#x bar4_split %d\n", + dev_dbg(&pdev->dev, "ppd %#x bar4_split %d\n", ppd, ndev->bar4_split); } else { /* This is a way for transparent BAR to figure out if we are @@ -2565,7 +2610,7 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev) mem = pci_select_bars(pdev, IORESOURCE_MEM); ndev->bar4_split = hweight32(mem) == HSX_SPLIT_BAR_MW_COUNT + 1; - dev_dbg(ndev_dev(ndev), "mem %#x bar4_split %d\n", + dev_dbg(&pdev->dev, "mem %#x bar4_split %d\n", mem, ndev->bar4_split); } @@ -2602,7 +2647,7 @@ static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev) rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA highmem\n"); } rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); @@ -2610,7 +2655,7 @@ static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev) rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA consistent highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA consistent highmem\n"); } ndev->self_mmio = pci_iomap(pdev, 0, 0); @@ -2636,7 +2681,7 @@ err_pci_enable: static void intel_ntb_deinit_pci(struct intel_ntb_dev *ndev) { - struct pci_dev *pdev = ndev_pdev(ndev); + struct pci_dev *pdev = ndev->ntb.pdev; if (ndev->peer_mmio && ndev->peer_mmio != ndev->self_mmio) pci_iounmap(pdev, ndev->peer_mmio); @@ -2906,8 +2951,10 @@ static const struct intel_ntb_xlat_reg skx_sec_xlat = { /* operations for primary side of local ntb */ static const struct ntb_dev_ops intel_ntb_ops = { .mw_count = intel_ntb_mw_count, - .mw_get_range = intel_ntb_mw_get_range, + .mw_get_align = intel_ntb_mw_get_align, .mw_set_trans = intel_ntb_mw_set_trans, + .peer_mw_count = intel_ntb_peer_mw_count, + .peer_mw_get_addr = intel_ntb_peer_mw_get_addr, .link_is_up = intel_ntb_link_is_up, .link_enable = intel_ntb_link_enable, .link_disable = intel_ntb_link_disable, @@ -2932,8 +2979,10 @@ static const struct ntb_dev_ops intel_ntb_ops = { static const struct ntb_dev_ops intel_ntb3_ops = { .mw_count = intel_ntb_mw_count, - .mw_get_range = intel_ntb_mw_get_range, + .mw_get_align = intel_ntb_mw_get_align, .mw_set_trans = intel_ntb3_mw_set_trans, + .peer_mw_count = intel_ntb_peer_mw_count, + .peer_mw_get_addr = intel_ntb_peer_mw_get_addr, .link_is_up = intel_ntb_link_is_up, .link_enable = intel_ntb3_link_enable, .link_disable = intel_ntb_link_disable, @@ -3008,4 +3057,3 @@ static void __exit intel_ntb_pci_driver_exit(void) debugfs_remove_recursive(debugfs_dir); } module_exit(intel_ntb_pci_driver_exit); - diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.h b/drivers/ntb/hw/intel/ntb_hw_intel.h index f2cf8a783f1e..2d6c38afb128 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.h +++ b/drivers/ntb/hw/intel/ntb_hw_intel.h @@ -382,9 +382,6 @@ struct intel_ntb_dev { struct dentry *debugfs_info; }; -#define ndev_pdev(ndev) ((ndev)->ntb.pdev) -#define ndev_name(ndev) pci_name(ndev_pdev(ndev)) -#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev) #define ntb_ndev(__ntb) container_of(__ntb, struct intel_ntb_dev, ntb) #define hb_ndev(__work) container_of(__work, struct intel_ntb_dev, \ hb_timer.work) diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c index 2e2530743831..03b80d89b980 100644 --- a/drivers/ntb/ntb.c +++ b/drivers/ntb/ntb.c @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -191,6 +193,73 @@ void ntb_db_event(struct ntb_dev *ntb, int vector) } EXPORT_SYMBOL(ntb_db_event); +void ntb_msg_event(struct ntb_dev *ntb) +{ + unsigned long irqflags; + + spin_lock_irqsave(&ntb->ctx_lock, irqflags); + { + if (ntb->ctx_ops && ntb->ctx_ops->msg_event) + ntb->ctx_ops->msg_event(ntb->ctx); + } + spin_unlock_irqrestore(&ntb->ctx_lock, irqflags); +} +EXPORT_SYMBOL(ntb_msg_event); + +int ntb_default_port_number(struct ntb_dev *ntb) +{ + switch (ntb->topo) { + case NTB_TOPO_PRI: + case NTB_TOPO_B2B_USD: + return NTB_PORT_PRI_USD; + case NTB_TOPO_SEC: + case NTB_TOPO_B2B_DSD: + return NTB_PORT_SEC_DSD; + default: + break; + } + + return -EINVAL; +} +EXPORT_SYMBOL(ntb_default_port_number); + +int ntb_default_peer_port_count(struct ntb_dev *ntb) +{ + return NTB_DEF_PEER_CNT; +} +EXPORT_SYMBOL(ntb_default_peer_port_count); + +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx) +{ + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + + switch (ntb->topo) { + case NTB_TOPO_PRI: + case NTB_TOPO_B2B_USD: + return NTB_PORT_SEC_DSD; + case NTB_TOPO_SEC: + case NTB_TOPO_B2B_DSD: + return NTB_PORT_PRI_USD; + default: + break; + } + + return -EINVAL; +} +EXPORT_SYMBOL(ntb_default_peer_port_number); + +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port) +{ + int peer_port = ntb_default_peer_port_number(ntb, NTB_DEF_PEER_IDX); + + if (peer_port == -EINVAL || port != peer_port) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(ntb_default_peer_port_idx); + static int ntb_probe(struct device *dev) { struct ntb_dev *ntb; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 10e5bf460139..9a03c5871efe 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -95,6 +95,9 @@ MODULE_PARM_DESC(use_dma, "Use DMA engine to perform large data copy"); static struct dentry *nt_debugfs_dir; +/* Only two-ports NTB devices are supported */ +#define PIDX NTB_DEF_PEER_IDX + struct ntb_queue_entry { /* ntb_queue list reference */ struct list_head entry; @@ -670,7 +673,7 @@ static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw) if (!mw->virt_addr) return; - ntb_mw_clear_trans(nt->ndev, num_mw); + ntb_mw_clear_trans(nt->ndev, PIDX, num_mw); dma_free_coherent(&pdev->dev, mw->buff_size, mw->virt_addr, mw->dma_addr); mw->xlat_size = 0; @@ -727,7 +730,8 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, } /* Notify HW the memory location of the receive buffer */ - rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size); + rc = ntb_mw_set_trans(nt->ndev, PIDX, num_mw, mw->dma_addr, + mw->xlat_size); if (rc) { dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw); ntb_free_mw(nt, num_mw); @@ -858,17 +862,17 @@ static void ntb_transport_link_work(struct work_struct *work) size = max_mw_size; spad = MW0_SZ_HIGH + (i * 2); - ntb_peer_spad_write(ndev, spad, upper_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, spad, upper_32_bits(size)); spad = MW0_SZ_LOW + (i * 2); - ntb_peer_spad_write(ndev, spad, lower_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, spad, lower_32_bits(size)); } - ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count); + ntb_peer_spad_write(ndev, PIDX, NUM_MWS, nt->mw_count); - ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count); + ntb_peer_spad_write(ndev, PIDX, NUM_QPS, nt->qp_count); - ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION); + ntb_peer_spad_write(ndev, PIDX, VERSION, NTB_TRANSPORT_VERSION); /* Query the remote side for its info */ val = ntb_spad_read(ndev, VERSION); @@ -944,7 +948,7 @@ static void ntb_qp_link_work(struct work_struct *work) val = ntb_spad_read(nt->ndev, QP_LINKS); - ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num)); + ntb_peer_spad_write(nt->ndev, PIDX, QP_LINKS, val | BIT(qp->qp_num)); /* query remote spad for qp ready bits */ dev_dbg_ratelimited(&pdev->dev, "Remote QP link status = %x\n", val); @@ -1055,7 +1059,12 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) int node; int rc, i; - mw_count = ntb_mw_count(ndev); + mw_count = ntb_mw_count(ndev, PIDX); + + if (!ndev->ops->mw_set_trans) { + dev_err(&ndev->dev, "Inbound MW based NTB API is required\n"); + return -EINVAL; + } if (ntb_db_is_unsafe(ndev)) dev_dbg(&ndev->dev, @@ -1064,6 +1073,9 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) dev_dbg(&ndev->dev, "scratchpad is unsafe, proceed anyway...\n"); + if (ntb_peer_port_count(ndev) != NTB_DEF_PEER_CNT) + dev_warn(&ndev->dev, "Multi-port NTB devices unsupported\n"); + node = dev_to_node(&ndev->dev); nt = kzalloc_node(sizeof(*nt), GFP_KERNEL, node); @@ -1094,8 +1106,13 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) for (i = 0; i < mw_count; i++) { mw = &nt->mw_vec[i]; - rc = ntb_mw_get_range(ndev, i, &mw->phys_addr, &mw->phys_size, - &mw->xlat_align, &mw->xlat_align_size); + rc = ntb_mw_get_align(ndev, PIDX, i, &mw->xlat_align, + &mw->xlat_align_size, NULL); + if (rc) + goto err1; + + rc = ntb_peer_mw_get_addr(ndev, i, &mw->phys_addr, + &mw->phys_size); if (rc) goto err1; @@ -2091,8 +2108,7 @@ void ntb_transport_link_down(struct ntb_transport_qp *qp) val = ntb_spad_read(qp->ndev, QP_LINKS); - ntb_peer_spad_write(qp->ndev, QP_LINKS, - val & ~BIT(qp->qp_num)); + ntb_peer_spad_write(qp->ndev, PIDX, QP_LINKS, val & ~BIT(qp->qp_num)); if (qp->link_is_up) ntb_send_link_down(qp); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 5cab2831ce99..759f772fa00c 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -76,6 +76,7 @@ #define DMA_RETRIES 20 #define SZ_4G (1ULL << 32) #define MAX_SEG_ORDER 20 /* no larger than 1M for kmalloc buffer */ +#define PIDX NTB_DEF_PEER_IDX MODULE_LICENSE(DRIVER_LICENSE); MODULE_VERSION(DRIVER_VERSION); @@ -100,6 +101,10 @@ static bool use_dma; /* default to 0 */ module_param(use_dma, bool, 0644); MODULE_PARM_DESC(use_dma, "Using DMA engine to measure performance"); +static bool on_node = true; /* default to 1 */ +module_param(on_node, bool, 0644); +MODULE_PARM_DESC(on_node, "Run threads only on NTB device node (default: true)"); + struct perf_mw { phys_addr_t phys_addr; resource_size_t phys_size; @@ -135,9 +140,6 @@ struct perf_ctx { bool link_is_up; struct delayed_work link_work; wait_queue_head_t link_wq; - struct dentry *debugfs_node_dir; - struct dentry *debugfs_run; - struct dentry *debugfs_threads; u8 perf_threads; /* mutex ensures only one set of threads run at once */ struct mutex run_mutex; @@ -344,6 +346,10 @@ static int perf_move_data(struct pthr_ctx *pctx, char __iomem *dst, char *src, static bool perf_dma_filter_fn(struct dma_chan *chan, void *node) { + /* Is the channel required to be on the same node as the device? */ + if (!on_node) + return true; + return dev_to_node(&chan->dev->device) == (int)(unsigned long)node; } @@ -361,7 +367,7 @@ static int ntb_perf_thread(void *data) pr_debug("kthread %s starting...\n", current->comm); - node = dev_to_node(&pdev->dev); + node = on_node ? dev_to_node(&pdev->dev) : NUMA_NO_NODE; if (use_dma && !pctx->dma_chan) { dma_cap_mask_t dma_mask; @@ -454,7 +460,7 @@ static void perf_free_mw(struct perf_ctx *perf) if (!mw->virt_addr) return; - ntb_mw_clear_trans(perf->ntb, 0); + ntb_mw_clear_trans(perf->ntb, PIDX, 0); dma_free_coherent(&pdev->dev, mw->buf_size, mw->virt_addr, mw->dma_addr); mw->xlat_size = 0; @@ -490,7 +496,7 @@ static int perf_set_mw(struct perf_ctx *perf, resource_size_t size) mw->buf_size = 0; } - rc = ntb_mw_set_trans(perf->ntb, 0, mw->dma_addr, mw->xlat_size); + rc = ntb_mw_set_trans(perf->ntb, PIDX, 0, mw->dma_addr, mw->xlat_size); if (rc) { dev_err(&perf->ntb->dev, "Unable to set mw0 translation\n"); perf_free_mw(perf); @@ -517,9 +523,9 @@ static void perf_link_work(struct work_struct *work) if (max_mw_size && size > max_mw_size) size = max_mw_size; - ntb_peer_spad_write(ndev, MW_SZ_HIGH, upper_32_bits(size)); - ntb_peer_spad_write(ndev, MW_SZ_LOW, lower_32_bits(size)); - ntb_peer_spad_write(ndev, VERSION, PERF_VERSION); + ntb_peer_spad_write(ndev, PIDX, MW_SZ_HIGH, upper_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, MW_SZ_LOW, lower_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, VERSION, PERF_VERSION); /* now read what peer wrote */ val = ntb_spad_read(ndev, VERSION); @@ -561,8 +567,12 @@ static int perf_setup_mw(struct ntb_dev *ntb, struct perf_ctx *perf) mw = &perf->mw; - rc = ntb_mw_get_range(ntb, 0, &mw->phys_addr, &mw->phys_size, - &mw->xlat_align, &mw->xlat_align_size); + rc = ntb_mw_get_align(ntb, PIDX, 0, &mw->xlat_align, + &mw->xlat_align_size, NULL); + if (rc) + return rc; + + rc = ntb_peer_mw_get_addr(ntb, 0, &mw->phys_addr, &mw->phys_size); if (rc) return rc; @@ -677,7 +687,8 @@ static ssize_t debugfs_run_write(struct file *filp, const char __user *ubuf, pr_info("Fix run_order to %u\n", run_order); } - node = dev_to_node(&perf->ntb->pdev->dev); + node = on_node ? dev_to_node(&perf->ntb->pdev->dev) + : NUMA_NO_NODE; atomic_set(&perf->tdone, 0); /* launch kernel thread */ @@ -723,34 +734,71 @@ static const struct file_operations ntb_perf_debugfs_run = { static int perf_debugfs_setup(struct perf_ctx *perf) { struct pci_dev *pdev = perf->ntb->pdev; + struct dentry *debugfs_node_dir; + struct dentry *debugfs_run; + struct dentry *debugfs_threads; + struct dentry *debugfs_seg_order; + struct dentry *debugfs_run_order; + struct dentry *debugfs_use_dma; + struct dentry *debugfs_on_node; if (!debugfs_initialized()) return -ENODEV; + /* Assumpion: only one NTB device in the system */ if (!perf_debugfs_dir) { perf_debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); if (!perf_debugfs_dir) return -ENODEV; } - perf->debugfs_node_dir = debugfs_create_dir(pci_name(pdev), - perf_debugfs_dir); - if (!perf->debugfs_node_dir) - return -ENODEV; + debugfs_node_dir = debugfs_create_dir(pci_name(pdev), + perf_debugfs_dir); + if (!debugfs_node_dir) + goto err; - perf->debugfs_run = debugfs_create_file("run", S_IRUSR | S_IWUSR, - perf->debugfs_node_dir, perf, - &ntb_perf_debugfs_run); - if (!perf->debugfs_run) - return -ENODEV; + debugfs_run = debugfs_create_file("run", S_IRUSR | S_IWUSR, + debugfs_node_dir, perf, + &ntb_perf_debugfs_run); + if (!debugfs_run) + goto err; - perf->debugfs_threads = debugfs_create_u8("threads", S_IRUSR | S_IWUSR, - perf->debugfs_node_dir, - &perf->perf_threads); - if (!perf->debugfs_threads) - return -ENODEV; + debugfs_threads = debugfs_create_u8("threads", S_IRUSR | S_IWUSR, + debugfs_node_dir, + &perf->perf_threads); + if (!debugfs_threads) + goto err; + + debugfs_seg_order = debugfs_create_u32("seg_order", 0600, + debugfs_node_dir, + &seg_order); + if (!debugfs_seg_order) + goto err; + + debugfs_run_order = debugfs_create_u32("run_order", 0600, + debugfs_node_dir, + &run_order); + if (!debugfs_run_order) + goto err; + + debugfs_use_dma = debugfs_create_bool("use_dma", 0600, + debugfs_node_dir, + &use_dma); + if (!debugfs_use_dma) + goto err; + + debugfs_on_node = debugfs_create_bool("on_node", 0600, + debugfs_node_dir, + &on_node); + if (!debugfs_on_node) + goto err; return 0; + +err: + debugfs_remove_recursive(perf_debugfs_dir); + perf_debugfs_dir = NULL; + return -ENODEV; } static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb) @@ -766,8 +814,15 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb) return -EIO; } - node = dev_to_node(&pdev->dev); + if (!ntb->ops->mw_set_trans) { + dev_err(&ntb->dev, "Need inbound MW based NTB API\n"); + return -EINVAL; + } + + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) + dev_warn(&ntb->dev, "Multi-port NTB devices unsupported\n"); + node = on_node ? dev_to_node(&pdev->dev) : NUMA_NO_NODE; perf = kzalloc_node(sizeof(*perf), GFP_KERNEL, node); if (!perf) { rc = -ENOMEM; diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c index 435861189d97..938a18bcfc3f 100644 --- a/drivers/ntb/test/ntb_pingpong.c +++ b/drivers/ntb/test/ntb_pingpong.c @@ -90,6 +90,9 @@ static unsigned long db_init = 0x7; module_param(db_init, ulong, 0644); MODULE_PARM_DESC(db_init, "Initial doorbell bits to ring on the peer"); +/* Only two-ports NTB devices are supported */ +#define PIDX NTB_DEF_PEER_IDX + struct pp_ctx { struct ntb_dev *ntb; u64 db_bits; @@ -135,7 +138,7 @@ static void pp_ping(unsigned long ctx) "Ping bits %#llx read %#x write %#x\n", db_bits, spad_rd, spad_wr); - ntb_peer_spad_write(pp->ntb, 0, spad_wr); + ntb_peer_spad_write(pp->ntb, PIDX, 0, spad_wr); ntb_peer_db_set(pp->ntb, db_bits); ntb_db_clear_mask(pp->ntb, db_mask); @@ -222,6 +225,12 @@ static int pp_probe(struct ntb_client *client, } } + if (ntb_spad_count(ntb) < 1) { + dev_dbg(&ntb->dev, "no enough scratchpads\n"); + rc = -EINVAL; + goto err_pp; + } + if (ntb_spad_is_unsafe(ntb)) { dev_dbg(&ntb->dev, "scratchpad is unsafe\n"); if (!unsafe) { @@ -230,6 +239,9 @@ static int pp_probe(struct ntb_client *client, } } + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) + dev_warn(&ntb->dev, "multi-port NTB is unsupported\n"); + pp = kmalloc(sizeof(*pp), GFP_KERNEL); if (!pp) { rc = -ENOMEM; diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index 61bf2ef87e0e..f002bf48a08d 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -119,7 +119,10 @@ MODULE_VERSION(DRIVER_VERSION); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESCRIPTION); -#define MAX_MWS 16 +/* It is rare to have hadrware with greater than six MWs */ +#define MAX_MWS 6 +/* Only two-ports devices are supported */ +#define PIDX NTB_DEF_PEER_IDX static struct dentry *tool_dbgfs; @@ -459,13 +462,22 @@ static TOOL_FOPS_RDWR(tool_spad_fops, tool_spad_read, tool_spad_write); +static u32 ntb_tool_peer_spad_read(struct ntb_dev *ntb, int sidx) +{ + return ntb_peer_spad_read(ntb, PIDX, sidx); +} + static ssize_t tool_peer_spad_read(struct file *filep, char __user *ubuf, size_t size, loff_t *offp) { struct tool_ctx *tc = filep->private_data; - return tool_spadfn_read(tc, ubuf, size, offp, - tc->ntb->ops->peer_spad_read); + return tool_spadfn_read(tc, ubuf, size, offp, ntb_tool_peer_spad_read); +} + +static int ntb_tool_peer_spad_write(struct ntb_dev *ntb, int sidx, u32 val) +{ + return ntb_peer_spad_write(ntb, PIDX, sidx, val); } static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf, @@ -474,7 +486,7 @@ static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf, struct tool_ctx *tc = filep->private_data; return tool_spadfn_write(tc, ubuf, size, offp, - tc->ntb->ops->peer_spad_write); + ntb_tool_peer_spad_write); } static TOOL_FOPS_RDWR(tool_peer_spad_fops, @@ -668,28 +680,27 @@ static int tool_setup_mw(struct tool_ctx *tc, int idx, size_t req_size) { int rc; struct tool_mw *mw = &tc->mws[idx]; - phys_addr_t base; - resource_size_t size, align, align_size; + resource_size_t size, align_addr, align_size; char buf[16]; if (mw->peer) return 0; - rc = ntb_mw_get_range(tc->ntb, idx, &base, &size, &align, - &align_size); + rc = ntb_mw_get_align(tc->ntb, PIDX, idx, &align_addr, + &align_size, &size); if (rc) return rc; mw->size = min_t(resource_size_t, req_size, size); - mw->size = round_up(mw->size, align); + mw->size = round_up(mw->size, align_addr); mw->size = round_up(mw->size, align_size); mw->peer = dma_alloc_coherent(&tc->ntb->pdev->dev, mw->size, &mw->peer_dma, GFP_KERNEL); - if (!mw->peer) + if (!mw->peer || !IS_ALIGNED(mw->peer_dma, align_addr)) return -ENOMEM; - rc = ntb_mw_set_trans(tc->ntb, idx, mw->peer_dma, mw->size); + rc = ntb_mw_set_trans(tc->ntb, PIDX, idx, mw->peer_dma, mw->size); if (rc) goto err_free_dma; @@ -716,7 +727,7 @@ static void tool_free_mw(struct tool_ctx *tc, int idx) struct tool_mw *mw = &tc->mws[idx]; if (mw->peer) { - ntb_mw_clear_trans(tc->ntb, idx); + ntb_mw_clear_trans(tc->ntb, PIDX, idx); dma_free_coherent(&tc->ntb->pdev->dev, mw->size, mw->peer, mw->peer_dma); @@ -742,8 +753,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, phys_addr_t base; resource_size_t mw_size; - resource_size_t align; + resource_size_t align_addr; resource_size_t align_size; + resource_size_t max_size; buf_size = min_t(size_t, size, 512); @@ -751,8 +763,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, if (!buf) return -ENOMEM; - ntb_mw_get_range(mw->tc->ntb, mw->idx, - &base, &mw_size, &align, &align_size); + ntb_mw_get_align(mw->tc->ntb, PIDX, mw->idx, + &align_addr, &align_size, &max_size); + ntb_peer_mw_get_addr(mw->tc->ntb, mw->idx, &base, &mw_size); off += scnprintf(buf + off, buf_size - off, "Peer MW %d Information:\n", mw->idx); @@ -767,13 +780,17 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, off += scnprintf(buf + off, buf_size - off, "Alignment \t%lld\n", - (unsigned long long)align); + (unsigned long long)align_addr); off += scnprintf(buf + off, buf_size - off, "Size Alignment \t%lld\n", (unsigned long long)align_size); off += scnprintf(buf + off, buf_size - off, + "Size Max \t%lld\n", + (unsigned long long)max_size); + + off += scnprintf(buf + off, buf_size - off, "Ready \t%c\n", (mw->peer) ? 'Y' : 'N'); @@ -827,8 +844,7 @@ static int tool_init_mw(struct tool_ctx *tc, int idx) phys_addr_t base; int rc; - rc = ntb_mw_get_range(tc->ntb, idx, &base, &mw->win_size, - NULL, NULL); + rc = ntb_peer_mw_get_addr(tc->ntb, idx, &base, &mw->win_size); if (rc) return rc; @@ -913,12 +929,27 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) int rc; int i; + if (!ntb->ops->mw_set_trans) { + dev_dbg(&ntb->dev, "need inbound MW based NTB API\n"); + rc = -EINVAL; + goto err_tc; + } + + if (ntb_spad_count(ntb) < 1) { + dev_dbg(&ntb->dev, "no enough scratchpads\n"); + rc = -EINVAL; + goto err_tc; + } + if (ntb_db_is_unsafe(ntb)) dev_dbg(&ntb->dev, "doorbell is unsafe\n"); if (ntb_spad_is_unsafe(ntb)) dev_dbg(&ntb->dev, "scratchpad is unsafe\n"); + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) + dev_warn(&ntb->dev, "multi-port NTB is unsupported\n"); + tc = kzalloc(sizeof(*tc), GFP_KERNEL); if (!tc) { rc = -ENOMEM; @@ -928,7 +959,7 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) tc->ntb = ntb; init_waitqueue_head(&tc->link_wq); - tc->mw_count = min(ntb_mw_count(tc->ntb), MAX_MWS); + tc->mw_count = min(ntb_mw_count(tc->ntb, PIDX), MAX_MWS); for (i = 0; i < tc->mw_count; i++) { rc = tool_init_mw(tc, i); if (rc) diff --git a/drivers/pci/host/pcie-rockchip.c b/drivers/pci/host/pcie-rockchip.c index 5acf8694fb23..7bb9870f6d8c 100644 --- a/drivers/pci/host/pcie-rockchip.c +++ b/drivers/pci/host/pcie-rockchip.c @@ -1483,7 +1483,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev) bridge->swizzle_irq = pci_common_swizzle; err = pci_scan_root_bus_bridge(bridge); - if (!err) + if (err < 0) goto err_free_res; bus = bridge->bus; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 607f677f48d2..d51e8738f9c2 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -511,6 +511,7 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev) } pci_restore_state(pci_dev); + pci_pme_restore(pci_dev); return 0; } @@ -522,6 +523,7 @@ static void pci_pm_default_resume_early(struct pci_dev *pci_dev) { pci_power_up(pci_dev); pci_restore_state(pci_dev); + pci_pme_restore(pci_dev); pci_fixup_device(pci_fixup_resume_early, pci_dev); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d88edf5c563b..af0cc3456dc1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1801,7 +1801,11 @@ static void __pci_pme_active(struct pci_dev *dev, bool enable) pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr); } -static void pci_pme_restore(struct pci_dev *dev) +/** + * pci_pme_restore - Restore PME configuration after config space restore. + * @dev: PCI device to update. + */ +void pci_pme_restore(struct pci_dev *dev) { u16 pmcsr; @@ -1811,6 +1815,7 @@ static void pci_pme_restore(struct pci_dev *dev) pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); if (dev->wakeup_prepared) { pmcsr |= PCI_PM_CTRL_PME_ENABLE; + pmcsr &= ~PCI_PM_CTRL_PME_STATUS; } else { pmcsr &= ~PCI_PM_CTRL_PME_ENABLE; pmcsr |= PCI_PM_CTRL_PME_STATUS; @@ -1907,14 +1912,9 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) { int ret = 0; - /* - * Don't do the same thing twice in a row for one device, but restore - * PME Enable in case it has been updated by config space restoration. - */ - if (!!enable == !!dev->wakeup_prepared) { - pci_pme_restore(dev); + /* Don't do the same thing twice in a row for one device. */ + if (!!enable == !!dev->wakeup_prepared) return 0; - } /* * According to "PCI System Architecture" 4th ed. by Tom Shanley & Don diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 03e3d0285aea..22e061738c6f 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -71,6 +71,7 @@ void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); +void pci_pme_restore(struct pci_dev *dev); bool pci_dev_keep_suspended(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c index 80e58d25006d..fafdb165dd2e 100644 --- a/drivers/pci/pcie/pme.c +++ b/drivers/pci/pcie/pme.c @@ -40,17 +40,11 @@ static int __init pcie_pme_setup(char *str) } __setup("pcie_pme=", pcie_pme_setup); -enum pme_suspend_level { - PME_SUSPEND_NONE = 0, - PME_SUSPEND_WAKEUP, - PME_SUSPEND_NOIRQ, -}; - struct pcie_pme_service_data { spinlock_t lock; struct pcie_device *srv; struct work_struct work; - enum pme_suspend_level suspend_level; + bool noirq; /* If set, keep the PME interrupt disabled. */ }; /** @@ -228,7 +222,7 @@ static void pcie_pme_work_fn(struct work_struct *work) spin_lock_irq(&data->lock); for (;;) { - if (data->suspend_level != PME_SUSPEND_NONE) + if (data->noirq) break; pcie_capability_read_dword(port, PCI_EXP_RTSTA, &rtsta); @@ -255,7 +249,7 @@ static void pcie_pme_work_fn(struct work_struct *work) spin_lock_irq(&data->lock); } - if (data->suspend_level == PME_SUSPEND_NONE) + if (!data->noirq) pcie_pme_interrupt_enable(port, true); spin_unlock_irq(&data->lock); @@ -378,7 +372,7 @@ static int pcie_pme_suspend(struct pcie_device *srv) { struct pcie_pme_service_data *data = get_service_data(srv); struct pci_dev *port = srv->port; - bool wakeup, wake_irq_enabled = false; + bool wakeup; int ret; if (device_may_wakeup(&port->dev)) { @@ -388,19 +382,16 @@ static int pcie_pme_suspend(struct pcie_device *srv) wakeup = pcie_pme_check_wakeup(port->subordinate); up_read(&pci_bus_sem); } - spin_lock_irq(&data->lock); if (wakeup) { ret = enable_irq_wake(srv->irq); - if (ret == 0) { - data->suspend_level = PME_SUSPEND_WAKEUP; - wake_irq_enabled = true; - } - } - if (!wake_irq_enabled) { - pcie_pme_interrupt_enable(port, false); - pcie_clear_root_pme_status(port); - data->suspend_level = PME_SUSPEND_NOIRQ; + if (!ret) + return 0; } + + spin_lock_irq(&data->lock); + pcie_pme_interrupt_enable(port, false); + pcie_clear_root_pme_status(port); + data->noirq = true; spin_unlock_irq(&data->lock); synchronize_irq(srv->irq); @@ -417,15 +408,15 @@ static int pcie_pme_resume(struct pcie_device *srv) struct pcie_pme_service_data *data = get_service_data(srv); spin_lock_irq(&data->lock); - if (data->suspend_level == PME_SUSPEND_NOIRQ) { + if (data->noirq) { struct pci_dev *port = srv->port; pcie_clear_root_pme_status(port); pcie_pme_interrupt_enable(port, true); + data->noirq = false; } else { disable_irq_wake(srv->irq); } - data->suspend_level = PME_SUSPEND_NONE; spin_unlock_irq(&data->lock); return 0; diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c index 4300a558d0f3..322de58eebaf 100644 --- a/drivers/platform/mips/cpu_hwmon.c +++ b/drivers/platform/mips/cpu_hwmon.c @@ -17,17 +17,27 @@ */ int loongson3_cpu_temp(int cpu) { - u32 reg; + u32 reg, prid_rev; reg = LOONGSON_CHIPTEMP(cpu); - if ((read_c0_prid() & PRID_REV_MASK) == PRID_REV_LOONGSON3A_R1) + prid_rev = read_c0_prid() & PRID_REV_MASK; + switch (prid_rev) { + case PRID_REV_LOONGSON3A_R1: reg = (reg >> 8) & 0xff; - else + break; + case PRID_REV_LOONGSON3A_R2: + case PRID_REV_LOONGSON3B_R1: + case PRID_REV_LOONGSON3B_R2: reg = ((reg >> 8) & 0xff) - 100; - + break; + case PRID_REV_LOONGSON3A_R3: + reg = (reg & 0xffff)*731/0x4000 - 273; + break; + } return (int)reg * 1000; } +static int nr_packages; static struct device *cpu_hwmon_dev; static ssize_t get_hwmon_name(struct device *dev, @@ -51,88 +61,74 @@ static ssize_t get_hwmon_name(struct device *dev, return sprintf(buf, "cpu-hwmon\n"); } -static ssize_t get_cpu0_temp(struct device *dev, - struct device_attribute *attr, char *buf); -static ssize_t get_cpu1_temp(struct device *dev, +static ssize_t get_cpu_temp(struct device *dev, struct device_attribute *attr, char *buf); -static ssize_t cpu0_temp_label(struct device *dev, +static ssize_t cpu_temp_label(struct device *dev, struct device_attribute *attr, char *buf); -static ssize_t cpu1_temp_label(struct device *dev, - struct device_attribute *attr, char *buf); - -static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, get_cpu0_temp, NULL, 1); -static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, cpu0_temp_label, NULL, 1); -static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, get_cpu1_temp, NULL, 2); -static SENSOR_DEVICE_ATTR(temp2_label, S_IRUGO, cpu1_temp_label, NULL, 2); -static const struct attribute *hwmon_cputemp1[] = { - &sensor_dev_attr_temp1_input.dev_attr.attr, - &sensor_dev_attr_temp1_label.dev_attr.attr, - NULL -}; - -static const struct attribute *hwmon_cputemp2[] = { - &sensor_dev_attr_temp2_input.dev_attr.attr, - &sensor_dev_attr_temp2_label.dev_attr.attr, - NULL +static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, get_cpu_temp, NULL, 1); +static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, cpu_temp_label, NULL, 1); +static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, get_cpu_temp, NULL, 2); +static SENSOR_DEVICE_ATTR(temp2_label, S_IRUGO, cpu_temp_label, NULL, 2); +static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, get_cpu_temp, NULL, 3); +static SENSOR_DEVICE_ATTR(temp3_label, S_IRUGO, cpu_temp_label, NULL, 3); +static SENSOR_DEVICE_ATTR(temp4_input, S_IRUGO, get_cpu_temp, NULL, 4); +static SENSOR_DEVICE_ATTR(temp4_label, S_IRUGO, cpu_temp_label, NULL, 4); + +static const struct attribute *hwmon_cputemp[4][3] = { + { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_temp1_label.dev_attr.attr, + NULL + }, + { + &sensor_dev_attr_temp2_input.dev_attr.attr, + &sensor_dev_attr_temp2_label.dev_attr.attr, + NULL + }, + { + &sensor_dev_attr_temp3_input.dev_attr.attr, + &sensor_dev_attr_temp3_label.dev_attr.attr, + NULL + }, + { + &sensor_dev_attr_temp4_input.dev_attr.attr, + &sensor_dev_attr_temp4_label.dev_attr.attr, + NULL + } }; -static ssize_t cpu0_temp_label(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "CPU 0 Temperature\n"); -} - -static ssize_t cpu1_temp_label(struct device *dev, +static ssize_t cpu_temp_label(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "CPU 1 Temperature\n"); + int id = (to_sensor_dev_attr(attr))->index - 1; + return sprintf(buf, "CPU %d Temperature\n", id); } -static ssize_t get_cpu0_temp(struct device *dev, +static ssize_t get_cpu_temp(struct device *dev, struct device_attribute *attr, char *buf) { - int value = loongson3_cpu_temp(0); - return sprintf(buf, "%d\n", value); -} - -static ssize_t get_cpu1_temp(struct device *dev, - struct device_attribute *attr, char *buf) -{ - int value = loongson3_cpu_temp(1); + int id = (to_sensor_dev_attr(attr))->index - 1; + int value = loongson3_cpu_temp(id); return sprintf(buf, "%d\n", value); } static int create_sysfs_cputemp_files(struct kobject *kobj) { - int ret; - - ret = sysfs_create_files(kobj, hwmon_cputemp1); - if (ret) - goto sysfs_create_temp1_fail; - - if (loongson_sysconf.nr_cpus <= loongson_sysconf.cores_per_package) - return 0; + int i, ret = 0; - ret = sysfs_create_files(kobj, hwmon_cputemp2); - if (ret) - goto sysfs_create_temp2_fail; + for (i=0; i<nr_packages; i++) + ret = sysfs_create_files(kobj, hwmon_cputemp[i]); - return 0; - -sysfs_create_temp2_fail: - sysfs_remove_files(kobj, hwmon_cputemp1); - -sysfs_create_temp1_fail: - return -1; + return ret; } static void remove_sysfs_cputemp_files(struct kobject *kobj) { - sysfs_remove_files(&cpu_hwmon_dev->kobj, hwmon_cputemp1); + int i; - if (loongson_sysconf.nr_cpus > loongson_sysconf.cores_per_package) - sysfs_remove_files(&cpu_hwmon_dev->kobj, hwmon_cputemp2); + for (i=0; i<nr_packages; i++) + sysfs_remove_files(kobj, hwmon_cputemp[i]); } #define CPU_THERMAL_THRESHOLD 90000 @@ -140,8 +136,15 @@ static struct delayed_work thermal_work; static void do_thermal_timer(struct work_struct *work) { - int value = loongson3_cpu_temp(0); - if (value <= CPU_THERMAL_THRESHOLD) + int i, value, temp_max = 0; + + for (i=0; i<nr_packages; i++) { + value = loongson3_cpu_temp(i); + if (value > temp_max) + temp_max = value; + } + + if (temp_max <= CPU_THERMAL_THRESHOLD) schedule_delayed_work(&thermal_work, msecs_to_jiffies(5000)); else orderly_poweroff(true); @@ -160,6 +163,9 @@ static int __init loongson_hwmon_init(void) goto fail_hwmon_device_register; } + nr_packages = loongson_sysconf.nr_cpus / + loongson_sysconf.cores_per_package; + ret = sysfs_create_group(&cpu_hwmon_dev->kobj, &cpu_hwmon_attribute_group); if (ret) { diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index 903b667f8e01..f9bc8ec6fb6b 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -47,18 +47,21 @@ static void chap_binaryhex_to_asciihex(char *dst, char *src, int src_len) } } -static void chap_gen_challenge( +static int chap_gen_challenge( struct iscsi_conn *conn, int caller, char *c_str, unsigned int *c_len) { + int ret; unsigned char challenge_asciihex[CHAP_CHALLENGE_LENGTH * 2 + 1]; struct iscsi_chap *chap = conn->auth_protocol; memset(challenge_asciihex, 0, CHAP_CHALLENGE_LENGTH * 2 + 1); - get_random_bytes(chap->challenge, CHAP_CHALLENGE_LENGTH); + ret = get_random_bytes_wait(chap->challenge, CHAP_CHALLENGE_LENGTH); + if (unlikely(ret)) + return ret; chap_binaryhex_to_asciihex(challenge_asciihex, chap->challenge, CHAP_CHALLENGE_LENGTH); /* @@ -69,6 +72,7 @@ static void chap_gen_challenge( pr_debug("[%s] Sending CHAP_C=0x%s\n\n", (caller) ? "server" : "client", challenge_asciihex); + return 0; } static int chap_check_algorithm(const char *a_str) @@ -143,6 +147,7 @@ static struct iscsi_chap *chap_server_open( case CHAP_DIGEST_UNKNOWN: default: pr_err("Unsupported CHAP_A value\n"); + kfree(conn->auth_protocol); return NULL; } @@ -156,7 +161,10 @@ static struct iscsi_chap *chap_server_open( /* * Generate Challenge. */ - chap_gen_challenge(conn, 1, aic_str, aic_len); + if (chap_gen_challenge(conn, 1, aic_str, aic_len) < 0) { + kfree(conn->auth_protocol); + return NULL; + } return chap; } diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 92b96b51d506..e9bdc8b86e7d 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -245,22 +245,26 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn) return 0; } -static void iscsi_login_set_conn_values( +static int iscsi_login_set_conn_values( struct iscsi_session *sess, struct iscsi_conn *conn, __be16 cid) { + int ret; conn->sess = sess; conn->cid = be16_to_cpu(cid); /* * Generate a random Status sequence number (statsn) for the new * iSCSI connection. */ - get_random_bytes(&conn->stat_sn, sizeof(u32)); + ret = get_random_bytes_wait(&conn->stat_sn, sizeof(u32)); + if (unlikely(ret)) + return ret; mutex_lock(&auth_id_lock); conn->auth_id = iscsit_global->auth_id++; mutex_unlock(&auth_id_lock); + return 0; } __printf(2, 3) int iscsi_change_param_sprintf( @@ -306,7 +310,11 @@ static int iscsi_login_zero_tsih_s1( return -ENOMEM; } - iscsi_login_set_conn_values(sess, conn, pdu->cid); + ret = iscsi_login_set_conn_values(sess, conn, pdu->cid); + if (unlikely(ret)) { + kfree(sess); + return ret; + } sess->init_task_tag = pdu->itt; memcpy(&sess->isid, pdu->isid, 6); sess->exp_cmd_sn = be32_to_cpu(pdu->cmdsn); @@ -497,8 +505,7 @@ static int iscsi_login_non_zero_tsih_s1( { struct iscsi_login_req *pdu = (struct iscsi_login_req *)buf; - iscsi_login_set_conn_values(NULL, conn, pdu->cid); - return 0; + return iscsi_login_set_conn_values(NULL, conn, pdu->cid); } /* @@ -554,9 +561,8 @@ static int iscsi_login_non_zero_tsih_s2( atomic_set(&sess->session_continuation, 1); spin_unlock_bh(&sess->conn_lock); - iscsi_login_set_conn_values(sess, conn, pdu->cid); - - if (iscsi_copy_param_list(&conn->param_list, + if (iscsi_login_set_conn_values(sess, conn, pdu->cid) < 0 || + iscsi_copy_param_list(&conn->param_list, conn->tpg->param_list, 0) < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_NO_RESOURCES); diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c index 0ecf80890c84..e6863c841662 100644 --- a/drivers/thermal/broadcom/bcm2835_thermal.c +++ b/drivers/thermal/broadcom/bcm2835_thermal.c @@ -245,7 +245,6 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) */ err = tz->ops->get_trip_temp(tz, 0, &trip_temp); if (err < 0) { - err = PTR_ERR(tz); dev_err(&pdev->dev, "Not able to read trip_temp: %d\n", err); diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 69d0f430b2d1..908a8014cf76 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -49,40 +49,45 @@ */ /** - * struct power_table - frequency to power conversion + * struct freq_table - frequency table along with power entries * @frequency: frequency in KHz * @power: power in mW * * This structure is built when the cooling device registers and helps - * in translating frequency to power and viceversa. + * in translating frequency to power and vice versa. */ -struct power_table { +struct freq_table { u32 frequency; u32 power; }; /** + * struct time_in_idle - Idle time stats + * @time: previous reading of the absolute time that this cpu was idle + * @timestamp: wall time of the last invocation of get_cpu_idle_time_us() + */ +struct time_in_idle { + u64 time; + u64 timestamp; +}; + +/** * struct cpufreq_cooling_device - data for cooling device with cpufreq * @id: unique integer value corresponding to each cpufreq_cooling_device * registered. - * @cool_dev: thermal_cooling_device pointer to keep track of the - * registered cooling device. + * @last_load: load measured by the latest call to cpufreq_get_requested_power() * @cpufreq_state: integer value representing the current state of cpufreq * cooling devices. * @clipped_freq: integer value representing the absolute value of the clipped * frequency. * @max_level: maximum cooling level. One less than total number of valid * cpufreq frequencies. - * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device. + * @freq_table: Freq table in descending order of frequencies + * @cdev: thermal_cooling_device pointer to keep track of the + * registered cooling device. + * @policy: cpufreq policy. * @node: list_head to link all cpufreq_cooling_device together. - * @last_load: load measured by the latest call to cpufreq_get_requested_power() - * @time_in_idle: previous reading of the absolute time that this cpu was idle - * @time_in_idle_timestamp: wall time of the last invocation of - * get_cpu_idle_time_us() - * @dyn_power_table: array of struct power_table for frequency to power - * conversion, sorted in ascending order. - * @dyn_power_table_entries: number of entries in the @dyn_power_table array - * @cpu_dev: the first cpu_device from @allowed_cpus that has OPPs registered + * @idle_time: idle time stats * @plat_get_static_power: callback to calculate the static power * * This structure is required for keeping information of each registered @@ -90,81 +95,45 @@ struct power_table { */ struct cpufreq_cooling_device { int id; - struct thermal_cooling_device *cool_dev; + u32 last_load; unsigned int cpufreq_state; unsigned int clipped_freq; unsigned int max_level; - unsigned int *freq_table; /* In descending order */ - struct cpumask allowed_cpus; + struct freq_table *freq_table; /* In descending order */ + struct thermal_cooling_device *cdev; + struct cpufreq_policy *policy; struct list_head node; - u32 last_load; - u64 *time_in_idle; - u64 *time_in_idle_timestamp; - struct power_table *dyn_power_table; - int dyn_power_table_entries; - struct device *cpu_dev; + struct time_in_idle *idle_time; get_static_t plat_get_static_power; }; -static DEFINE_IDA(cpufreq_ida); +static DEFINE_IDA(cpufreq_ida); static DEFINE_MUTEX(cooling_list_lock); -static LIST_HEAD(cpufreq_dev_list); +static LIST_HEAD(cpufreq_cdev_list); /* Below code defines functions to be used for cpufreq as cooling device */ /** * get_level: Find the level for a particular frequency - * @cpufreq_dev: cpufreq_dev for which the property is required + * @cpufreq_cdev: cpufreq_cdev for which the property is required * @freq: Frequency * - * Return: level on success, THERMAL_CSTATE_INVALID on error. + * Return: level corresponding to the frequency. */ -static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_dev, +static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, unsigned int freq) { + struct freq_table *freq_table = cpufreq_cdev->freq_table; unsigned long level; - for (level = 0; level <= cpufreq_dev->max_level; level++) { - if (freq == cpufreq_dev->freq_table[level]) - return level; - - if (freq > cpufreq_dev->freq_table[level]) + for (level = 1; level <= cpufreq_cdev->max_level; level++) + if (freq > freq_table[level].frequency) break; - } - return THERMAL_CSTATE_INVALID; + return level - 1; } /** - * cpufreq_cooling_get_level - for a given cpu, return the cooling level. - * @cpu: cpu for which the level is required - * @freq: the frequency of interest - * - * This function will match the cooling level corresponding to the - * requested @freq and return it. - * - * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID - * otherwise. - */ -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - struct cpufreq_cooling_device *cpufreq_dev; - - mutex_lock(&cooling_list_lock); - list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) { - if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) { - mutex_unlock(&cooling_list_lock); - return get_level(cpufreq_dev, freq); - } - } - mutex_unlock(&cooling_list_lock); - - pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu); - return THERMAL_CSTATE_INVALID; -} -EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level); - -/** * cpufreq_thermal_notifier - notifier callback for cpufreq policy change. * @nb: struct notifier_block * with callback info. * @event: value showing cpufreq event for which this function invoked. @@ -181,14 +150,18 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, { struct cpufreq_policy *policy = data; unsigned long clipped_freq; - struct cpufreq_cooling_device *cpufreq_dev; + struct cpufreq_cooling_device *cpufreq_cdev; if (event != CPUFREQ_ADJUST) return NOTIFY_DONE; mutex_lock(&cooling_list_lock); - list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) { - if (!cpumask_test_cpu(policy->cpu, &cpufreq_dev->allowed_cpus)) + list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) { + /* + * A new copy of the policy is sent to the notifier and can't + * compare that directly. + */ + if (policy->cpu != cpufreq_cdev->policy->cpu) continue; /* @@ -202,7 +175,7 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, * But, if clipped_freq is greater than policy->max, we don't * need to do anything. */ - clipped_freq = cpufreq_dev->clipped_freq; + clipped_freq = cpufreq_cdev->clipped_freq; if (policy->max > clipped_freq) cpufreq_verify_within_limits(policy, 0, clipped_freq); @@ -214,63 +187,63 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, } /** - * build_dyn_power_table() - create a dynamic power to frequency table - * @cpufreq_device: the cpufreq cooling device in which to store the table + * update_freq_table() - Update the freq table with power numbers + * @cpufreq_cdev: the cpufreq cooling device in which to update the table * @capacitance: dynamic power coefficient for these cpus * - * Build a dynamic power to frequency table for this cpu and store it - * in @cpufreq_device. This table will be used in cpu_power_to_freq() and - * cpu_freq_to_power() to convert between power and frequency - * efficiently. Power is stored in mW, frequency in KHz. The - * resulting table is in ascending order. + * Update the freq table with power numbers. This table will be used in + * cpu_power_to_freq() and cpu_freq_to_power() to convert between power and + * frequency efficiently. Power is stored in mW, frequency in KHz. The + * resulting table is in descending order. * * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs, - * -ENOMEM if we run out of memory or -EAGAIN if an OPP was - * added/enabled while the function was executing. + * or -ENOMEM if we run out of memory. */ -static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device, - u32 capacitance) +static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev, + u32 capacitance) { - struct power_table *power_table; + struct freq_table *freq_table = cpufreq_cdev->freq_table; struct dev_pm_opp *opp; struct device *dev = NULL; - int num_opps = 0, cpu, i, ret = 0; - unsigned long freq; - - for_each_cpu(cpu, &cpufreq_device->allowed_cpus) { - dev = get_cpu_device(cpu); - if (!dev) { - dev_warn(&cpufreq_device->cool_dev->device, - "No cpu device for cpu %d\n", cpu); - continue; - } + int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i; - num_opps = dev_pm_opp_get_opp_count(dev); - if (num_opps > 0) - break; - else if (num_opps < 0) - return num_opps; + dev = get_cpu_device(cpu); + if (unlikely(!dev)) { + dev_warn(&cpufreq_cdev->cdev->device, + "No cpu device for cpu %d\n", cpu); + return -ENODEV; } - if (num_opps == 0) - return -EINVAL; + num_opps = dev_pm_opp_get_opp_count(dev); + if (num_opps < 0) + return num_opps; - power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL); - if (!power_table) - return -ENOMEM; + /* + * The cpufreq table is also built from the OPP table and so the count + * should match. + */ + if (num_opps != cpufreq_cdev->max_level + 1) { + dev_warn(dev, "Number of OPPs not matching with max_levels\n"); + return -EINVAL; + } - for (freq = 0, i = 0; - opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp); - freq++, i++) { - u32 freq_mhz, voltage_mv; + for (i = 0; i <= cpufreq_cdev->max_level; i++) { + unsigned long freq = freq_table[i].frequency * 1000; + u32 freq_mhz = freq_table[i].frequency / 1000; u64 power; + u32 voltage_mv; - if (i >= num_opps) { - ret = -EAGAIN; - goto free_power_table; + /* + * Find ceil frequency as 'freq' may be slightly lower than OPP + * freq due to truncation while converting to kHz. + */ + opp = dev_pm_opp_find_freq_ceil(dev, &freq); + if (IS_ERR(opp)) { + dev_err(dev, "failed to get opp for %lu frequency\n", + freq); + return -EINVAL; } - freq_mhz = freq / 1000000; voltage_mv = dev_pm_opp_get_voltage(opp) / 1000; dev_pm_opp_put(opp); @@ -281,89 +254,73 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device, power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv; do_div(power, 1000000000); - /* frequency is stored in power_table in KHz */ - power_table[i].frequency = freq / 1000; - /* power is stored in mW */ - power_table[i].power = power; + freq_table[i].power = power; } - if (i != num_opps) { - ret = PTR_ERR(opp); - goto free_power_table; - } - - cpufreq_device->cpu_dev = dev; - cpufreq_device->dyn_power_table = power_table; - cpufreq_device->dyn_power_table_entries = i; - return 0; - -free_power_table: - kfree(power_table); - - return ret; } -static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device, +static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, u32 freq) { int i; - struct power_table *pt = cpufreq_device->dyn_power_table; + struct freq_table *freq_table = cpufreq_cdev->freq_table; - for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++) - if (freq < pt[i].frequency) + for (i = 1; i <= cpufreq_cdev->max_level; i++) + if (freq > freq_table[i].frequency) break; - return pt[i - 1].power; + return freq_table[i - 1].power; } -static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device, +static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, u32 power) { int i; - struct power_table *pt = cpufreq_device->dyn_power_table; + struct freq_table *freq_table = cpufreq_cdev->freq_table; - for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++) - if (power < pt[i].power) + for (i = 1; i <= cpufreq_cdev->max_level; i++) + if (power > freq_table[i].power) break; - return pt[i - 1].frequency; + return freq_table[i - 1].frequency; } /** * get_load() - get load for a cpu since last updated - * @cpufreq_device: &struct cpufreq_cooling_device for this cpu + * @cpufreq_cdev: &struct cpufreq_cooling_device for this cpu * @cpu: cpu number - * @cpu_idx: index of the cpu in cpufreq_device->allowed_cpus + * @cpu_idx: index of the cpu in time_in_idle* * * Return: The average load of cpu @cpu in percentage since this * function was last called. */ -static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu, +static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu, int cpu_idx) { u32 load; u64 now, now_idle, delta_time, delta_idle; + struct time_in_idle *idle_time = &cpufreq_cdev->idle_time[cpu_idx]; now_idle = get_cpu_idle_time(cpu, &now, 0); - delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx]; - delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx]; + delta_idle = now_idle - idle_time->time; + delta_time = now - idle_time->timestamp; if (delta_time <= delta_idle) load = 0; else load = div64_u64(100 * (delta_time - delta_idle), delta_time); - cpufreq_device->time_in_idle[cpu_idx] = now_idle; - cpufreq_device->time_in_idle_timestamp[cpu_idx] = now; + idle_time->time = now_idle; + idle_time->timestamp = now; return load; } /** * get_static_power() - calculate the static power consumed by the cpus - * @cpufreq_device: struct &cpufreq_cooling_device for this cpu cdev + * @cpufreq_cdev: struct &cpufreq_cooling_device for this cpu cdev * @tz: thermal zone device in which we're operating * @freq: frequency in KHz * @power: pointer in which to store the calculated static power @@ -376,26 +333,28 @@ static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu, * * Return: 0 on success, -E* on failure. */ -static int get_static_power(struct cpufreq_cooling_device *cpufreq_device, +static int get_static_power(struct cpufreq_cooling_device *cpufreq_cdev, struct thermal_zone_device *tz, unsigned long freq, u32 *power) { struct dev_pm_opp *opp; unsigned long voltage; - struct cpumask *cpumask = &cpufreq_device->allowed_cpus; + struct cpufreq_policy *policy = cpufreq_cdev->policy; + struct cpumask *cpumask = policy->related_cpus; unsigned long freq_hz = freq * 1000; + struct device *dev; - if (!cpufreq_device->plat_get_static_power || - !cpufreq_device->cpu_dev) { + if (!cpufreq_cdev->plat_get_static_power) { *power = 0; return 0; } - opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz, - true); + dev = get_cpu_device(policy->cpu); + WARN_ON(!dev); + + opp = dev_pm_opp_find_freq_exact(dev, freq_hz, true); if (IS_ERR(opp)) { - dev_warn_ratelimited(cpufreq_device->cpu_dev, - "Failed to find OPP for frequency %lu: %ld\n", + dev_warn_ratelimited(dev, "Failed to find OPP for frequency %lu: %ld\n", freq_hz, PTR_ERR(opp)); return -EINVAL; } @@ -404,31 +363,30 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device, dev_pm_opp_put(opp); if (voltage == 0) { - dev_err_ratelimited(cpufreq_device->cpu_dev, - "Failed to get voltage for frequency %lu\n", + dev_err_ratelimited(dev, "Failed to get voltage for frequency %lu\n", freq_hz); return -EINVAL; } - return cpufreq_device->plat_get_static_power(cpumask, tz->passive_delay, - voltage, power); + return cpufreq_cdev->plat_get_static_power(cpumask, tz->passive_delay, + voltage, power); } /** * get_dynamic_power() - calculate the dynamic power - * @cpufreq_device: &cpufreq_cooling_device for this cdev + * @cpufreq_cdev: &cpufreq_cooling_device for this cdev * @freq: current frequency * * Return: the dynamic power consumed by the cpus described by - * @cpufreq_device. + * @cpufreq_cdev. */ -static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device, +static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev, unsigned long freq) { u32 raw_cpu_power; - raw_cpu_power = cpu_freq_to_power(cpufreq_device, freq); - return (raw_cpu_power * cpufreq_device->last_load) / 100; + raw_cpu_power = cpu_freq_to_power(cpufreq_cdev, freq); + return (raw_cpu_power * cpufreq_cdev->last_load) / 100; } /* cpufreq cooling device callback functions are defined below */ @@ -446,9 +404,9 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device, static int cpufreq_get_max_state(struct thermal_cooling_device *cdev, unsigned long *state) { - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - *state = cpufreq_device->max_level; + *state = cpufreq_cdev->max_level; return 0; } @@ -465,9 +423,9 @@ static int cpufreq_get_max_state(struct thermal_cooling_device *cdev, static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - *state = cpufreq_device->cpufreq_state; + *state = cpufreq_cdev->cpufreq_state; return 0; } @@ -485,23 +443,22 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev, static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state) { - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; - unsigned int cpu = cpumask_any(&cpufreq_device->allowed_cpus); + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; unsigned int clip_freq; /* Request state should be less than max_level */ - if (WARN_ON(state > cpufreq_device->max_level)) + if (WARN_ON(state > cpufreq_cdev->max_level)) return -EINVAL; /* Check if the old cooling action is same as new cooling action */ - if (cpufreq_device->cpufreq_state == state) + if (cpufreq_cdev->cpufreq_state == state) return 0; - clip_freq = cpufreq_device->freq_table[state]; - cpufreq_device->cpufreq_state = state; - cpufreq_device->clipped_freq = clip_freq; + clip_freq = cpufreq_cdev->freq_table[state].frequency; + cpufreq_cdev->cpufreq_state = state; + cpufreq_cdev->clipped_freq = clip_freq; - cpufreq_update_policy(cpu); + cpufreq_update_policy(cpufreq_cdev->policy->cpu); return 0; } @@ -536,33 +493,23 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, unsigned long freq; int i = 0, cpu, ret; u32 static_power, dynamic_power, total_load = 0; - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + struct cpufreq_policy *policy = cpufreq_cdev->policy; u32 *load_cpu = NULL; - cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask); - - /* - * All the CPUs are offline, thus the requested power by - * the cdev is 0 - */ - if (cpu >= nr_cpu_ids) { - *power = 0; - return 0; - } - - freq = cpufreq_quick_get(cpu); + freq = cpufreq_quick_get(policy->cpu); if (trace_thermal_power_cpu_get_power_enabled()) { - u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus); + u32 ncpus = cpumask_weight(policy->related_cpus); load_cpu = kcalloc(ncpus, sizeof(*load_cpu), GFP_KERNEL); } - for_each_cpu(cpu, &cpufreq_device->allowed_cpus) { + for_each_cpu(cpu, policy->related_cpus) { u32 load; if (cpu_online(cpu)) - load = get_load(cpufreq_device, cpu, i); + load = get_load(cpufreq_cdev, cpu, i); else load = 0; @@ -573,19 +520,19 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, i++; } - cpufreq_device->last_load = total_load; + cpufreq_cdev->last_load = total_load; - dynamic_power = get_dynamic_power(cpufreq_device, freq); - ret = get_static_power(cpufreq_device, tz, freq, &static_power); + dynamic_power = get_dynamic_power(cpufreq_cdev, freq); + ret = get_static_power(cpufreq_cdev, tz, freq, &static_power); if (ret) { kfree(load_cpu); return ret; } if (load_cpu) { - trace_thermal_power_cpu_get_power( - &cpufreq_device->allowed_cpus, - freq, load_cpu, i, dynamic_power, static_power); + trace_thermal_power_cpu_get_power(policy->related_cpus, freq, + load_cpu, i, dynamic_power, + static_power); kfree(load_cpu); } @@ -614,38 +561,23 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, unsigned long state, u32 *power) { unsigned int freq, num_cpus; - cpumask_var_t cpumask; u32 static_power, dynamic_power; int ret; - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; - - if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) - return -ENOMEM; - - cpumask_and(cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask); - num_cpus = cpumask_weight(cpumask); + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - /* None of our cpus are online, so no power */ - if (num_cpus == 0) { - *power = 0; - ret = 0; - goto out; - } + /* Request state should be less than max_level */ + if (WARN_ON(state > cpufreq_cdev->max_level)) + return -EINVAL; - freq = cpufreq_device->freq_table[state]; - if (!freq) { - ret = -EINVAL; - goto out; - } + num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus); - dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus; - ret = get_static_power(cpufreq_device, tz, freq, &static_power); + freq = cpufreq_cdev->freq_table[state].frequency; + dynamic_power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus; + ret = get_static_power(cpufreq_cdev, tz, freq, &static_power); if (ret) - goto out; + return ret; *power = static_power + dynamic_power; -out: - free_cpumask_var(cpumask); return ret; } @@ -673,39 +605,27 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, struct thermal_zone_device *tz, u32 power, unsigned long *state) { - unsigned int cpu, cur_freq, target_freq; + unsigned int cur_freq, target_freq; int ret; s32 dyn_power; u32 last_load, normalised_power, static_power; - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + struct cpufreq_policy *policy = cpufreq_cdev->policy; - cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask); - - /* None of our cpus are online */ - if (cpu >= nr_cpu_ids) - return -ENODEV; - - cur_freq = cpufreq_quick_get(cpu); - ret = get_static_power(cpufreq_device, tz, cur_freq, &static_power); + cur_freq = cpufreq_quick_get(policy->cpu); + ret = get_static_power(cpufreq_cdev, tz, cur_freq, &static_power); if (ret) return ret; dyn_power = power - static_power; dyn_power = dyn_power > 0 ? dyn_power : 0; - last_load = cpufreq_device->last_load ?: 1; + last_load = cpufreq_cdev->last_load ?: 1; normalised_power = (dyn_power * 100) / last_load; - target_freq = cpu_power_to_freq(cpufreq_device, normalised_power); + target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power); - *state = cpufreq_cooling_get_level(cpu, target_freq); - if (*state == THERMAL_CSTATE_INVALID) { - dev_err_ratelimited(&cdev->device, - "Failed to convert %dKHz for cpu %d into a cdev state\n", - target_freq, cpu); - return -EINVAL; - } - - trace_thermal_power_cpu_limit(&cpufreq_device->allowed_cpus, - target_freq, *state, power); + *state = get_level(cpufreq_cdev, target_freq); + trace_thermal_power_cpu_limit(policy->related_cpus, target_freq, *state, + power); return 0; } @@ -748,7 +668,7 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table, /** * __cpufreq_cooling_register - helper function to create cpufreq cooling device * @np: a valid struct device_node to the cooling device device tree node - * @clip_cpus: cpumask of cpus where the frequency constraints will happen. + * @policy: cpufreq policy * Normally this should be same as cpufreq policy->related_cpus. * @capacitance: dynamic power coefficient for these cpus * @plat_static_func: function to calculate the static power consumed by these @@ -764,102 +684,68 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table, */ static struct thermal_cooling_device * __cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, u32 capacitance, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { - struct cpufreq_policy *policy; - struct thermal_cooling_device *cool_dev; - struct cpufreq_cooling_device *cpufreq_dev; + struct thermal_cooling_device *cdev; + struct cpufreq_cooling_device *cpufreq_cdev; char dev_name[THERMAL_NAME_LENGTH]; - struct cpufreq_frequency_table *pos, *table; - cpumask_var_t temp_mask; unsigned int freq, i, num_cpus; int ret; struct thermal_cooling_device_ops *cooling_ops; bool first; - if (!alloc_cpumask_var(&temp_mask, GFP_KERNEL)) - return ERR_PTR(-ENOMEM); - - cpumask_and(temp_mask, clip_cpus, cpu_online_mask); - policy = cpufreq_cpu_get(cpumask_first(temp_mask)); - if (!policy) { - pr_debug("%s: CPUFreq policy not found\n", __func__); - cool_dev = ERR_PTR(-EPROBE_DEFER); - goto free_cpumask; + if (IS_ERR_OR_NULL(policy)) { + pr_err("%s: cpufreq policy isn't valid: %p", __func__, policy); + return ERR_PTR(-EINVAL); } - table = policy->freq_table; - if (!table) { - pr_debug("%s: CPUFreq table not found\n", __func__); - cool_dev = ERR_PTR(-ENODEV); - goto put_policy; + i = cpufreq_table_count_valid_entries(policy); + if (!i) { + pr_debug("%s: CPUFreq table not found or has no valid entries\n", + __func__); + return ERR_PTR(-ENODEV); } - cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL); - if (!cpufreq_dev) { - cool_dev = ERR_PTR(-ENOMEM); - goto put_policy; - } + cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL); + if (!cpufreq_cdev) + return ERR_PTR(-ENOMEM); - num_cpus = cpumask_weight(clip_cpus); - cpufreq_dev->time_in_idle = kcalloc(num_cpus, - sizeof(*cpufreq_dev->time_in_idle), - GFP_KERNEL); - if (!cpufreq_dev->time_in_idle) { - cool_dev = ERR_PTR(-ENOMEM); + cpufreq_cdev->policy = policy; + num_cpus = cpumask_weight(policy->related_cpus); + cpufreq_cdev->idle_time = kcalloc(num_cpus, + sizeof(*cpufreq_cdev->idle_time), + GFP_KERNEL); + if (!cpufreq_cdev->idle_time) { + cdev = ERR_PTR(-ENOMEM); goto free_cdev; } - cpufreq_dev->time_in_idle_timestamp = - kcalloc(num_cpus, sizeof(*cpufreq_dev->time_in_idle_timestamp), - GFP_KERNEL); - if (!cpufreq_dev->time_in_idle_timestamp) { - cool_dev = ERR_PTR(-ENOMEM); - goto free_time_in_idle; - } - - /* Find max levels */ - cpufreq_for_each_valid_entry(pos, table) - cpufreq_dev->max_level++; - - cpufreq_dev->freq_table = kmalloc(sizeof(*cpufreq_dev->freq_table) * - cpufreq_dev->max_level, GFP_KERNEL); - if (!cpufreq_dev->freq_table) { - cool_dev = ERR_PTR(-ENOMEM); - goto free_time_in_idle_timestamp; - } - /* max_level is an index, not a counter */ - cpufreq_dev->max_level--; - - cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus); - - if (capacitance) { - cpufreq_dev->plat_get_static_power = plat_static_func; - - ret = build_dyn_power_table(cpufreq_dev, capacitance); - if (ret) { - cool_dev = ERR_PTR(ret); - goto free_table; - } - - cooling_ops = &cpufreq_power_cooling_ops; - } else { - cooling_ops = &cpufreq_cooling_ops; + cpufreq_cdev->max_level = i - 1; + + cpufreq_cdev->freq_table = kmalloc_array(i, + sizeof(*cpufreq_cdev->freq_table), + GFP_KERNEL); + if (!cpufreq_cdev->freq_table) { + cdev = ERR_PTR(-ENOMEM); + goto free_idle_time; } ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL); if (ret < 0) { - cool_dev = ERR_PTR(ret); - goto free_power_table; + cdev = ERR_PTR(ret); + goto free_table; } - cpufreq_dev->id = ret; + cpufreq_cdev->id = ret; + + snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d", + cpufreq_cdev->id); /* Fill freq-table in descending order of frequencies */ - for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) { - freq = find_next_max(table, freq); - cpufreq_dev->freq_table[i] = freq; + for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) { + freq = find_next_max(policy->freq_table, freq); + cpufreq_cdev->freq_table[i].frequency = freq; /* Warn for duplicate entries */ if (!freq) @@ -868,51 +754,54 @@ __cpufreq_cooling_register(struct device_node *np, pr_debug("%s: freq:%u KHz\n", __func__, freq); } - snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d", - cpufreq_dev->id); + if (capacitance) { + cpufreq_cdev->plat_get_static_power = plat_static_func; + + ret = update_freq_table(cpufreq_cdev, capacitance); + if (ret) { + cdev = ERR_PTR(ret); + goto remove_ida; + } + + cooling_ops = &cpufreq_power_cooling_ops; + } else { + cooling_ops = &cpufreq_cooling_ops; + } - cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev, - cooling_ops); - if (IS_ERR(cool_dev)) + cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev, + cooling_ops); + if (IS_ERR(cdev)) goto remove_ida; - cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0]; - cpufreq_dev->cool_dev = cool_dev; + cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0].frequency; + cpufreq_cdev->cdev = cdev; mutex_lock(&cooling_list_lock); /* Register the notifier for first cpufreq cooling device */ - first = list_empty(&cpufreq_dev_list); - list_add(&cpufreq_dev->node, &cpufreq_dev_list); + first = list_empty(&cpufreq_cdev_list); + list_add(&cpufreq_cdev->node, &cpufreq_cdev_list); mutex_unlock(&cooling_list_lock); if (first) cpufreq_register_notifier(&thermal_cpufreq_notifier_block, CPUFREQ_POLICY_NOTIFIER); - goto put_policy; + return cdev; remove_ida: - ida_simple_remove(&cpufreq_ida, cpufreq_dev->id); -free_power_table: - kfree(cpufreq_dev->dyn_power_table); + ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); free_table: - kfree(cpufreq_dev->freq_table); -free_time_in_idle_timestamp: - kfree(cpufreq_dev->time_in_idle_timestamp); -free_time_in_idle: - kfree(cpufreq_dev->time_in_idle); + kfree(cpufreq_cdev->freq_table); +free_idle_time: + kfree(cpufreq_cdev->idle_time); free_cdev: - kfree(cpufreq_dev); -put_policy: - cpufreq_cpu_put(policy); -free_cpumask: - free_cpumask_var(temp_mask); - return cool_dev; + kfree(cpufreq_cdev); + return cdev; } /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen. + * @policy: cpufreq policy * * This interface function registers the cpufreq cooling device with the name * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq @@ -922,16 +811,16 @@ free_cpumask: * on failure, it returns a corresponding ERR_PTR(). */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { - return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL); + return __cpufreq_cooling_register(NULL, policy, 0, NULL); } EXPORT_SYMBOL_GPL(cpufreq_cooling_register); /** * of_cpufreq_cooling_register - function to create cpufreq cooling device. * @np: a valid struct device_node to the cooling device device tree node - * @clip_cpus: cpumask of cpus where the frequency constraints will happen. + * @policy: cpufreq policy * * This interface function registers the cpufreq cooling device with the name * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq @@ -943,18 +832,18 @@ EXPORT_SYMBOL_GPL(cpufreq_cooling_register); */ struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { if (!np) return ERR_PTR(-EINVAL); - return __cpufreq_cooling_register(np, clip_cpus, 0, NULL); + return __cpufreq_cooling_register(np, policy, 0, NULL); } EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register); /** * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy * @capacitance: dynamic power coefficient for these cpus * @plat_static_func: function to calculate the static power consumed by these * cpus (optional) @@ -974,10 +863,10 @@ EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register); * on failure, it returns a corresponding ERR_PTR(). */ struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { - return __cpufreq_cooling_register(NULL, clip_cpus, capacitance, + return __cpufreq_cooling_register(NULL, policy, capacitance, plat_static_func); } EXPORT_SYMBOL(cpufreq_power_cooling_register); @@ -985,7 +874,7 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register); /** * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions * @np: a valid struct device_node to the cooling device device tree node - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy * @capacitance: dynamic power coefficient for these cpus * @plat_static_func: function to calculate the static power consumed by these * cpus (optional) @@ -1007,14 +896,14 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register); */ struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { if (!np) return ERR_PTR(-EINVAL); - return __cpufreq_cooling_register(np, clip_cpus, capacitance, + return __cpufreq_cooling_register(np, policy, capacitance, plat_static_func); } EXPORT_SYMBOL(of_cpufreq_power_cooling_register); @@ -1027,30 +916,28 @@ EXPORT_SYMBOL(of_cpufreq_power_cooling_register); */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { - struct cpufreq_cooling_device *cpufreq_dev; + struct cpufreq_cooling_device *cpufreq_cdev; bool last; if (!cdev) return; - cpufreq_dev = cdev->devdata; + cpufreq_cdev = cdev->devdata; mutex_lock(&cooling_list_lock); - list_del(&cpufreq_dev->node); + list_del(&cpufreq_cdev->node); /* Unregister the notifier for the last cpufreq cooling device */ - last = list_empty(&cpufreq_dev_list); + last = list_empty(&cpufreq_cdev_list); mutex_unlock(&cooling_list_lock); if (last) cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block, CPUFREQ_POLICY_NOTIFIER); - thermal_cooling_device_unregister(cpufreq_dev->cool_dev); - ida_simple_remove(&cpufreq_ida, cpufreq_dev->id); - kfree(cpufreq_dev->dyn_power_table); - kfree(cpufreq_dev->time_in_idle_timestamp); - kfree(cpufreq_dev->time_in_idle); - kfree(cpufreq_dev->freq_table); - kfree(cpufreq_dev); + thermal_cooling_device_unregister(cpufreq_cdev->cdev); + ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); + kfree(cpufreq_cdev->idle_time); + kfree(cpufreq_cdev->freq_table); + kfree(cpufreq_cdev); } EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister); diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c index 68bd1b569118..d3469fbc5207 100644 --- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -71,6 +71,7 @@ static long get_target_state(struct thermal_zone_device *tz, /** * fair_share_throttle - throttles devices associated with the given zone * @tz - thermal_zone_device + * @trip - trip point index * * Throttling Logic: This uses three parameters to calculate the new * throttle state of the cooling devices associated with the given zone. diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index f6429666a1cf..9c3ce341eb97 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -397,8 +397,11 @@ static int hisi_thermal_suspend(struct device *dev) static int hisi_thermal_resume(struct device *dev) { struct hisi_thermal_data *data = dev_get_drvdata(dev); + int ret; - clk_prepare_enable(data->clk); + ret = clk_prepare_enable(data->clk); + if (ret) + return ret; data->irq_enabled = true; hisi_thermal_enable_bind_irq_sensor(data); diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index fb648a45754e..4798b4b1fd77 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -8,6 +8,7 @@ */ #include <linux/clk.h> +#include <linux/cpufreq.h> #include <linux/cpu_cooling.h> #include <linux/delay.h> #include <linux/device.h> @@ -88,6 +89,7 @@ static struct thermal_soc_data thermal_imx6sx_data = { }; struct imx_thermal_data { + struct cpufreq_policy *policy; struct thermal_zone_device *tz; struct thermal_cooling_device *cdev; enum thermal_device_mode mode; @@ -525,13 +527,18 @@ static int imx_thermal_probe(struct platform_device *pdev) regmap_write(map, MISC0 + REG_SET, MISC0_REFTOP_SELBIASOFF); regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN); - data->cdev = cpufreq_cooling_register(cpu_present_mask); + data->policy = cpufreq_cpu_get(0); + if (!data->policy) { + pr_debug("%s: CPUFreq policy not found\n", __func__); + return -EPROBE_DEFER; + } + + data->cdev = cpufreq_cooling_register(data->policy); if (IS_ERR(data->cdev)) { ret = PTR_ERR(data->cdev); - if (ret != -EPROBE_DEFER) - dev_err(&pdev->dev, - "failed to register cpufreq cooling device: %d\n", - ret); + dev_err(&pdev->dev, + "failed to register cpufreq cooling device: %d\n", ret); + cpufreq_cpu_put(data->policy); return ret; } @@ -542,6 +549,7 @@ static int imx_thermal_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to get thermal clk: %d\n", ret); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -556,6 +564,7 @@ static int imx_thermal_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -571,6 +580,7 @@ static int imx_thermal_probe(struct platform_device *pdev) "failed to register thermal zone device %d\n", ret); clk_disable_unprepare(data->thermal_clk); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -599,6 +609,7 @@ static int imx_thermal_probe(struct platform_device *pdev) clk_disable_unprepare(data->thermal_clk); thermal_zone_device_unregister(data->tz); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -620,6 +631,7 @@ static int imx_thermal_remove(struct platform_device *pdev) thermal_zone_device_unregister(data->tz); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return 0; } @@ -648,8 +660,11 @@ static int imx_thermal_resume(struct device *dev) { struct imx_thermal_data *data = dev_get_drvdata(dev); struct regmap *map = data->tempmon; + int ret; - clk_prepare_enable(data->thermal_clk); + ret = clk_prepare_enable(data->thermal_clk); + if (ret) + return ret; /* Enabled thermal sensor after resume */ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN); regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP); diff --git a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c index 2c2ec7666eb1..51ceb80212a7 100644 --- a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c +++ b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c @@ -62,8 +62,8 @@ static int acpi_thermal_rel_release(struct inode *inode, struct file *file) * acpi_parse_trt - Thermal Relationship Table _TRT for passive cooling * * @handle: ACPI handle of the device contains _TRT - * @art_count: the number of valid entries resulted from parsing _TRT - * @artp: pointer to pointer of array of art entries in parsing result + * @trt_count: the number of valid entries resulted from parsing _TRT + * @trtp: pointer to pointer of array of _TRT entries in parsing result * @create_dev: whether to create platform devices for target and source * */ @@ -208,7 +208,7 @@ int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp, if (art->target) { result = acpi_bus_get_device(art->target, &adev); if (result) - pr_warn("Failed to get source ACPI device\n"); + pr_warn("Failed to get target ACPI device\n"); } } diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c index c4890c9437eb..8a7f24dd9315 100644 --- a/drivers/thermal/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/int340x_thermal/int3403_thermal.c @@ -238,8 +238,16 @@ static int int3403_add(struct platform_device *pdev) status = acpi_evaluate_integer(priv->adev->handle, "PTYP", NULL, &priv->type); if (ACPI_FAILURE(status)) { - result = -EINVAL; - goto err; + unsigned long long tmp; + + status = acpi_evaluate_integer(priv->adev->handle, "_TMP", + NULL, &tmp); + if (ACPI_FAILURE(status)) { + result = -EINVAL; + goto err; + } else { + priv->type = INT3403_TYPE_SENSOR; + } } platform_set_drvdata(pdev, priv); diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index bcef2e7c4ec9..be95826631b7 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -186,8 +186,7 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) /** * step_wise_throttle - throttles devices associated with the given zone * @tz - thermal_zone_device - * @trip - the trip point - * @trip_type - type of the trip point + * @trip - trip point index * * Throttling Logic: This uses the trend of the thermal zone to throttle. * If the thermal zone is 'heating up' this throttles all the cooling diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index 02790f69e26c..c211a8e4a210 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -28,6 +28,7 @@ #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/thermal.h> +#include <linux/cpufreq.h> #include <linux/cpumask.h> #include <linux/cpu_cooling.h> #include <linux/of.h> @@ -37,6 +38,7 @@ /* common data structures */ struct ti_thermal_data { + struct cpufreq_policy *policy; struct thermal_zone_device *ti_thermal; struct thermal_zone_device *pcb_tz; struct thermal_cooling_device *cool_dev; @@ -247,15 +249,19 @@ int ti_thermal_register_cpu_cooling(struct ti_bandgap *bgp, int id) if (!data) return -EINVAL; + data->policy = cpufreq_cpu_get(0); + if (!data->policy) { + pr_debug("%s: CPUFreq policy not found\n", __func__); + return -EPROBE_DEFER; + } + /* Register cooling device */ - data->cool_dev = cpufreq_cooling_register(cpu_present_mask); + data->cool_dev = cpufreq_cooling_register(data->policy); if (IS_ERR(data->cool_dev)) { int ret = PTR_ERR(data->cool_dev); - - if (ret != -EPROBE_DEFER) - dev_err(bgp->dev, - "Failed to register cpu cooling device %d\n", - ret); + dev_err(bgp->dev, "Failed to register cpu cooling device %d\n", + ret); + cpufreq_cpu_put(data->policy); return ret; } @@ -270,8 +276,10 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id) data = ti_bandgap_get_sensor_data(bgp, id); - if (data) + if (data) { cpufreq_cooling_unregister(data->cool_dev); + cpufreq_cpu_put(data->policy); + } return 0; } diff --git a/drivers/thermal/user_space.c b/drivers/thermal/user_space.c index c908150c268d..8e92a06ef48a 100644 --- a/drivers/thermal/user_space.c +++ b/drivers/thermal/user_space.c @@ -24,12 +24,13 @@ #include <linux/thermal.h> #include <linux/slab.h> + #include "thermal_core.h" /** * notify_user_space - Notifies user space about thermal events * @tz - thermal_zone_device - * @trip - Trip point index + * @trip - trip point index * * This function notifies the user space through UEvents. */ diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index c202930086ed..8fb89ddc6cc7 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -33,6 +33,7 @@ #include <linux/parser.h> #include <linux/idr.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> @@ -82,6 +83,13 @@ static const match_table_t tokens = { {Opt_err, NULL} }; +static const char *const v9fs_cache_modes[nr__p9_cache_modes] = { + [CACHE_NONE] = "none", + [CACHE_MMAP] = "mmap", + [CACHE_LOOSE] = "loose", + [CACHE_FSCACHE] = "fscache", +}; + /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { @@ -104,6 +112,58 @@ static int get_cache_mode(char *s) return version; } +/* + * Display the mount options in /proc/mounts. + */ +int v9fs_show_options(struct seq_file *m, struct dentry *root) +{ + struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; + + if (v9ses->debug) + seq_printf(m, ",debug=%x", v9ses->debug); + if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) + seq_printf(m, ",dfltuid=%u", + from_kuid_munged(&init_user_ns, v9ses->dfltuid)); + if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID)) + seq_printf(m, ",dfltgid=%u", + from_kgid_munged(&init_user_ns, v9ses->dfltgid)); + if (v9ses->afid != ~0) + seq_printf(m, ",afid=%u", v9ses->afid); + if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0) + seq_printf(m, ",uname=%s", v9ses->uname); + if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0) + seq_printf(m, ",aname=%s", v9ses->aname); + if (v9ses->nodev) + seq_puts(m, ",nodevmap"); + if (v9ses->cache) + seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]); +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE) + seq_printf(m, ",cachetag=%s", v9ses->cachetag); +#endif + + switch (v9ses->flags & V9FS_ACCESS_MASK) { + case V9FS_ACCESS_USER: + seq_puts(m, ",access=user"); + break; + case V9FS_ACCESS_ANY: + seq_puts(m, ",access=any"); + break; + case V9FS_ACCESS_CLIENT: + seq_puts(m, ",access=client"); + break; + case V9FS_ACCESS_SINGLE: + seq_printf(m, ",access=%u", + from_kuid_munged(&init_user_ns, v9ses->uid)); + break; + } + + if (v9ses->flags & V9FS_POSIX_ACL) + seq_puts(m, ",posixacl"); + + return p9_show_client_options(m, v9ses->clnt); +} + /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information @@ -230,6 +290,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE + kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); #endif break; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 76eaf49abd3a..982e017acadb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -67,6 +67,7 @@ enum p9_cache_modes { CACHE_MMAP, CACHE_LOOSE, CACHE_FSCACHE, + nr__p9_cache_modes }; /** @@ -137,6 +138,8 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) return container_of(inode, struct v9fs_inode, vfs_inode); } +extern int v9fs_show_options(struct seq_file *m, struct dentry *root); + struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *, char *); extern void v9fs_session_close(struct v9fs_session_info *v9ses); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index a0965fb587a5..8b75463cb211 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -33,7 +33,6 @@ #include <linux/string.h> #include <linux/inet.h> #include <linux/pagemap.h> -#include <linux/seq_file.h> #include <linux/mount.h> #include <linux/idr.h> #include <linux/sched.h> @@ -104,7 +103,6 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_flags |= MS_POSIXACL; #endif - save_mount_options(sb, data); return 0; } @@ -349,7 +347,7 @@ static const struct super_operations v9fs_super_ops = { .destroy_inode = v9fs_destroy_inode, .statfs = simple_statfs, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode, }; @@ -360,7 +358,7 @@ static const struct super_operations v9fs_super_ops_dotl = { .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode_dotl, }; diff --git a/fs/affs/super.c b/fs/affs/super.c index c2c27a8f128e..7bf47a41cb4f 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -20,9 +20,11 @@ #include <linux/slab.h> #include <linux/writeback.h> #include <linux/blkdev.h> +#include <linux/seq_file.h> #include "affs.h" static int affs_statfs(struct dentry *dentry, struct kstatfs *buf); +static int affs_show_options(struct seq_file *m, struct dentry *root); static int affs_remount (struct super_block *sb, int *flags, char *data); static void @@ -159,7 +161,7 @@ static const struct super_operations affs_sops = { .sync_fs = affs_sync_fs, .statfs = affs_statfs, .remount_fs = affs_remount, - .show_options = generic_show_options, + .show_options = affs_show_options, }; enum { @@ -293,6 +295,40 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, return 1; } +static int affs_show_options(struct seq_file *m, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct affs_sb_info *sbi = AFFS_SB(sb); + + if (sb->s_blocksize) + seq_printf(m, ",bs=%lu", sb->s_blocksize); + if (affs_test_opt(sbi->s_flags, SF_SETMODE)) + seq_printf(m, ",mode=%o", sbi->s_mode); + if (affs_test_opt(sbi->s_flags, SF_MUFS)) + seq_puts(m, ",mufs"); + if (affs_test_opt(sbi->s_flags, SF_NO_TRUNCATE)) + seq_puts(m, ",nofilenametruncate"); + if (affs_test_opt(sbi->s_flags, SF_PREFIX)) + seq_printf(m, ",prefix=%s", sbi->s_prefix); + if (affs_test_opt(sbi->s_flags, SF_IMMUTABLE)) + seq_puts(m, ",protect"); + if (sbi->s_reserved != 2) + seq_printf(m, ",reserved=%u", sbi->s_reserved); + if (sbi->s_root_block != (sbi->s_reserved + sbi->s_partition_size - 1) / 2) + seq_printf(m, ",root=%u", sbi->s_root_block); + if (affs_test_opt(sbi->s_flags, SF_SETGID)) + seq_printf(m, ",setgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + if (affs_test_opt(sbi->s_flags, SF_SETUID)) + seq_printf(m, ",setuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (affs_test_opt(sbi->s_flags, SF_VERBOSE)) + seq_puts(m, ",verbose"); + if (sbi->s_volume[0]) + seq_printf(m, ",volume=%s", sbi->s_volume); + return 0; +} + /* This function definitely needs to be split up. Some fine day I'll * hopefully have the guts to do so. Until then: sorry for the mess. */ @@ -316,8 +352,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) u8 sig[4]; int ret; - save_mount_options(sb, data); - pr_debug("read_super(%s)\n", data ? (const char *)data : "no options"); sb->s_magic = AFFS_SUPER_MAGIC; @@ -548,8 +582,6 @@ affs_remount(struct super_block *sb, int *flags, char *data) } flush_delayed_work(&sbi->sb_work); - if (new_opts) - replace_mount_options(sb, new_opts); sbi->s_flags = mount_flags; sbi->s_mode = mode; diff --git a/fs/afs/super.c b/fs/afs/super.c index 67680c2d96cf..689173c0a682 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -37,6 +37,8 @@ static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); +static int afs_show_devname(struct seq_file *m, struct dentry *root); +static int afs_show_options(struct seq_file *m, struct dentry *root); struct file_system_type afs_fs_type = { .owner = THIS_MODULE, @@ -53,7 +55,8 @@ static const struct super_operations afs_super_ops = { .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .evict_inode = afs_evict_inode, - .show_options = generic_show_options, + .show_devname = afs_show_devname, + .show_options = afs_show_options, }; static struct kmem_cache *afs_inode_cachep; @@ -136,6 +139,45 @@ void __exit afs_fs_exit(void) } /* + * Display the mount device name in /proc/mounts. + */ +static int afs_show_devname(struct seq_file *m, struct dentry *root) +{ + struct afs_super_info *as = root->d_sb->s_fs_info; + struct afs_volume *volume = as->volume; + struct afs_cell *cell = volume->cell; + const char *suf = ""; + char pref = '%'; + + switch (volume->type) { + case AFSVL_RWVOL: + break; + case AFSVL_ROVOL: + pref = '#'; + if (volume->type_force) + suf = ".readonly"; + break; + case AFSVL_BACKVOL: + pref = '#'; + suf = ".backup"; + break; + } + + seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->vlocation->vldb.name, suf); + return 0; +} + +/* + * Display the mount options in /proc/mounts. + */ +static int afs_show_options(struct seq_file *m, struct dentry *root) +{ + if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) + seq_puts(m, "autocell"); + return 0; +} + +/* * parse the mount options * - this function has been shamelessly adapted from the ext3 fs which * shamelessly adapted it from the msdos fs @@ -427,7 +469,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, deactivate_locked_super(sb); goto error; } - save_mount_options(sb, new_opts); sb->s_flags |= MS_ACTIVE; } else { _debug("reuse"); diff --git a/fs/befs/btree.c b/fs/befs/btree.c index d509887c580c..1b7e0f7128d6 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -120,18 +120,15 @@ static int befs_compare_strings(const void *key1, int keylen1, const void *key2, int keylen2); /** - * befs_bt_read_super - read in btree superblock convert to cpu byteorder - * @sb: Filesystem superblock - * @ds: Datastream to read from - * @sup: Buffer in which to place the btree superblock + * befs_bt_read_super() - read in btree superblock convert to cpu byteorder + * @sb: Filesystem superblock + * @ds: Datastream to read from + * @sup: Buffer in which to place the btree superblock * * Calls befs_read_datastream to read in the btree superblock and * makes sure it is in cpu byteorder, byteswapping if necessary. - * - * On success, returns BEFS_OK and *@sup contains the btree superblock, - * in cpu byte order. - * - * On failure, BEFS_ERR is returned. + * Return: BEFS_OK on success and if *@sup contains the btree superblock in cpu + * byte order. Otherwise return BEFS_ERR on error. */ static int befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds, diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 63e7c4760bfb..4a4a5a366158 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/cred.h> #include <linux/exportfs.h> +#include <linux/seq_file.h> #include "befs.h" #include "btree.h" @@ -53,6 +54,7 @@ static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, static void befs_put_super(struct super_block *); static int befs_remount(struct super_block *, int *, char *); static int befs_statfs(struct dentry *, struct kstatfs *); +static int befs_show_options(struct seq_file *, struct dentry *); static int parse_options(char *, struct befs_mount_options *); static struct dentry *befs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); @@ -66,7 +68,7 @@ static const struct super_operations befs_sops = { .put_super = befs_put_super, /* uninit super */ .statfs = befs_statfs, /* statfs */ .remount_fs = befs_remount, - .show_options = generic_show_options, + .show_options = befs_show_options, }; /* slab cache for befs_inode_info objects */ @@ -771,6 +773,24 @@ parse_options(char *options, struct befs_mount_options *opts) return 1; } +static int befs_show_options(struct seq_file *m, struct dentry *root) +{ + struct befs_sb_info *befs_sb = BEFS_SB(root->d_sb); + struct befs_mount_options *opts = &befs_sb->mount_opts; + + if (!uid_eq(opts->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->uid)); + if (!gid_eq(opts->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->gid)); + if (opts->iocharset) + seq_printf(m, ",charset=%s", opts->iocharset); + if (opts->debug) + seq_puts(m, ",debug"); + return 0; +} + /* This function has the responsibiltiy of getting the * filesystem ready for unmounting. * Basically, we free everything that we allocated in @@ -804,8 +824,6 @@ befs_fill_super(struct super_block *sb, void *data, int silent) const off_t x86_sb_off = 512; int blocksize; - save_mount_options(sb, data); - sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL); if (sb->s_fs_info == NULL) goto unacquire_none; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 2edcefc0a294..69ec23daa25e 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -422,9 +422,9 @@ static int load_flat_file(struct linux_binprm *bprm, { struct flat_hdr *hdr; unsigned long textpos, datapos, realdatastart; - unsigned long text_len, data_len, bss_len, stack_len, full_data, flags; + u32 text_len, data_len, bss_len, stack_len, full_data, flags; unsigned long len, memp, memp_size, extra, rlim; - unsigned long __user *reloc, *rp; + u32 __user *reloc, *rp; struct inode *inode; int i, rev, relocs; loff_t fpos; @@ -596,13 +596,13 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - reloc = (unsigned long __user *) + reloc = (u32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = realdatastart; memp_size = len; } else { - len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); + len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32); len = PAGE_ALIGN(len); textpos = vm_mmap(NULL, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); @@ -618,10 +618,10 @@ static int load_flat_file(struct linux_binprm *bprm, realdatastart = textpos + ntohl(hdr->data_start); datapos = ALIGN(realdatastart + - MAX_SHARED_LIBS * sizeof(unsigned long), + MAX_SHARED_LIBS * sizeof(u32), FLAT_DATA_ALIGN); - reloc = (unsigned long __user *) + reloc = (u32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = textpos; memp_size = len; @@ -694,7 +694,7 @@ static int load_flat_file(struct linux_binprm *bprm, ret = result; pr_err("Unable to read code+data+bss, errno %d\n", ret); vm_munmap(textpos, text_len + data_len + extra + - MAX_SHARED_LIBS * sizeof(unsigned long)); + MAX_SHARED_LIBS * sizeof(u32)); goto err; } } @@ -754,8 +754,8 @@ static int load_flat_file(struct linux_binprm *bprm, * image. */ if (flags & FLAT_FLAG_GOTPIC) { - for (rp = (unsigned long __user *)datapos; ; rp++) { - unsigned long addr, rp_val; + for (rp = (u32 __user *)datapos; ; rp++) { + u32 addr, rp_val; if (get_user(rp_val, rp)) return -EFAULT; if (rp_val == 0xffffffff) @@ -784,9 +784,9 @@ static int load_flat_file(struct linux_binprm *bprm, * __start to address 4 so that is okay). */ if (rev > OLD_FLAT_VERSION) { - unsigned long __maybe_unused persistent = 0; + u32 __maybe_unused persistent = 0; for (i = 0; i < relocs; i++) { - unsigned long addr, relval; + u32 addr, relval; /* * Get the address of the pointer to be @@ -799,15 +799,18 @@ static int load_flat_file(struct linux_binprm *bprm, if (flat_set_persistent(relval, &persistent)) continue; addr = flat_get_relocate_addr(relval); - rp = (unsigned long __user *)calc_reloc(addr, libinfo, id, 1); - if (rp == (unsigned long __user *)RELOC_FAILED) { + rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1); + if (rp == (u32 __user *)RELOC_FAILED) { ret = -ENOEXEC; goto err; } /* Get the pointer's value. */ - addr = flat_get_addr_from_rp(rp, relval, flags, - &persistent); + ret = flat_get_addr_from_rp(rp, relval, flags, + &addr, &persistent); + if (unlikely(ret)) + goto err; + if (addr != 0) { /* * Do the relocation. PIC relocs in the data section are @@ -822,12 +825,14 @@ static int load_flat_file(struct linux_binprm *bprm, } /* Write back the relocated pointer. */ - flat_put_addr_at_rp(rp, addr, relval); + ret = flat_put_addr_at_rp(rp, addr, relval); + if (unlikely(ret)) + goto err; } } } else { for (i = 0; i < relocs; i++) { - unsigned long relval; + u32 relval; if (get_user(relval, reloc + i)) return -EFAULT; relval = ntohl(relval); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 2c0b7b57fcd5..d2ef9ac2a630 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -152,6 +152,7 @@ csum_failed: * we have verified the checksum already, set page * checked so the end_io handlers know about it */ + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, cb->orig_bio, i) SetPageChecked(bvec->bv_page); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 086dcbadce09..080e2ebb8aa0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -964,6 +964,7 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) struct btrfs_root *root; int i, ret = 0; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 556484cf5d93..0aff9b278c19 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2258,7 +2258,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, return 0; } -int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, +bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, int failed_mirror) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -2274,7 +2274,7 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, btrfs_debug(fs_info, "Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d", num_copies, failrec->this_mirror, failed_mirror); - return 0; + return false; } /* @@ -2315,10 +2315,10 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, btrfs_debug(fs_info, "Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d", num_copies, failrec->this_mirror, failed_mirror); - return 0; + return false; } - return 1; + return true; } @@ -2382,8 +2382,8 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, if (ret) return ret; - ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror); - if (!ret) { + if (!btrfs_check_repairable(inode, failed_bio, failrec, + failed_mirror)) { free_io_failure(failure_tree, tree, failrec); return -EIO; } @@ -2396,10 +2396,6 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, start - page_offset(page), (int)phy_offset, failed_bio->bi_end_io, NULL); - if (!bio) { - free_io_failure(failure_tree, tree, failrec); - return -EIO; - } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); btrfs_debug(btrfs_sb(inode->i_sb), @@ -2456,6 +2452,7 @@ static void end_bio_extent_writepage(struct bio *bio) u64 end; int i; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; @@ -2526,6 +2523,7 @@ static void end_bio_extent_readpage(struct bio *bio) int ret; int i; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; @@ -3680,6 +3678,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) struct extent_buffer *eb; int i, done; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 3fb8513bf02e..4f030912f3ef 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -539,8 +539,8 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end); int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, struct io_failure_record **failrec_ret); -int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, - struct io_failure_record *failrec, int fail_mirror); +bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, + struct io_failure_record *failrec, int fail_mirror); struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, struct page *page, int pg_offset, int icsum, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 06dea7c89bbd..95c212037095 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8016,10 +8016,6 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, isector >>= inode->i_sb->s_blocksize_bits; bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page, pgoff, isector, repair_endio, repair_arg); - if (!bio) { - free_io_failure(failure_tree, io_tree, failrec); - return -EIO; - } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); btrfs_debug(BTRFS_I(inode)->root->fs_info, @@ -8059,6 +8055,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); done->uptodate = 1; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree, io_tree, done->start, bvec->bv_page, @@ -8150,6 +8147,7 @@ static void btrfs_retry_endio(struct bio *bio) io_tree = &BTRFS_I(inode)->io_tree; failure_tree = &BTRFS_I(inode)->io_failure_tree; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page, bvec->bv_offset, done->start, diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 6f845d219cd6..208638384cd2 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1136,20 +1136,27 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) static void index_rbio_pages(struct btrfs_raid_bio *rbio) { struct bio *bio; - struct bio_vec *bvec; u64 start; unsigned long stripe_offset; unsigned long page_index; - int i; spin_lock_irq(&rbio->bio_list_lock); bio_list_for_each(bio, &rbio->bio_list) { + struct bio_vec bvec; + struct bvec_iter iter; + int i = 0; + start = (u64)bio->bi_iter.bi_sector << 9; stripe_offset = start - rbio->bbio->raid_map[0]; page_index = stripe_offset >> PAGE_SHIFT; - bio_for_each_segment_all(bvec, bio, i) - rbio->bio_pages[page_index + i] = bvec->bv_page; + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_io_bio(bio)->iter; + + bio_for_each_segment(bvec, bio, iter) { + rbio->bio_pages[page_index + i] = bvec.bv_page; + i++; + } } spin_unlock_irq(&rbio->bio_list_lock); } @@ -1423,11 +1430,14 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio, */ static void set_bio_pages_uptodate(struct bio *bio) { - struct bio_vec *bvec; - int i; + struct bio_vec bvec; + struct bvec_iter iter; + + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_io_bio(bio)->iter; - bio_for_each_segment_all(bvec, bio, i) - SetPageUptodate(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) + SetPageUptodate(bvec.bv_page); } /* diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e937c10b8287..b082210df9c8 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1856,7 +1856,7 @@ out: */ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, const char *name, int name_len, - u64 *who_ino, u64 *who_gen) + u64 *who_ino, u64 *who_gen, u64 *who_mode) { int ret = 0; u64 gen; @@ -1905,7 +1905,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, if (other_inode > sctx->send_progress || is_waiting_for_move(sctx, other_inode)) { ret = get_inode_info(sctx->parent_root, other_inode, NULL, - who_gen, NULL, NULL, NULL, NULL); + who_gen, who_mode, NULL, NULL, NULL); if (ret < 0) goto out; @@ -3683,6 +3683,36 @@ out: return ret; } +static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) +{ + int ret; + struct fs_path *new_path; + + /* + * Our reference's name member points to its full_path member string, so + * we use here a new path. + */ + new_path = fs_path_alloc(); + if (!new_path) + return -ENOMEM; + + ret = get_cur_path(sctx, ref->dir, ref->dir_gen, new_path); + if (ret < 0) { + fs_path_free(new_path); + return ret; + } + ret = fs_path_add(new_path, ref->name, ref->name_len); + if (ret < 0) { + fs_path_free(new_path); + return ret; + } + + fs_path_free(ref->full_path); + set_ref_path(ref, new_path); + + return 0; +} + /* * This does all the move/link/unlink/rmdir magic. */ @@ -3696,10 +3726,12 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct fs_path *valid_path = NULL; u64 ow_inode = 0; u64 ow_gen; + u64 ow_mode; int did_overwrite = 0; int is_orphan = 0; u64 last_dir_ino_rm = 0; bool can_rename = true; + bool orphanized_dir = false; bool orphanized_ancestor = false; btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino); @@ -3798,7 +3830,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) */ ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen, cur->name, cur->name_len, - &ow_inode, &ow_gen); + &ow_inode, &ow_gen, &ow_mode); if (ret < 0) goto out; if (ret) { @@ -3815,6 +3847,8 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) cur->full_path); if (ret < 0) goto out; + if (S_ISDIR(ow_mode)) + orphanized_dir = true; /* * If ow_inode has its rename operation delayed @@ -3920,6 +3954,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (ret < 0) goto out; } else { + /* + * We might have previously orphanized an inode + * which is an ancestor of our current inode, + * so our reference's full path, which was + * computed before any such orphanizations, must + * be updated. + */ + if (orphanized_dir) { + ret = update_ref_path(sctx, cur); + if (ret < 0) + goto out; + } ret = send_link(sctx, cur->full_path, valid_path); if (ret < 0) @@ -3990,34 +4036,9 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) * ancestor inode. */ if (orphanized_ancestor) { - struct fs_path *new_path; - - /* - * Our reference's name member points to - * its full_path member string, so we - * use here a new path. - */ - new_path = fs_path_alloc(); - if (!new_path) { - ret = -ENOMEM; - goto out; - } - ret = get_cur_path(sctx, cur->dir, - cur->dir_gen, - new_path); - if (ret < 0) { - fs_path_free(new_path); - goto out; - } - ret = fs_path_add(new_path, - cur->name, - cur->name_len); - if (ret < 0) { - fs_path_free(new_path); + ret = update_ref_path(sctx, cur); + if (ret < 0) goto out; - } - fs_path_free(cur->full_path); - set_ref_path(cur, new_path); } ret = send_unlink(sctx, cur->full_path); if (ret < 0) @@ -5249,15 +5270,12 @@ static int is_extent_unchanged(struct send_ctx *sctx, goto out; } - right_disknr = btrfs_file_extent_disk_bytenr(eb, ei); if (right_type == BTRFS_FILE_EXTENT_INLINE) { right_len = btrfs_file_extent_inline_len(eb, slot, ei); right_len = PAGE_ALIGN(right_len); } else { right_len = btrfs_file_extent_num_bytes(eb, ei); } - right_offset = btrfs_file_extent_offset(eb, ei); - right_gen = btrfs_file_extent_generation(eb, ei); /* * Are we at extent 8? If yes, we know the extent is changed. @@ -5282,6 +5300,10 @@ static int is_extent_unchanged(struct send_ctx *sctx, goto out; } + right_disknr = btrfs_file_extent_disk_bytenr(eb, ei); + right_offset = btrfs_file_extent_offset(eb, ei); + right_gen = btrfs_file_extent_generation(eb, ei); + left_offset_fixed = left_offset; if (key.offset < ekey->offset) { /* Fix the right offset for 2a and 7. */ diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 74e47794e63f..12540b6104b5 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1154,7 +1154,6 @@ static int btrfs_fill_super(struct super_block *sb, goto fail_close; } - save_mount_options(sb, data); cleancache_init_fs(sb); sb->s_flags |= MS_ACTIVE; return 0; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 556f480c6936..180b3356ff86 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1354,7 +1354,7 @@ init_cifs(void) spin_lock_init(&cifs_tcp_ses_lock); spin_lock_init(&GlobalMid_Lock); - get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret)); + cifs_lock_secret = get_random_u32(); if (cifs_max_pending < 2) { cifs_max_pending = 2; diff --git a/fs/dcache.c b/fs/dcache.c index 6c30be668487..f90141387f01 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -90,6 +90,11 @@ EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; +const struct qstr empty_name = QSTR_INIT("", 0); +EXPORT_SYMBOL(empty_name); +const struct qstr slash_name = QSTR_INIT("/", 1); +EXPORT_SYMBOL(slash_name); + /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try @@ -1606,8 +1611,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { - static const struct qstr anon = QSTR_INIT("/", 1); - name = &anon; + name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index a0e4e2f7e0be..c59f015f386e 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -203,8 +203,6 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent) struct debugfs_fs_info *fsi; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) { diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index d7a7c53803c1..5b68e4294faa 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -29,7 +29,6 @@ static const struct super_operations efivarfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .evict_inode = efivarfs_evict_inode, - .show_options = generic_show_options, }; static struct super_block *efivarfs_sb; diff --git a/fs/filesystems.c b/fs/filesystems.c index 8b99955e3504..a920ad2629ac 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -33,9 +33,10 @@ static struct file_system_type *file_systems; static DEFINE_RWLOCK(file_systems_lock); /* WARNING: This can be used only if we _already_ own a reference */ -void get_filesystem(struct file_system_type *fs) +struct file_system_type *get_filesystem(struct file_system_type *fs) { __module_get(fs->owner); + return fs; } void put_filesystem(struct file_system_type *fs) diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index db427658ccd9..5ee2e2f8576c 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -872,7 +872,6 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; - struct qstr name = { .name = "" }; struct timespec tv = current_time(inode); error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); @@ -896,7 +895,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, leaf->lf_sec = cpu_to_be64(tv.tv_sec); memset(leaf->lf_reserved2, 0, sizeof(leaf->lf_reserved2)); dent = (struct gfs2_dirent *)(leaf+1); - gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent); + gfs2_qstr2dirent(&empty_name, bh->b_size - sizeof(struct gfs2_leaf), dent); *pbh = bh; return leaf; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 52388611635e..28d2753be094 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -46,13 +46,13 @@ static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; struct hugetlbfs_config { - kuid_t uid; - kgid_t gid; - umode_t mode; - long max_hpages; - long nr_inodes; - struct hstate *hstate; - long min_hpages; + struct hstate *hstate; + long max_hpages; + long nr_inodes; + long min_hpages; + kuid_t uid; + kgid_t gid; + umode_t mode; }; struct hugetlbfs_inode_info { @@ -861,6 +861,46 @@ static int hugetlbfs_error_remove_page(struct address_space *mapping, return 0; } +/* + * Display the mount options in /proc/mounts. + */ +static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); + struct hugepage_subpool *spool = sbinfo->spool; + unsigned long hpage_size = huge_page_size(sbinfo->hstate); + unsigned hpage_shift = huge_page_shift(sbinfo->hstate); + char mod; + + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); + if (sbinfo->mode != 0755) + seq_printf(m, ",mode=%o", sbinfo->mode); + if (sbinfo->max_inodes != -1) + seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); + + hpage_size /= 1024; + mod = 'K'; + if (hpage_size >= 1024) { + hpage_size /= 1024; + mod = 'M'; + } + seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); + if (spool) { + if (spool->max_hpages != -1) + seq_printf(m, ",size=%llu", + (unsigned long long)spool->max_hpages << hpage_shift); + if (spool->min_hpages != -1) + seq_printf(m, ",min_size=%llu", + (unsigned long long)spool->min_hpages << hpage_shift); + } + return 0; +} + static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); @@ -1019,19 +1059,19 @@ static const struct super_operations hugetlbfs_ops = { .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, - .show_options = generic_show_options, + .show_options = hugetlbfs_show_options, }; -enum { NO_SIZE, SIZE_STD, SIZE_PERCENT }; +enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ -static long long +static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, - int val_type) + enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; @@ -1053,7 +1093,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) substring_t args[MAX_OPT_ARGS]; int option; unsigned long long max_size_opt = 0, min_size_opt = 0; - int max_val_type = NO_SIZE, min_val_type = NO_SIZE; + enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE; if (!options) return 0; @@ -1167,8 +1207,6 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) struct hugetlbfs_config config; struct hugetlbfs_sb_info *sbinfo; - save_mount_options(sb, data); - config.max_hpages = -1; /* No limit on size by default */ config.nr_inodes = -1; /* No limit on number of inodes by default */ config.uid = current_fsuid(); @@ -1189,6 +1227,10 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; sbinfo->spool = NULL; + sbinfo->uid = config.uid; + sbinfo->gid = config.gid; + sbinfo->mode = config.mode; + /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimim size) are taken diff --git a/fs/iomap.c b/fs/iomap.c index 173222863aca..039266128b7f 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -610,8 +610,8 @@ iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) loff_t length = size - offset; loff_t ret; - /* Nothing to be found beyond the end of the file. */ - if (offset >= size) + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) return -ENXIO; while (length > 0) { @@ -656,8 +656,8 @@ iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) loff_t length = size - offset; loff_t ret; - /* Nothing to be found beyond the end of the file. */ - if (offset >= size) + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) return -ENXIO; while (length > 0) { diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 020ba0936146..8cf898a59730 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -23,6 +23,7 @@ #include <linux/parser.h> #include <linux/mpage.h> #include <linux/user_namespace.h> +#include <linux/seq_file.h> #include "isofs.h" #include "zisofs.h" @@ -57,6 +58,7 @@ static void isofs_put_super(struct super_block *sb) static int isofs_read_inode(struct inode *, int relocated); static int isofs_statfs (struct dentry *, struct kstatfs *); +static int isofs_show_options(struct seq_file *, struct dentry *); static struct kmem_cache *isofs_inode_cachep; @@ -123,7 +125,7 @@ static const struct super_operations isofs_sops = { .put_super = isofs_put_super, .statfs = isofs_statfs, .remount_fs = isofs_remount, - .show_options = generic_show_options, + .show_options = isofs_show_options, }; @@ -473,6 +475,48 @@ static int parse_options(char *options, struct iso9660_options *popt) } /* + * Display the mount options in /proc/mounts. + */ +static int isofs_show_options(struct seq_file *m, struct dentry *root) +{ + struct isofs_sb_info *sbi = ISOFS_SB(root->d_sb); + + if (!sbi->s_rock) seq_puts(m, ",norock"); + else if (!sbi->s_joliet_level) seq_puts(m, ",nojoliet"); + if (sbi->s_cruft) seq_puts(m, ",cruft"); + if (sbi->s_hide) seq_puts(m, ",hide"); + if (sbi->s_nocompress) seq_puts(m, ",nocompress"); + if (sbi->s_overriderockperm) seq_puts(m, ",overriderockperm"); + if (sbi->s_showassoc) seq_puts(m, ",showassoc"); + if (sbi->s_utf8) seq_puts(m, ",utf8"); + + if (sbi->s_check) seq_printf(m, ",check=%c", sbi->s_check); + if (sbi->s_mapping) seq_printf(m, ",map=%c", sbi->s_mapping); + if (sbi->s_session != 255) seq_printf(m, ",session=%u", sbi->s_session - 1); + if (sbi->s_sbsector != -1) seq_printf(m, ",sbsector=%u", sbi->s_sbsector); + + if (root->d_sb->s_blocksize != 1024) + seq_printf(m, ",blocksize=%lu", root->d_sb->s_blocksize); + + if (sbi->s_uid_set) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (sbi->s_gid_set) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + + if (sbi->s_dmode != ISOFS_INVALID_MODE) + seq_printf(m, ",dmode=%o", sbi->s_dmode); + if (sbi->s_fmode != ISOFS_INVALID_MODE) + seq_printf(m, ",fmode=%o", sbi->s_fmode); + + if (sbi->s_nls_iocharset && + strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) + seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); + return 0; +} + +/* * look if the driver can tell the multi session redirection value * * don't change this if you don't know what you do, please! @@ -583,8 +627,6 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) int table, error = -EINVAL; unsigned int vol_desc_start; - save_mount_options(s, data); - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; @@ -605,6 +647,8 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) opt.blocksize = sb_min_blocksize(s, opt.blocksize); sbi->s_high_sierra = 0; /* default is iso9660 */ + sbi->s_session = opt.session; + sbi->s_sbsector = opt.sbsector; vol_desc_start = (opt.sbsector != -1) ? opt.sbsector : isofs_get_last_session(s,opt.session); @@ -911,6 +955,7 @@ root_found: table += 2; if (opt.check == 'r') table++; + sbi->s_check = opt.check; if (table) s->s_d_op = &isofs_dentry_ops[table - 1]; diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 0ac4c1f73fbd..133a456b0425 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -36,8 +36,11 @@ struct isofs_sb_info { unsigned long s_max_size; int s_rock_offset; /* offset of SUSP fields within SU area */ + s32 s_sbsector; unsigned char s_joliet_level; unsigned char s_mapping; + unsigned char s_check; + unsigned char s_session; unsigned int s_high_sierra:1; unsigned int s_rock:2; unsigned int s_utf8:1; diff --git a/fs/namei.c b/fs/namei.c index e0b46eb0e212..88fd38d1e3e7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3400,7 +3400,6 @@ out: struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { - static const struct qstr name = QSTR_INIT("/", 1); struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; @@ -3414,7 +3413,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; - child = d_alloc(dentry, &name); + child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; error = dir->i_op->tmpfile(dir, child, mode); diff --git a/fs/namespace.c b/fs/namespace.c index 81f934b5d571..f8893dc6a989 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1238,65 +1238,6 @@ struct vfsmount *mnt_clone_internal(const struct path *path) return &p->mnt; } -static inline void mangle(struct seq_file *m, const char *s) -{ - seq_escape(m, s, " \t\n\\"); -} - -/* - * Simple .show_options callback for filesystems which don't want to - * implement more complex mount option showing. - * - * See also save_mount_options(). - */ -int generic_show_options(struct seq_file *m, struct dentry *root) -{ - const char *options; - - rcu_read_lock(); - options = rcu_dereference(root->d_sb->s_options); - - if (options != NULL && options[0]) { - seq_putc(m, ','); - mangle(m, options); - } - rcu_read_unlock(); - - return 0; -} -EXPORT_SYMBOL(generic_show_options); - -/* - * If filesystem uses generic_show_options(), this function should be - * called from the fill_super() callback. - * - * The .remount_fs callback usually needs to be handled in a special - * way, to make sure, that previous options are not overwritten if the - * remount fails. - * - * Also note, that if the filesystem's .remount_fs function doesn't - * reset all options to their default value, but changes only newly - * given options, then the displayed options will not reflect reality - * any more. - */ -void save_mount_options(struct super_block *sb, char *options) -{ - BUG_ON(sb->s_options); - rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL)); -} -EXPORT_SYMBOL(save_mount_options); - -void replace_mount_options(struct super_block *sb, char *options) -{ - char *old = sb->s_options; - rcu_assign_pointer(sb->s_options, options); - if (old) { - synchronize_rcu(); - kfree(old); - } -} -EXPORT_SYMBOL(replace_mount_options); - #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) @@ -1657,7 +1598,7 @@ out_unlock: namespace_unlock(); } -/* +/* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) @@ -2211,7 +2152,7 @@ static int do_loopback(struct path *path, const char *old_name, err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) - goto out; + goto out; mp = lock_mount(path); err = PTR_ERR(mp); diff --git a/fs/nsfs.c b/fs/nsfs.c index f3db56e83dd2..08127a2b8559 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -53,7 +53,6 @@ static void nsfs_evict(struct inode *inode) static void *__ns_get_path(struct path *path, struct ns_common *ns) { struct vfsmount *mnt = nsfs_mnt; - struct qstr qname = { .name = "", }; struct dentry *dentry; struct inode *inode; unsigned long d; @@ -85,7 +84,7 @@ slow: inode->i_fop = &ns_file_operations; inode->i_private = ns; - dentry = d_alloc_pseudo(mnt->mnt_sb, &qname); + dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 8c9034ee7383..ee14af9e26f2 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -13,6 +13,7 @@ #include <linux/buffer_head.h> #include <linux/vmalloc.h> #include <linux/writeback.h> +#include <linux/seq_file.h> #include <linux/crc-itu-t.h> #include "omfs.h" @@ -290,12 +291,40 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } +/* + * Display the mount options in /proc/mounts. + */ +static int omfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct omfs_sb_info *sbi = OMFS_SB(root->d_sb); + umode_t cur_umask = current_umask(); + + if (!uid_eq(sbi->s_uid, current_uid())) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (!gid_eq(sbi->s_gid, current_gid())) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + + if (sbi->s_dmask == sbi->s_fmask) { + if (sbi->s_fmask != cur_umask) + seq_printf(m, ",umask=%o", sbi->s_fmask); + } else { + if (sbi->s_dmask != cur_umask) + seq_printf(m, ",dmask=%o", sbi->s_dmask); + if (sbi->s_fmask != cur_umask) + seq_printf(m, ",fmask=%o", sbi->s_fmask); + } + + return 0; +} + static const struct super_operations omfs_sops = { .write_inode = omfs_write_inode, .evict_inode = omfs_evict_inode, .put_super = omfs_put_super, .statfs = omfs_statfs, - .show_options = generic_show_options, + .show_options = omfs_show_options, }; /* @@ -434,8 +463,6 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *root; int ret = -EINVAL; - save_mount_options(sb, (char *) data); - sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 5c7c273e17ec..5a1bed6c8c6a 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -35,6 +35,19 @@ static const match_table_t tokens = { uint64_t orangefs_features; +static int orangefs_show_options(struct seq_file *m, struct dentry *root) +{ + struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(root->d_sb); + + if (root->d_sb->s_flags & MS_POSIXACL) + seq_puts(m, ",acl"); + if (orangefs_sb->flags & ORANGEFS_OPT_INTR) + seq_puts(m, ",intr"); + if (orangefs_sb->flags & ORANGEFS_OPT_LOCAL_LOCK) + seq_puts(m, ",local_lock"); + return 0; +} + static int parse_mount_options(struct super_block *sb, char *options, int silent) { @@ -305,7 +318,7 @@ static const struct super_operations orangefs_s_ops = { .drop_inode = generic_delete_inode, .statfs = orangefs_statfs, .remount_fs = orangefs_remount_fs, - .show_options = generic_show_options, + .show_options = orangefs_show_options, }; static struct dentry *orangefs_fh_to_dentry(struct super_block *sb, diff --git a/fs/pipe.c b/fs/pipe.c index 73b84baf58f8..97e5be897753 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -739,13 +739,12 @@ int create_pipe_files(struct file **res, int flags) struct inode *inode = get_pipe_inode(); struct file *f; struct path path; - static struct qstr name = { .name = "" }; if (!inode) return -ENFILE; err = -ENOMEM; - path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name); + path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name); if (!path.dentry) goto err_inode; path.mnt = mntget(pipe_mnt); diff --git a/fs/proc/base.c b/fs/proc/base.c index 88b773f318cd..719c2e943ea1 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1360,20 +1360,19 @@ static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; - int err, n; + int err; + unsigned int n; + + err = kstrtouint_from_user(buf, count, 0, &n); + if (err) + return err; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; + WRITE_ONCE(task->fail_nth, n); put_task_struct(task); - if (task != current) - return -EPERM; - err = kstrtoint_from_user(buf, count, 10, &n); - if (err) - return err; - if (n < 0 || n == INT_MAX) - return -EINVAL; - current->fail_nth = n + 1; + return count; } @@ -1381,21 +1380,18 @@ static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; - int err; + char numbuf[PROC_NUMBUF]; + ssize_t len; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; + len = snprintf(numbuf, sizeof(numbuf), "%u\n", + READ_ONCE(task->fail_nth)); + len = simple_read_from_buffer(buf, count, ppos, numbuf, len); put_task_struct(task); - if (task != current) - return -EPERM; - if (count < 1) - return -EINVAL; - err = put_user((char)(current->fail_nth ? 'N' : 'Y'), buf); - if (err) - return err; - current->fail_nth = 0; - return 1; + + return len; } static const struct file_operations proc_fail_nth_operations = { @@ -2966,6 +2962,7 @@ static const struct pid_entry tgid_base_stuff[] = { #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), + REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_ELF_CORE REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), @@ -3358,11 +3355,7 @@ static const struct pid_entry tid_base_stuff[] = { #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), - /* - * Operations on the file check that the task is current, - * so we create it with 0666 to support testing under unprivileged user. - */ - REG("fail-nth", 0666, proc_fail_nth_operations), + REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 4d02c3b65061..fefd22611cf6 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -283,6 +283,16 @@ static void parse_options(char *options) } } +/* + * Display the mount options in /proc/mounts. + */ +static int pstore_show_options(struct seq_file *m, struct dentry *root) +{ + if (kmsg_bytes != PSTORE_DEFAULT_KMSG_BYTES) + seq_printf(m, ",kmsg_bytes=%lu", kmsg_bytes); + return 0; +} + static int pstore_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); @@ -296,7 +306,7 @@ static const struct super_operations pstore_ops = { .drop_inode = generic_delete_inode, .evict_inode = pstore_evict_inode, .remount_fs = pstore_remount, - .show_options = generic_show_options, + .show_options = pstore_show_options, }; static struct super_block *pstore_sb; @@ -448,8 +458,6 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - save_mount_options(sb, data); - pstore_sb = sb; sb->s_maxbytes = MAX_LFS_FILESIZE; diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 58051265626f..7f4e48c8d188 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -5,6 +5,9 @@ #include <linux/time.h> #include <linux/pstore.h> +#define PSTORE_DEFAULT_KMSG_BYTES 10240 +extern unsigned long kmsg_bytes; + #ifdef CONFIG_PSTORE_FTRACE extern void pstore_register_ftrace(void); extern void pstore_unregister_ftrace(void); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 1b6e0ff6bff5..2b21d180157c 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -99,7 +99,7 @@ static char *big_oops_buf; static size_t big_oops_buf_sz; /* How much of the console log to snapshot */ -static unsigned long kmsg_bytes = 10240; +unsigned long kmsg_bytes = PSTORE_DEFAULT_KMSG_BYTES; void pstore_set_kmsg_bytes(int bytes) { diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 26e45863e499..11201b2d06b9 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -38,6 +38,14 @@ #include <linux/uaccess.h> #include "internal.h" +struct ramfs_mount_opts { + umode_t mode; +}; + +struct ramfs_fs_info { + struct ramfs_mount_opts mount_opts; +}; + #define RAMFS_DEFAULT_MODE 0755 static const struct super_operations ramfs_ops; @@ -149,14 +157,22 @@ static const struct inode_operations ramfs_dir_inode_operations = { .rename = simple_rename, }; +/* + * Display the mount options in /proc/mounts. + */ +static int ramfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct ramfs_fs_info *fsi = root->d_sb->s_fs_info; + + if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", fsi->mount_opts.mode); + return 0; +} + static const struct super_operations ramfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, - .show_options = generic_show_options, -}; - -struct ramfs_mount_opts { - umode_t mode; + .show_options = ramfs_show_options, }; enum { @@ -169,10 +185,6 @@ static const match_table_t tokens = { {Opt_err, NULL} }; -struct ramfs_fs_info { - struct ramfs_mount_opts mount_opts; -}; - static int ramfs_parse_options(char *data, struct ramfs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -211,8 +223,6 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 685f1e056998..306e4e9d172d 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1599,8 +1599,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) } out_ok_unlocked: - if (new_opts) - replace_mount_options(s, new_opts); return 0; out_err_unlock: @@ -1916,8 +1914,6 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) char *qf_names[REISERFS_MAXQUOTAS] = {}; unsigned int qfmt = 0; - save_mount_options(s, data); - sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; diff --git a/fs/super.c b/fs/super.c index adb0c0de428c..6bc3352adcf3 100644 --- a/fs/super.c +++ b/fs/super.c @@ -168,7 +168,6 @@ static void destroy_super(struct super_block *s) WARN_ON(!list_empty(&s->s_mounts)); put_user_ns(s->s_user_ns); kfree(s->s_subtype); - kfree(s->s_options); call_rcu(&s->rcu, destroy_super_rcu); } @@ -508,7 +507,7 @@ retry: return ERR_PTR(-ENOMEM); goto retry; } - + err = set(s, data); if (err) { spin_unlock(&sb_lock); @@ -771,7 +770,7 @@ restart: spin_unlock(&sb_lock); return NULL; } - + struct super_block *user_get_super(dev_t dev) { struct super_block *sb; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 328e89c2cf83..bea8ad876bf9 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -270,8 +270,6 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) struct tracefs_fs_info *fsi; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) { diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index 382ed428cfd2..114ba455bac3 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -9,8 +9,13 @@ static int ubifs_crypt_get_context(struct inode *inode, void *ctx, size_t len) static int ubifs_crypt_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { + /* + * Creating an encryption context is done unlocked since we + * operate on a new inode which is not visible to other users + * at this point. So, no need to check whether inode is locked. + */ return ubifs_xattr_set(inode, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); + ctx, len, 0, false); } static bool ubifs_crypt_empty_dir(struct inode *inode) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 566079d9b402..417fe0b29f23 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -143,6 +143,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, case S_IFBLK: case S_IFCHR: inode->i_op = &ubifs_file_inode_operations; + encrypted = false; break; default: BUG(); @@ -1061,7 +1062,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, int sz_change; int err, devlen = 0; struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, - .new_ino_d = ALIGN(devlen, 8), .dirtied_ino = 1 }; struct fscrypt_name nm; @@ -1079,6 +1079,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, devlen = ubifs_encode_dev(dev, rdev); } + req.new_ino_d = ALIGN(devlen, 8); err = ubifs_budget_space(c, &req); if (err) { kfree(dev); @@ -1396,17 +1397,14 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS); if (!dev) { - ubifs_release_budget(c, &req); - ubifs_release_budget(c, &ino_req); - return -ENOMEM; + err = -ENOMEM; + goto out_release; } err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout); if (err) { - ubifs_release_budget(c, &req); - ubifs_release_budget(c, &ino_req); kfree(dev); - return err; + goto out_release; } whiteout->i_state |= I_LINKABLE; @@ -1494,12 +1492,10 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, err = ubifs_budget_space(c, &wht_req); if (err) { - ubifs_release_budget(c, &req); - ubifs_release_budget(c, &ino_req); kfree(whiteout_ui->data); whiteout_ui->data_len = 0; iput(whiteout); - return err; + goto out_release; } inc_nlink(whiteout); @@ -1554,6 +1550,7 @@ out_cancel: iput(whiteout); } unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); +out_release: ubifs_release_budget(c, &ino_req); ubifs_release_budget(c, &req); fscrypt_free_filename(&old_nm); @@ -1647,6 +1644,21 @@ int ubifs_getattr(const struct path *path, struct kstat *stat, struct ubifs_inode *ui = ubifs_inode(inode); mutex_lock(&ui->ui_mutex); + + if (ui->flags & UBIFS_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (ui->flags & UBIFS_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (ui->flags & UBIFS_CRYPT_FL) + stat->attributes |= STATX_ATTR_ENCRYPTED; + if (ui->flags & UBIFS_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE); + generic_fillattr(inode, stat); stat->blksize = UBIFS_BLOCK_SIZE; stat->size = ui->ui_size; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2cda3d67e2d0..8cad0b19b404 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -735,6 +735,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, int err, page_idx, page_cnt, ret = 0, n = 0; int allocate = bu->buf ? 0 : 1; loff_t isize; + gfp_t ra_gfp_mask = readahead_gfp_mask(mapping) & ~__GFP_FS; err = ubifs_tnc_get_bu_keys(c, bu); if (err) @@ -796,8 +797,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, if (page_offset > end_index) break; - page = find_or_create_page(mapping, page_offset, - GFP_NOFS | __GFP_COLD); + page = find_or_create_page(mapping, page_offset, ra_gfp_mask); if (!page) break; if (!PageUptodate(page)) @@ -1284,6 +1284,14 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) if (err) return err; + if (ubifs_crypt_is_encrypted(inode) && (attr->ia_valid & ATTR_SIZE)) { + err = fscrypt_get_encryption_info(inode); + if (err) + return err; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size < inode->i_size) /* Truncation to a smaller size */ err = do_truncation(c, inode, attr); @@ -1607,15 +1615,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = { static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) { int err; - struct inode *inode = file->f_mapping->host; - - if (ubifs_crypt_is_encrypted(inode)) { - err = fscrypt_get_encryption_info(inode); - if (err) - return -EACCES; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } err = generic_file_mmap(file, vma); if (err) @@ -1698,12 +1697,6 @@ static const char *ubifs_get_link(struct dentry *dentry, pstr.name[pstr.len] = '\0'; - // XXX this probably won't happen anymore... - if (pstr.name[0] == '\0') { - fscrypt_fname_free_buffer(&pstr); - return ERR_PTR(-ENOENT); - } - set_delayed_call(done, kfree_link, pstr.name); return pstr.name; } diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 294519b98874..04c4ec6483e5 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -549,8 +549,6 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, struct ubifs_ino_node *ino; union ubifs_key dent_key, ino_key; - //dbg_jnl("ino %lu, dent '%.*s', data len %d in dir ino %lu", - // inode->i_ino, nm->len, nm->name, ui->data_len, dir->i_ino); ubifs_assert(mutex_is_locked(&host_ui->ui_mutex)); dlen = UBIFS_DENT_NODE_SZ + fname_len(nm) + 1; @@ -574,7 +572,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, /* Make sure to also account for extended attributes */ len += host_ui->data_len; - dent = kmalloc(len, GFP_NOFS); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -585,7 +583,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, if (!xent) { dent->ch.node_type = UBIFS_DENT_NODE; - dent_key_init(c, &dent_key, dir->i_ino, nm); + if (nm->hash) + dent_key_init_hash(c, &dent_key, dir->i_ino, nm->hash); + else + dent_key_init(c, &dent_key, dir->i_ino, nm); } else { dent->ch.node_type = UBIFS_XENT_NODE; xent_key_init(c, &dent_key, dir->i_ino, nm); @@ -629,7 +630,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, kfree(dent); if (deletion) { - err = ubifs_tnc_remove_nm(c, &dent_key, nm); + if (nm->hash) + err = ubifs_tnc_remove_dh(c, &dent_key, nm->minor_hash); + else + err = ubifs_tnc_remove_nm(c, &dent_key, nm); if (err) goto out_ro; err = ubifs_add_dirt(c, lnum, dlen); @@ -950,9 +954,6 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, int twoparents = (fst_dir != snd_dir); void *p; - //dbg_jnl("dent '%pd' in dir ino %lu between dent '%pd' in dir ino %lu", - // fst_dentry, fst_dir->i_ino, snd_dentry, snd_dir->i_ino); - ubifs_assert(ubifs_inode(fst_dir)->data_len == 0); ubifs_assert(ubifs_inode(snd_dir)->data_len == 0); ubifs_assert(mutex_is_locked(&ubifs_inode(fst_dir)->ui_mutex)); @@ -967,7 +968,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, if (twoparents) len += plen; - dent1 = kmalloc(len, GFP_NOFS); + dent1 = kzalloc(len, GFP_NOFS); if (!dent1) return -ENOMEM; @@ -984,6 +985,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, dent1->nlen = cpu_to_le16(fname_len(snd_nm)); memcpy(dent1->name, fname_name(snd_nm), fname_len(snd_nm)); dent1->name[fname_len(snd_nm)] = '\0'; + set_dent_cookie(c, dent1); zero_dent_node_unused(dent1); ubifs_prep_grp_node(c, dent1, dlen1, 0); @@ -996,6 +998,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, dent2->nlen = cpu_to_le16(fname_len(fst_nm)); memcpy(dent2->name, fname_name(fst_nm), fname_len(fst_nm)); dent2->name[fname_len(fst_nm)] = '\0'; + set_dent_cookie(c, dent2); zero_dent_node_unused(dent2); ubifs_prep_grp_node(c, dent2, dlen2, 0); @@ -1094,8 +1097,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, int move = (old_dir != new_dir); struct ubifs_inode *uninitialized_var(new_ui); - //dbg_jnl("dent '%pd' in dir ino %lu to dent '%pd' in dir ino %lu", - // old_dentry, old_dir->i_ino, new_dentry, new_dir->i_ino); ubifs_assert(ubifs_inode(old_dir)->data_len == 0); ubifs_assert(ubifs_inode(new_dir)->data_len == 0); ubifs_assert(mutex_is_locked(&ubifs_inode(old_dir)->ui_mutex)); @@ -1117,7 +1118,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8); if (move) len += plen; - dent = kmalloc(len, GFP_NOFS); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -1298,7 +1299,9 @@ static int truncate_data_node(const struct ubifs_info *c, const struct inode *in goto out; } - if (compr_type != UBIFS_COMPR_NONE) { + if (compr_type == UBIFS_COMPR_NONE) { + out_len = *new_len; + } else { err = ubifs_decompress(c, &dn->data, dlen, buf, &out_len, compr_type); if (err) goto out; @@ -1485,9 +1488,6 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, int sync = IS_DIRSYNC(host); struct ubifs_inode *host_ui = ubifs_inode(host); - //dbg_jnl("host %lu, xattr ino %lu, name '%s', data len %d", - // host->i_ino, inode->i_ino, nm->name, - // ubifs_inode(inode)->data_len); ubifs_assert(inode->i_nlink == 0); ubifs_assert(mutex_is_locked(&host_ui->ui_mutex)); @@ -1500,7 +1500,7 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, hlen = host_ui->data_len + UBIFS_INO_NODE_SZ; len = aligned_xlen + UBIFS_INO_NODE_SZ + ALIGN(hlen, 8); - xent = kmalloc(len, GFP_NOFS); + xent = kzalloc(len, GFP_NOFS); if (!xent) return -ENOMEM; @@ -1607,7 +1607,7 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, aligned_len1 = ALIGN(len1, 8); aligned_len = aligned_len1 + ALIGN(len2, 8); - ino = kmalloc(aligned_len, GFP_NOFS); + ino = kzalloc(aligned_len, GFP_NOFS); if (!ino) return -ENOMEM; diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 7547be512db2..b1f7c0caa3ac 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -162,6 +162,7 @@ static inline void dent_key_init(const struct ubifs_info *c, uint32_t hash = c->key_hash(fname_name(nm), fname_len(nm)); ubifs_assert(!(hash & ~UBIFS_S_KEY_HASH_MASK)); + ubifs_assert(!nm->hash && !nm->minor_hash); key->u32[0] = inum; key->u32[1] = hash | (UBIFS_DENT_KEY << UBIFS_S_KEY_HASH_BITS); } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index cf4cc99b75b5..bffadbb67e47 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -45,7 +45,7 @@ #define UBIFS_KMALLOC_OK (128*1024) /* Slab cache for UBIFS inodes */ -struct kmem_cache *ubifs_inode_slab; +static struct kmem_cache *ubifs_inode_slab; /* UBIFS TNC shrinker description */ static struct shrinker ubifs_shrinker_info = { @@ -446,6 +446,8 @@ static int ubifs_show_options(struct seq_file *s, struct dentry *root) ubifs_compr_name(c->mount_opts.compr_type)); } + seq_printf(s, ",ubi=%d,vol=%d", c->vi.ubi_num, c->vi.vol_id); + return 0; } @@ -931,6 +933,7 @@ enum { Opt_chk_data_crc, Opt_no_chk_data_crc, Opt_override_compr, + Opt_ignore, Opt_err, }; @@ -942,6 +945,8 @@ static const match_table_t tokens = { {Opt_chk_data_crc, "chk_data_crc"}, {Opt_no_chk_data_crc, "no_chk_data_crc"}, {Opt_override_compr, "compr=%s"}, + {Opt_ignore, "ubi=%s"}, + {Opt_ignore, "vol=%s"}, {Opt_err, NULL}, }; @@ -1042,6 +1047,8 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, c->default_compr = c->mount_opts.compr_type; break; } + case Opt_ignore: + break; default: { unsigned long flag; @@ -1869,8 +1876,10 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) bu_init(c); else { dbg_gen("disable bulk-read"); + mutex_lock(&c->bu_mutex); kfree(c->bu.buf); c->bu.buf = NULL; + mutex_unlock(&c->bu_mutex); } ubifs_assert(c->lst.taken_empty_lebs > 0); diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 709aa098dd46..0a213dcba2a1 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1812,7 +1812,7 @@ static int do_lookup_nm(struct ubifs_info *c, const union ubifs_key *key, int found, n, err; struct ubifs_znode *znode; - //dbg_tnck(key, "name '%.*s' key ", nm->len, nm->name); + dbg_tnck(key, "key "); mutex_lock(&c->tnc_mutex); found = ubifs_lookup_level0(c, key, &znode, &n); if (!found) { @@ -1880,48 +1880,65 @@ int ubifs_tnc_lookup_nm(struct ubifs_info *c, const union ubifs_key *key, return do_lookup_nm(c, key, node, nm); } -static int do_lookup_dh(struct ubifs_info *c, const union ubifs_key *key, - struct ubifs_dent_node *dent, uint32_t cookie) +static int search_dh_cookie(struct ubifs_info *c, const union ubifs_key *key, + struct ubifs_dent_node *dent, uint32_t cookie, + struct ubifs_znode **zn, int *n) { - int n, err, type = key_type(c, key); - struct ubifs_znode *znode; + int err; + struct ubifs_znode *znode = *zn; struct ubifs_zbranch *zbr; - union ubifs_key *dkey, start_key; - - ubifs_assert(is_hash_key(c, key)); - - lowest_dent_key(c, &start_key, key_inum(c, key)); - - mutex_lock(&c->tnc_mutex); - err = ubifs_lookup_level0(c, &start_key, &znode, &n); - if (unlikely(err < 0)) - goto out_unlock; + union ubifs_key *dkey; for (;;) { if (!err) { - err = tnc_next(c, &znode, &n); + err = tnc_next(c, &znode, n); if (err) - goto out_unlock; + goto out; } - zbr = &znode->zbranch[n]; + zbr = &znode->zbranch[*n]; dkey = &zbr->key; if (key_inum(c, dkey) != key_inum(c, key) || - key_type(c, dkey) != type) { + key_type(c, dkey) != key_type(c, key)) { err = -ENOENT; - goto out_unlock; + goto out; } err = tnc_read_hashed_node(c, zbr, dent); if (err) - goto out_unlock; + goto out; if (key_hash(c, key) == key_hash(c, dkey) && - le32_to_cpu(dent->cookie) == cookie) - goto out_unlock; + le32_to_cpu(dent->cookie) == cookie) { + *zn = znode; + goto out; + } } +out: + + return err; +} + +static int do_lookup_dh(struct ubifs_info *c, const union ubifs_key *key, + struct ubifs_dent_node *dent, uint32_t cookie) +{ + int n, err; + struct ubifs_znode *znode; + union ubifs_key start_key; + + ubifs_assert(is_hash_key(c, key)); + + lowest_dent_key(c, &start_key, key_inum(c, key)); + + mutex_lock(&c->tnc_mutex); + err = ubifs_lookup_level0(c, &start_key, &znode, &n); + if (unlikely(err < 0)) + goto out_unlock; + + err = search_dh_cookie(c, key, dent, cookie, &znode, &n); + out_unlock: mutex_unlock(&c->tnc_mutex); return err; @@ -2393,8 +2410,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, struct ubifs_znode *znode; mutex_lock(&c->tnc_mutex); - //dbg_tnck(key, "LEB %d:%d, name '%.*s', key ", - // lnum, offs, nm->len, nm->name); + dbg_tnck(key, "LEB %d:%d, key ", lnum, offs); found = lookup_level0_dirty(c, key, &znode, &n); if (found < 0) { err = found; @@ -2628,7 +2644,7 @@ int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key, struct ubifs_znode *znode; mutex_lock(&c->tnc_mutex); - //dbg_tnck(key, "%.*s, key ", nm->len, nm->name); + dbg_tnck(key, "key "); err = lookup_level0_dirty(c, key, &znode, &n); if (err < 0) goto out_unlock; @@ -2663,6 +2679,74 @@ out_unlock: } /** + * ubifs_tnc_remove_dh - remove an index entry for a "double hashed" node. + * @c: UBIFS file-system description object + * @key: key of node + * @cookie: node cookie for collision resolution + * + * Returns %0 on success or negative error code on failure. + */ +int ubifs_tnc_remove_dh(struct ubifs_info *c, const union ubifs_key *key, + uint32_t cookie) +{ + int n, err; + struct ubifs_znode *znode; + struct ubifs_dent_node *dent; + struct ubifs_zbranch *zbr; + + if (!c->double_hash) + return -EOPNOTSUPP; + + mutex_lock(&c->tnc_mutex); + err = lookup_level0_dirty(c, key, &znode, &n); + if (err <= 0) + goto out_unlock; + + zbr = &znode->zbranch[n]; + dent = kmalloc(UBIFS_MAX_DENT_NODE_SZ, GFP_NOFS); + if (!dent) { + err = -ENOMEM; + goto out_unlock; + } + + err = tnc_read_hashed_node(c, zbr, dent); + if (err) + goto out_free; + + /* If the cookie does not match, we're facing a hash collision. */ + if (le32_to_cpu(dent->cookie) != cookie) { + union ubifs_key start_key; + + lowest_dent_key(c, &start_key, key_inum(c, key)); + + err = ubifs_lookup_level0(c, &start_key, &znode, &n); + if (unlikely(err < 0)) + goto out_free; + + err = search_dh_cookie(c, key, dent, cookie, &znode, &n); + if (err) + goto out_free; + } + + if (znode->cnext || !ubifs_zn_dirty(znode)) { + znode = dirty_cow_bottom_up(c, znode); + if (IS_ERR(znode)) { + err = PTR_ERR(znode); + goto out_free; + } + } + err = tnc_delete(c, znode, n); + +out_free: + kfree(dent); +out_unlock: + if (!err) + err = dbg_check_tnc(c, 0); + mutex_unlock(&c->tnc_mutex); + return err; +} + +/** * key_in_range - determine if a key falls within a range of keys. * @c: UBIFS file-system description object * @key: key to check @@ -2802,6 +2886,8 @@ int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum) dbg_tnc("xent '%s', ino %lu", xent->name, (unsigned long)xattr_inum); + ubifs_evict_xattr_inode(c, xattr_inum); + fname_name(&nm) = xent->name; fname_len(&nm) = le16_to_cpu(xent->nlen); err = ubifs_tnc_remove_nm(c, &key1, &nm); @@ -2863,7 +2949,7 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c, struct ubifs_zbranch *zbr; union ubifs_key *dkey; - //dbg_tnck(key, "%s ", nm->name ? (char *)nm->name : "(lowest)"); + dbg_tnck(key, "key "); ubifs_assert(is_hash_key(c, key)); mutex_lock(&c->tnc_mutex); diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index 51157da3f76e..aa31f60220ef 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -57,6 +57,8 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, ubifs_dump_znode(c, znode); if (zbr->znode) ubifs_dump_znode(c, zbr->znode); + + return -EINVAL; } } ubifs_prepare_node(c, idx, len, 0); @@ -859,6 +861,8 @@ static int write_index(struct ubifs_info *c) ubifs_dump_znode(c, znode); if (zbr->znode) ubifs_dump_znode(c, zbr->znode); + + return -EINVAL; } } len = ubifs_idx_node_sz(c, znode->child_cnt); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 298b4d89eee9..cd43651f1731 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1451,7 +1451,6 @@ struct ubifs_info { extern struct list_head ubifs_infos; extern spinlock_t ubifs_infos_lock; extern atomic_long_t ubifs_clean_zn_cnt; -extern struct kmem_cache *ubifs_inode_slab; extern const struct super_operations ubifs_super_operations; extern const struct address_space_operations ubifs_file_address_operations; extern const struct file_operations ubifs_file_operations; @@ -1590,6 +1589,8 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, int ubifs_tnc_remove(struct ubifs_info *c, const union ubifs_key *key); int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key, const struct fscrypt_name *nm); +int ubifs_tnc_remove_dh(struct ubifs_info *c, const union ubifs_key *key, + uint32_t cookie); int ubifs_tnc_remove_range(struct ubifs_info *c, union ubifs_key *from_key, union ubifs_key *to_key); int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum); @@ -1754,9 +1755,10 @@ int ubifs_check_dir_empty(struct inode *dir); extern const struct xattr_handler *ubifs_xattr_handlers[]; ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size); int ubifs_xattr_set(struct inode *host, const char *name, const void *value, - size_t size, int flags); + size_t size, int flags, bool check_lock); ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, size_t size); +void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum); #ifdef CONFIG_UBIFS_FS_SECURITY extern int ubifs_init_security(struct inode *dentry, struct inode *inode, diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 6c9e62c2ef55..c13eae819cbc 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -280,7 +280,7 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum) } int ubifs_xattr_set(struct inode *host, const char *name, const void *value, - size_t size, int flags) + size_t size, int flags, bool check_lock) { struct inode *inode; struct ubifs_info *c = host->i_sb->s_fs_info; @@ -289,12 +289,7 @@ int ubifs_xattr_set(struct inode *host, const char *name, const void *value, union ubifs_key key; int err; - /* - * Creating an encryption context is done unlocked since we - * operate on a new inode which is not visible to other users - * at this point. - */ - if (strcmp(name, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT) != 0) + if (check_lock) ubifs_assert(inode_is_locked(host)); if (size > UBIFS_MAX_INO_DATA) @@ -513,6 +508,28 @@ out_cancel: return err; } +/** + * ubifs_evict_xattr_inode - Evict an xattr inode. + * @c: UBIFS file-system description object + * @xattr_inum: xattr inode number + * + * When an inode that hosts xattrs is being removed we have to make sure + * that cached inodes of the xattrs also get removed from the inode cache + * otherwise we'd waste memory. This function looks up an inode from the + * inode cache and clears the link counter such that iput() will evict + * the inode. + */ +void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum) +{ + struct inode *inode; + + inode = ilookup(c->vfs_sb, xattr_inum); + if (inode) { + clear_nlink(inode); + iput(inode); + } +} + static int ubifs_xattr_remove(struct inode *host, const char *name) { struct inode *inode; @@ -576,8 +593,12 @@ static int init_xattrs(struct inode *inode, const struct xattr *xattr_array, } strcpy(name, XATTR_SECURITY_PREFIX); strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); + /* + * creating a new inode without holding the inode rwsem, + * no need to check whether inode is locked. + */ err = ubifs_xattr_set(inode, name, xattr->value, - xattr->value_len, 0); + xattr->value_len, 0, false); kfree(name); if (err < 0) break; @@ -624,7 +645,7 @@ static int xattr_set(const struct xattr_handler *handler, name = xattr_full_name(handler, name); if (value) - return ubifs_xattr_set(inode, name, value, size, flags); + return ubifs_xattr_set(inode, name, value, size, flags, true); else return ubifs_xattr_remove(inode, name); } diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index ef8a1c75a467..de7b9bd30bec 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -114,12 +114,14 @@ xfs_inode_hasattr( * Overall external interface routines. *========================================================================*/ -/* Retrieve an extended attribute and its value. Must have iolock. */ +/* Retrieve an extended attribute and its value. Must have ilock. */ int xfs_attr_get_ilocked( struct xfs_inode *ip, struct xfs_da_args *args) { + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + if (!xfs_inode_hasattr(ip)) return -ENOATTR; else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index 2834574cb6e7..d69c772271cb 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -136,8 +136,6 @@ typedef uint16_t xfs_qwarncnt_t; */ #define XFS_QMOPT_INHERIT 0x1000000 -#define XFS_QMOPT_NOLOCK 0x2000000 /* don't ilock during dqget */ - /* * flags to xfs_trans_mod_dquot. */ diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 545eca508d42..7740c8a5e736 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -463,6 +463,8 @@ xfs_attr_list_int_ilocked( { struct xfs_inode *dp = context->dp; + ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + /* * Decide on what work routines to call based on the inode size. */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f89f7b5241e6..fd2ef8c2c9a7 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -472,23 +472,18 @@ xfs_qm_dqtobp( struct xfs_mount *mp = dqp->q_mount; xfs_dqid_t id = be32_to_cpu(dqp->q_core.d_id); struct xfs_trans *tp = (tpp ? *tpp : NULL); - uint lock_mode = 0; + uint lock_mode; quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags); dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk; - ASSERT(!(flags & XFS_QMOPT_NOLOCK) || - xfs_isilocked(quotip, XFS_ILOCK_SHARED) || - xfs_isilocked(quotip, XFS_ILOCK_EXCL)); - if (!(flags & XFS_QMOPT_NOLOCK)) - lock_mode = xfs_ilock_data_map_shared(quotip); + lock_mode = xfs_ilock_data_map_shared(quotip); if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) { /* * Return if this type of quotas is turned off while we * didn't have the quota inode lock. */ - if (lock_mode) - xfs_iunlock(quotip, lock_mode); + xfs_iunlock(quotip, lock_mode); return -ESRCH; } @@ -498,8 +493,7 @@ xfs_qm_dqtobp( error = xfs_bmapi_read(quotip, dqp->q_fileoffset, XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0); - if (lock_mode) - xfs_iunlock(quotip, lock_mode); + xfs_iunlock(quotip, lock_mode); if (error) return error; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 12cd9cf7de41..23a50d7aa46a 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -61,6 +61,8 @@ xfs_readlink_bmap_ilocked( int fsblocks = 0; int offset; + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + fsblocks = xfs_symlink_blocks(mp, pathlen); error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0); if (error) diff --git a/include/asm-generic/uaccess-unaligned.h b/include/asm-generic/uaccess-unaligned.h deleted file mode 100644 index 67deb898f0c5..000000000000 --- a/include/asm-generic/uaccess-unaligned.h +++ /dev/null @@ -1,26 +0,0 @@ -#ifndef __ASM_GENERIC_UACCESS_UNALIGNED_H -#define __ASM_GENERIC_UACCESS_UNALIGNED_H - -/* - * This macro should be used instead of __get_user() when accessing - * values at locations that are not known to be aligned. - */ -#define __get_user_unaligned(x, ptr) \ -({ \ - __typeof__ (*(ptr)) __x; \ - __copy_from_user(&__x, (ptr), sizeof(*(ptr))) ? -EFAULT : 0; \ - (x) = __x; \ -}) - - -/* - * This macro should be used instead of __put_user() when accessing - * values at locations that are not known to be aligned. - */ -#define __put_user_unaligned(x, ptr) \ -({ \ - __typeof__ (*(ptr)) __x = (x); \ - __copy_to_user((ptr), &__x, sizeof(*(ptr))) ? -EFAULT : 0; \ -}) - -#endif /* __ASM_GENERIC_UACCESS_UNALIGNED_H */ diff --git a/include/dt-bindings/clock/boston-clock.h b/include/dt-bindings/clock/boston-clock.h new file mode 100644 index 000000000000..a6f009821137 --- /dev/null +++ b/include/dt-bindings/clock/boston-clock.h @@ -0,0 +1,14 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * + * SPDX-License-Identifier: GPL-2.0 + */ + +#ifndef __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ +#define __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ + +#define BOSTON_CLK_INPUT 0 +#define BOSTON_CLK_SYS 1 +#define BOSTON_CLK_CPU 2 + +#endif /* __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ */ diff --git a/include/linux/clk.h b/include/linux/clk.h index 91bd464f4c9b..12c96d94d1fa 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -657,6 +657,28 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } +static inline int clk_bulk_prepare_enable(int num_clks, + struct clk_bulk_data *clks) +{ + int ret; + + ret = clk_bulk_prepare(num_clks, clks); + if (ret) + return ret; + ret = clk_bulk_enable(num_clks, clks); + if (ret) + clk_bulk_unprepare(num_clks, clks); + + return ret; +} + +static inline void clk_bulk_disable_unprepare(int num_clks, + struct clk_bulk_data *clks) +{ + clk_bulk_disable(num_clks, clks); + clk_bulk_unprepare(num_clks, clks); +} + #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index c156f5082758..d4292ebc5c8b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -28,47 +28,49 @@ #include <linux/thermal.h> #include <linux/cpumask.h> +struct cpufreq_policy; + typedef int (*get_static_t)(cpumask_t *cpumask, int interval, unsigned long voltage, u32 *power); #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus); +cpufreq_cooling_register(struct cpufreq_policy *policy); struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ #ifdef CONFIG_THERMAL_OF struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus); + struct cpufreq_policy *policy); struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -82,15 +84,14 @@ of_cpufreq_power_cooling_register(struct device_node *np, */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { return NULL; @@ -98,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus, static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -117,11 +118,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - return THERMAL_CSTATE_INVALID; -} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 905117bd5012..f10a9b3761cd 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -862,6 +862,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, return -EINVAL; } } + +static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *pos; + int count = 0; + + if (unlikely(!policy->freq_table)) + return 0; + + cpufreq_for_each_valid_entry(pos, policy->freq_table) + count++; + + return count; +} #else static inline int cpufreq_boost_trigger_state(int state) { diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c706eaac692e..3f3ff4ccdc3f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -55,6 +55,11 @@ struct qstr { #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +extern const char empty_string[]; +extern const struct qstr empty_name; +extern const char slash_string[]; +extern const struct qstr slash_name; + struct dentry_stat_t { long nr_dentry; long nr_unused; diff --git a/include/linux/flat.h b/include/linux/flat.h index 2c1eb15c4ba4..7d542dfd0def 100644 --- a/include/linux/flat.h +++ b/include/linux/flat.h @@ -9,8 +9,8 @@ #ifndef _LINUX_FLAT_H #define _LINUX_FLAT_H -#include <asm/flat.h> #include <uapi/linux/flat.h> +#include <asm/flat.h> /* * While it would be nice to keep this header clean, users of older diff --git a/include/linux/fs.h b/include/linux/fs.h index 976aaa1af82a..7b5d6816542b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1364,11 +1364,6 @@ struct super_block { */ char *s_subtype; - /* - * Saved mount options for lazy filesystems using - * generic_show_options() - */ - char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* @@ -3046,7 +3041,7 @@ extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -extern void get_filesystem(struct file_system_type *fs); +extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); @@ -3123,10 +3118,6 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -extern int generic_show_options(struct seq_file *m, struct dentry *root); -extern void save_mount_options(struct super_block *sb, char *options); -extern void replace_mount_options(struct super_block *sb, char *options); - static inline bool io_is_direct(struct file *filp) { return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 9ab375419189..50893a1646cf 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -99,6 +99,10 @@ struct fwnode_operations { (fwnode ? (fwnode_has_op(fwnode, op) ? \ (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ -EINVAL) +#define fwnode_call_bool_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : false) : \ + false) #define fwnode_call_ptr_op(fwnode, op, ...) \ (fwnode_has_op(fwnode, op) ? \ (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8d9fe131a240..0ed8e41aaf11 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -268,6 +268,9 @@ struct hugetlbfs_sb_info { spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; + kuid_t uid; + kgid_t gid; + umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0b50e7b35ed4..648b34cabb38 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -234,7 +234,7 @@ struct kvm_vcpu { int guest_fpu_loaded, guest_xcr0_loaded; struct swait_queue_head wq; - struct pid *pid; + struct pid __rcu *pid; int sigset_active; sigset_t sigset; struct kvm_vcpu_stat stat; @@ -390,7 +390,7 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; + struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; /* @@ -404,7 +404,7 @@ struct kvm { int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; - struct kvm_io_bus *buses[KVM_NR_BUSES]; + struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_EVENTFD struct { spinlock_t lock; @@ -473,6 +473,12 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) +{ + return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock)); +} + static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case @@ -562,9 +568,8 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots[as_id], - srcu_read_lock_held(&kvm->srcu) - || lockdep_is_held(&kvm->slots_lock)); + return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) diff --git a/include/linux/net.h b/include/linux/net.h index abcfa46a2bd9..dda2cc939a53 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -274,6 +274,8 @@ do { \ #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) +#define net_get_random_once_wait(buf, nbytes) \ + get_random_once_wait((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); diff --git a/include/linux/ntb.h b/include/linux/ntb.h index de87ceac110e..609e232c00da 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -106,6 +108,7 @@ static inline char *ntb_topo_string(enum ntb_topo topo) * @NTB_SPEED_GEN1: Link is trained to gen1 speed. * @NTB_SPEED_GEN2: Link is trained to gen2 speed. * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + * @NTB_SPEED_GEN4: Link is trained to gen4 speed. */ enum ntb_speed { NTB_SPEED_AUTO = -1, @@ -113,6 +116,7 @@ enum ntb_speed { NTB_SPEED_GEN1 = 1, NTB_SPEED_GEN2 = 2, NTB_SPEED_GEN3 = 3, + NTB_SPEED_GEN4 = 4 }; /** @@ -140,6 +144,20 @@ enum ntb_width { }; /** + * enum ntb_default_port - NTB default port number + * @NTB_PORT_PRI_USD: Default port of the NTB_TOPO_PRI/NTB_TOPO_B2B_USD + * topologies + * @NTB_PORT_SEC_DSD: Default port of the NTB_TOPO_SEC/NTB_TOPO_B2B_DSD + * topologies + */ +enum ntb_default_port { + NTB_PORT_PRI_USD, + NTB_PORT_SEC_DSD +}; +#define NTB_DEF_PEER_CNT (1) +#define NTB_DEF_PEER_IDX (0) + +/** * struct ntb_client_ops - ntb client operations * @probe: Notify client of a new device. * @remove: Notify client to remove a device. @@ -162,10 +180,12 @@ static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) * struct ntb_ctx_ops - ntb driver context operations * @link_event: See ntb_link_event(). * @db_event: See ntb_db_event(). + * @msg_event: See ntb_msg_event(). */ struct ntb_ctx_ops { void (*link_event)(void *ctx); void (*db_event)(void *ctx, int db_vector); + void (*msg_event)(void *ctx); }; static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) @@ -174,18 +194,27 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) return /* ops->link_event && */ /* ops->db_event && */ + /* ops->msg_event && */ 1; } /** * struct ntb_ctx_ops - ntb device operations - * @mw_count: See ntb_mw_count(). - * @mw_get_range: See ntb_mw_get_range(). - * @mw_set_trans: See ntb_mw_set_trans(). - * @mw_clear_trans: See ntb_mw_clear_trans(). + * @port_number: See ntb_port_number(). + * @peer_port_count: See ntb_peer_port_count(). + * @peer_port_number: See ntb_peer_port_number(). + * @peer_port_idx: See ntb_peer_port_idx(). * @link_is_up: See ntb_link_is_up(). * @link_enable: See ntb_link_enable(). * @link_disable: See ntb_link_disable(). + * @mw_count: See ntb_mw_count(). + * @mw_get_align: See ntb_mw_get_align(). + * @mw_set_trans: See ntb_mw_set_trans(). + * @mw_clear_trans: See ntb_mw_clear_trans(). + * @peer_mw_count: See ntb_peer_mw_count(). + * @peer_mw_get_addr: See ntb_peer_mw_get_addr(). + * @peer_mw_set_trans: See ntb_peer_mw_set_trans(). + * @peer_mw_clear_trans:See ntb_peer_mw_clear_trans(). * @db_is_unsafe: See ntb_db_is_unsafe(). * @db_valid_mask: See ntb_db_valid_mask(). * @db_vector_count: See ntb_db_vector_count(). @@ -210,22 +239,43 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_addr: See ntb_peer_spad_addr(). * @peer_spad_read: See ntb_peer_spad_read(). * @peer_spad_write: See ntb_peer_spad_write(). + * @msg_count: See ntb_msg_count(). + * @msg_inbits: See ntb_msg_inbits(). + * @msg_outbits: See ntb_msg_outbits(). + * @msg_read_sts: See ntb_msg_read_sts(). + * @msg_clear_sts: See ntb_msg_clear_sts(). + * @msg_set_mask: See ntb_msg_set_mask(). + * @msg_clear_mask: See ntb_msg_clear_mask(). + * @msg_read: See ntb_msg_read(). + * @msg_write: See ntb_msg_write(). */ struct ntb_dev_ops { - int (*mw_count)(struct ntb_dev *ntb); - int (*mw_get_range)(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size); - int (*mw_set_trans)(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size); - int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + int (*port_number)(struct ntb_dev *ntb); + int (*peer_port_count)(struct ntb_dev *ntb); + int (*peer_port_number)(struct ntb_dev *ntb, int pidx); + int (*peer_port_idx)(struct ntb_dev *ntb, int port); - int (*link_is_up)(struct ntb_dev *ntb, + u64 (*link_is_up)(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width); int (*link_enable)(struct ntb_dev *ntb, enum ntb_speed max_speed, enum ntb_width max_width); int (*link_disable)(struct ntb_dev *ntb); + int (*mw_count)(struct ntb_dev *ntb, int pidx); + int (*mw_get_align)(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max); + int (*mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size); + int (*mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*peer_mw_count)(struct ntb_dev *ntb); + int (*peer_mw_get_addr)(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size); + int (*peer_mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size); + int (*peer_mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*db_is_unsafe)(struct ntb_dev *ntb); u64 (*db_valid_mask)(struct ntb_dev *ntb); int (*db_vector_count)(struct ntb_dev *ntb); @@ -252,32 +302,55 @@ struct ntb_dev_ops { int (*spad_is_unsafe)(struct ntb_dev *ntb); int (*spad_count)(struct ntb_dev *ntb); - u32 (*spad_read)(struct ntb_dev *ntb, int idx); - int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*spad_read)(struct ntb_dev *ntb, int sidx); + int (*spad_write)(struct ntb_dev *ntb, int sidx, u32 val); - int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + int (*peer_spad_addr)(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr); - u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); - int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx); + int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx, + u32 val); + + int (*msg_count)(struct ntb_dev *ntb); + u64 (*msg_inbits)(struct ntb_dev *ntb); + u64 (*msg_outbits)(struct ntb_dev *ntb); + u64 (*msg_read_sts)(struct ntb_dev *ntb); + int (*msg_clear_sts)(struct ntb_dev *ntb, u64 sts_bits); + int (*msg_set_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_clear_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_read)(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg); + int (*msg_write)(struct ntb_dev *ntb, int midx, int pidx, u32 msg); }; static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return - ops->mw_count && - ops->mw_get_range && - ops->mw_set_trans && - /* ops->mw_clear_trans && */ + /* Port operations are required for multiport devices */ + !ops->peer_port_count == !ops->port_number && + !ops->peer_port_number == !ops->port_number && + !ops->peer_port_idx == !ops->port_number && + + /* Link operations are required */ ops->link_is_up && ops->link_enable && ops->link_disable && + + /* One or both MW interfaces should be developed */ + ops->mw_count && + ops->mw_get_align && + (ops->mw_set_trans || + ops->peer_mw_set_trans) && + /* ops->mw_clear_trans && */ + ops->peer_mw_count && + ops->peer_mw_get_addr && + /* ops->peer_mw_clear_trans && */ + + /* Doorbell operations are mostly required */ /* ops->db_is_unsafe && */ ops->db_valid_mask && - /* both set, or both unset */ - (!ops->db_vector_count == !ops->db_vector_mask) && - + (!ops->db_vector_count == !ops->db_vector_mask) && ops->db_read && /* ops->db_set && */ ops->db_clear && @@ -291,13 +364,24 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->peer_db_read_mask && */ /* ops->peer_db_set_mask && */ /* ops->peer_db_clear_mask && */ - /* ops->spad_is_unsafe && */ - ops->spad_count && - ops->spad_read && - ops->spad_write && - /* ops->peer_spad_addr && */ - /* ops->peer_spad_read && */ - ops->peer_spad_write && + + /* Scrachpads interface is optional */ + /* !ops->spad_is_unsafe == !ops->spad_count && */ + !ops->spad_read == !ops->spad_count && + !ops->spad_write == !ops->spad_count && + /* !ops->peer_spad_addr == !ops->spad_count && */ + /* !ops->peer_spad_read == !ops->spad_count && */ + !ops->peer_spad_write == !ops->spad_count && + + /* Messaging interface is optional */ + !ops->msg_inbits == !ops->msg_count && + !ops->msg_outbits == !ops->msg_count && + !ops->msg_read_sts == !ops->msg_count && + !ops->msg_clear_sts == !ops->msg_count && + /* !ops->msg_set_mask == !ops->msg_count && */ + /* !ops->msg_clear_mask == !ops->msg_count && */ + !ops->msg_read == !ops->msg_count && + !ops->msg_write == !ops->msg_count && 1; } @@ -310,13 +394,12 @@ struct ntb_client { struct device_driver drv; const struct ntb_client_ops ops; }; - #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** * struct ntb_device - ntb device * @dev: Linux device object. - * @pdev: Pci device entry of the ntb. + * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. * @ops: See &ntb_dev_ops. * @ctx: See &ntb_ctx_ops. @@ -337,7 +420,6 @@ struct ntb_dev { /* block unregister until device is fully released */ struct completion released; }; - #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) /** @@ -434,86 +516,152 @@ void ntb_link_event(struct ntb_dev *ntb); * multiple interrupt vectors for doorbells, the vector number indicates which * vector received the interrupt. The vector number is relative to the first * vector used for doorbells, starting at zero, and must be less than - ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * ntb_db_vector_count(). The driver may call ntb_db_read() to check which * doorbell bits need service, and ntb_db_vector_mask() to determine which of * those bits are associated with the vector number. */ void ntb_db_event(struct ntb_dev *ntb, int vector); /** - * ntb_mw_count() - get the number of memory windows + * ntb_msg_event() - notify driver context of a message event * @ntb: NTB device context. * - * Hardware and topology may support a different number of memory windows. + * Notify the driver context of a message event. If hardware supports + * message registers, this event indicates, that a new message arrived in + * some incoming message register or last sent message couldn't be delivered. + * The events can be masked/unmasked by the methods ntb_msg_set_mask() and + * ntb_msg_clear_mask(). + */ +void ntb_msg_event(struct ntb_dev *ntb); + +/** + * ntb_default_port_number() - get the default local port number + * @ntb: NTB device context. * - * Return: the number of memory windows. + * If hardware driver doesn't specify port_number() callback method, the NTB + * is considered with just two ports. So this method returns default local + * port number in compliance with topology. + * + * NOTE Don't call this method directly. The ntb_port_number() function should + * be used instead. + * + * Return: the default local port number + */ +int ntb_default_port_number(struct ntb_dev *ntb); + +/** + * ntb_default_port_count() - get the default number of peer device ports + * @ntb: NTB device context. + * + * By default hardware driver supports just one peer device. + * + * NOTE Don't call this method directly. The ntb_peer_port_count() function + * should be used instead. + * + * Return: the default number of peer ports + */ +int ntb_default_peer_port_count(struct ntb_dev *ntb); + +/** + * ntb_default_peer_port_number() - get the default peer port by given index + * @ntb: NTB device context. + * @idx: Peer port index (should not differ from zero). + * + * By default hardware driver supports just one peer device, so this method + * shall return the corresponding value from enum ntb_default_port. + * + * NOTE Don't call this method directly. The ntb_peer_port_number() function + * should be used instead. + * + * Return: the peer device port or negative value indicating an error + */ +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx); + +/** + * ntb_default_peer_port_idx() - get the default peer device port index by + * given port number + * @ntb: NTB device context. + * @port: Peer port number (should be one of enum ntb_default_port). + * + * By default hardware driver supports just one peer device, so while + * specified port-argument indicates peer port from enum ntb_default_port, + * the return value shall be zero. + * + * NOTE Don't call this method directly. The ntb_peer_port_idx() function + * should be used instead. + * + * Return: the peer port index or negative value indicating an error + */ +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port); + +/** + * ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Hardware must support at least simple two-ports ntb connection + * + * Return: the local port number */ -static inline int ntb_mw_count(struct ntb_dev *ntb) +static inline int ntb_port_number(struct ntb_dev *ntb) { - return ntb->ops->mw_count(ntb); + if (!ntb->ops->port_number) + return ntb_default_port_number(ntb); + + return ntb->ops->port_number(ntb); } /** - * ntb_mw_get_range() - get the range of a memory window + * ntb_peer_port_count() - get the number of peer device ports * @ntb: NTB device context. - * @idx: Memory window number. - * @base: OUT - the base address for mapping the memory window - * @size: OUT - the size for mapping the memory window - * @align: OUT - the base alignment for translating the memory window - * @align_size: OUT - the size alignment for translating the memory window * - * Get the range of a memory window. NULL may be given for any output - * parameter if the value is not needed. The base and size may be used for - * mapping the memory window, to access the peer memory. The alignment and - * size may be used for translating the memory window, for the peer to access - * memory on the local system. + * Hardware may support an access to memory of several remote domains + * over multi-port NTB devices. This method returns the number of peers, + * local device can have shared memory with. * - * Return: Zero on success, otherwise an error number. + * Return: the number of peer ports */ -static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size) +static inline int ntb_peer_port_count(struct ntb_dev *ntb) { - return ntb->ops->mw_get_range(ntb, idx, base, size, - align, align_size); + if (!ntb->ops->peer_port_count) + return ntb_default_peer_port_count(ntb); + + return ntb->ops->peer_port_count(ntb); } /** - * ntb_mw_set_trans() - set the translation of a memory window + * ntb_peer_port_number() - get the peer port by given index * @ntb: NTB device context. - * @idx: Memory window number. - * @addr: The dma address local memory to expose to the peer. - * @size: The size of the local memory to expose to the peer. + * @pidx: Peer port index. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Peer ports are continuously enumerated by NTB API logic, so this method + * lets to retrieve port real number by its index. * - * Return: Zero on success, otherwise an error number. + * Return: the peer device port or negative value indicating an error */ -static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size) +static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) { - return ntb->ops->mw_set_trans(ntb, idx, addr, size); + if (!ntb->ops->peer_port_number) + return ntb_default_peer_port_number(ntb, pidx); + + return ntb->ops->peer_port_number(ntb, pidx); } /** - * ntb_mw_clear_trans() - clear the translation of a memory window + * ntb_peer_port_idx() - get the peer device port index by given port number * @ntb: NTB device context. - * @idx: Memory window number. + * @port: Peer port number. * - * Clear the translation of a memory window. The peer may no longer access - * local memory through the window. + * Inverse operation of ntb_peer_port_number(), so one can get port index + * by specified port number. * - * Return: Zero on success, otherwise an error number. + * Return: the peer port index or negative value indicating an error */ -static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port) { - if (!ntb->ops->mw_clear_trans) - return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + if (!ntb->ops->peer_port_idx) + return ntb_default_peer_port_idx(ntb, port); - return ntb->ops->mw_clear_trans(ntb, idx); + return ntb->ops->peer_port_idx(ntb, port); } /** @@ -526,25 +674,26 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * state once after every link event. It is safe to query the link state in * the context of the link event callback. * - * Return: One if the link is up, zero if the link is down, otherwise a - * negative value indicating the error number. + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. */ -static inline int ntb_link_is_up(struct ntb_dev *ntb, +static inline u64 ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { return ntb->ops->link_is_up(ntb, speed, width); } /** - * ntb_link_enable() - enable the link on the secondary side of the ntb + * ntb_link_enable() - enable the local port ntb connection * @ntb: NTB device context. * @max_speed: The maximum link speed expressed as PCIe generation number. * @max_width: The maximum link width expressed as the number of PCIe lanes. * - * Enable the link on the secondary side of the ntb. This can only be done - * from the primary side of the ntb in primary or b2b topology. The ntb device - * should train the link to its maximum speed and width, or the requested speed - * and width, whichever is smaller, if supported. + * Enable the NTB/PCIe link on the local or remote (for bridge-to-bridge + * topology) side of the bridge. If it's supported the ntb device should train + * the link to its maximum speed and width, or the requested speed and width, + * whichever is smaller. Some hardware doesn't support PCIe link training, so + * the last two arguments will be ignored then. * * Return: Zero on success, otherwise an error number. */ @@ -556,14 +705,14 @@ static inline int ntb_link_enable(struct ntb_dev *ntb, } /** - * ntb_link_disable() - disable the link on the secondary side of the ntb + * ntb_link_disable() - disable the local port ntb connection * @ntb: NTB device context. * - * Disable the link on the secondary side of the ntb. This can only be - * done from the primary side of the ntb in primary or b2b topology. The ntb - * device should disable the link. Returning from this call must indicate that - * a barrier has passed, though with no more writes may pass in either - * direction across the link, except if this call returns an error number. + * Disable the link on the local or remote (for b2b topology) of the ntb. + * The ntb device should disable the link. Returning from this call must + * indicate that a barrier has passed, though with no more writes may pass in + * either direction across the link, except if this call returns an error + * number. * * Return: Zero on success, otherwise an error number. */ @@ -573,6 +722,183 @@ static inline int ntb_link_disable(struct ntb_dev *ntb) } /** + * ntb_mw_count() - get the number of inbound memory windows, which could + * be created for a specified peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * + * Hardware and topology may support a different number of memory windows. + * Moreover different peer devices can support different number of memory + * windows. Simply speaking this method returns the number of possible inbound + * memory windows to share with specified peer device. + * + * Return: the number of memory windows. + */ +static inline int ntb_mw_count(struct ntb_dev *ntb, int pidx) +{ + return ntb->ops->mw_count(ntb, pidx); +} + +/** + * ntb_mw_get_align() - get the restriction parameters of inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * Get the alignments of an inbound memory window with specified index. + * NULL may be given for any output parameter if the value is not needed. + * The alignment and size parameters may be used for allocation of proper + * shared memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) +{ + return ntb->ops->mw_get_align(ntb, pidx, widx, addr_align, size_align, + size_max); +} + +/** + * ntb_mw_set_trans() - set the translation of an inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr: The dma address of local memory to expose to the peer. + * @size: The size of the local memory to expose to the peer. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * and size must be aligned in compliance with restrictions of + * ntb_mw_get_align(). The region size should not exceed the size_max parameter + * of that method. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size) +{ + if (!ntb->ops->mw_set_trans) + return 0; + + return ntb->ops->mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_mw_clear_trans() - clear the translation address of an inbound memory + * window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of an inbound memory window. The peer may no longer + * access local memory through the window. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int pidx, int widx) +{ + if (!ntb->ops->mw_clear_trans) + return ntb_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, pidx, widx); +} + +/** + * ntb_peer_mw_count() - get the number of outbound memory windows, which could + * be mapped to access a shared memory + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * This method returns the number of outbound memory windows supported by + * local device. + * + * Return: the number of memory windows. + */ +static inline int ntb_peer_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->peer_mw_count(ntb); +} + +/** + * ntb_peer_mw_get_addr() - get map address of an outbound memory window + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Get base and size of memory region to map. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + return ntb->ops->peer_mw_get_addr(ntb, widx, base, size); +} + +/** + * ntb_peer_mw_set_trans() - set a translation address of a memory window + * retrieved from a peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * Set the translation of an outbound memory window. The local device may + * access shared memory allocated by a peer device sent the address. + * + * This method may not be implemented due to the hardware specific memory + * windows interface, so a translation address can be only set on the side, + * where shared memory (inbound memory windows) is allocated. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + if (!ntb->ops->peer_mw_set_trans) + return 0; + + return ntb->ops->peer_mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_peer_mw_clear_trans() - clear the translation address of an outbound + * memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of a outbound memory window. The local device may no + * longer access a shared memory through the window. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + if (!ntb->ops->peer_mw_clear_trans) + return ntb_peer_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->peer_mw_clear_trans(ntb, pidx, widx); +} + +/** * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell * @ntb: NTB device context. * @@ -900,47 +1226,58 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) * @ntb: NTB device context. * * Hardware and topology may support a different number of scratchpads. + * Although it must be the same for all ports per NTB device. * * Return: the number of scratchpads. */ static inline int ntb_spad_count(struct ntb_dev *ntb) { + if (!ntb->ops->spad_count) + return 0; + return ntb->ops->spad_count(ntb); } /** * ntb_spad_read() - read the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * * Read the local scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int sidx) { - return ntb->ops->spad_read(ntb, idx); + if (!ntb->ops->spad_read) + return ~(u32)0; + + return ntb->ops->spad_read(ntb, sidx); } /** * ntb_spad_write() - write the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the local scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) { - return ntb->ops->spad_write(ntb, idx, val); + if (!ntb->ops->spad_write) + return -EINVAL; + + return ntb->ops->spad_write(ntb, sidx, val); } /** * ntb_peer_spad_addr() - address of the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * * Return the address of the peer doorbell register. This may be used, for @@ -948,45 +1285,213 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { if (!ntb->ops->peer_spad_addr) return -EINVAL; - return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); + return ntb->ops->peer_spad_addr(ntb, pidx, sidx, spad_addr); } /** * ntb_peer_spad_read() - read the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * * Read the peer scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { if (!ntb->ops->peer_spad_read) - return 0; + return ~(u32)0; - return ntb->ops->peer_spad_read(ntb, idx); + return ntb->ops->peer_spad_read(ntb, pidx, sidx); } /** * ntb_peer_spad_write() - write the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the peer scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx, + u32 val) +{ + if (!ntb->ops->peer_spad_write) + return -EINVAL; + + return ntb->ops->peer_spad_write(ntb, pidx, sidx, val); +} + +/** + * ntb_msg_count() - get the number of message registers + * @ntb: NTB device context. + * + * Hardware may support a different number of message registers. + * + * Return: the number of message registers. + */ +static inline int ntb_msg_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_count) + return 0; + + return ntb->ops->msg_count(ntb); +} + +/** + * ntb_msg_inbits() - get a bitfield of inbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to inbound message registers. + * + * Return: bitfield of inbound message registers. + */ +static inline u64 ntb_msg_inbits(struct ntb_dev *ntb) { - return ntb->ops->peer_spad_write(ntb, idx, val); + if (!ntb->ops->msg_inbits) + return 0; + + return ntb->ops->msg_inbits(ntb); +} + +/** + * ntb_msg_outbits() - get a bitfield of outbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to outbound message registers. + * + * Return: bitfield of outbound message registers. + */ +static inline u64 ntb_msg_outbits(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_outbits) + return 0; + + return ntb->ops->msg_outbits(ntb); +} + +/** + * ntb_msg_read_sts() - read the message registers status + * @ntb: NTB device context. + * + * Read the status of message register. Inbound and outbound message registers + * related bits can be filtered by masks retrieved from ntb_msg_inbits() and + * ntb_msg_outbits(). + * + * Return: status bits of message registers + */ +static inline u64 ntb_msg_read_sts(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_read_sts) + return 0; + + return ntb->ops->msg_read_sts(ntb); +} + +/** + * ntb_msg_clear_sts() - clear status bits of message registers + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + if (!ntb->ops->msg_clear_sts) + return -EINVAL; + + return ntb->ops->msg_clear_sts(ntb, sts_bits); +} + +/** + * ntb_msg_set_mask() - set mask of message register status bits + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message registers status bits from raising the message event. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_set_mask) + return -EINVAL; + + return ntb->ops->msg_set_mask(ntb, mask_bits); +} + +/** + * ntb_msg_clear_mask() - clear message registers mask + * @ntb: NTB device context. + * @mask_bits: Mask bits to clear. + * + * Clear bits in the message events mask register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_clear_mask) + return -EINVAL; + + return ntb->ops->msg_clear_mask(ntb, mask_bits); +} + +/** + * ntb_msg_read() - read message register with specified index + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register. Source port index of a + * message is retrieved as well. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, + u32 *msg) +{ + if (!ntb->ops->msg_read) + return -EINVAL; + + return ntb->ops->msg_read(ntb, midx, pidx, msg); +} + +/** + * ntb_msg_write() - write data to the specified message register + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Send data to a specified peer device using the defined message register. + * Message event can be raised if the midx registers isn't empty while + * calling this method and the corresponding interrupt isn't masked. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, + u32 msg) +{ + if (!ntb->ops->msg_write) + return -EINVAL; + + return ntb->ops->msg_write(ntb, midx, pidx, msg); } #endif diff --git a/include/linux/once.h b/include/linux/once.h index 285f12cb40e6..9c98aaa87cbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -53,5 +53,7 @@ void __do_once_done(bool *done, struct static_key *once_key, #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) +#define get_random_once_wait(buf, nbytes) \ + DO_ONCE(get_random_bytes_wait, (buf), (nbytes)) \ #endif /* _LINUX_ONCE_H */ diff --git a/include/linux/random.h b/include/linux/random.h index 1fa0dc880bd7..eafea6a09361 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern void add_input_randomness(unsigned int type, unsigned int code, extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); +extern int wait_for_random_bytes(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); @@ -78,6 +79,31 @@ static inline unsigned long get_random_canary(void) return val & CANARY_MASK; } +/* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). + * Returns the result of the call to wait_for_random_bytes. */ +static inline int get_random_bytes_wait(void *buf, int nbytes) +{ + int ret = wait_for_random_bytes(); + if (unlikely(ret)) + return ret; + get_random_bytes(buf, nbytes); + return 0; +} + +#define declare_get_random_var_wait(var) \ + static inline int get_random_ ## var ## _wait(var *out) { \ + int ret = wait_for_random_bytes(); \ + if (unlikely(ret)) \ + return ret; \ + *out = get_random_ ## var(); \ + return 0; \ + } +declare_get_random_var_wait(u32) +declare_get_random_var_wait(u64) +declare_get_random_var_wait(int) +declare_get_random_var_wait(long) +#undef declare_get_random_var + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 3822d749fc9e..2ba9ec93423f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -974,7 +974,7 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; - int fail_nth; + unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call diff --git a/include/linux/string.h b/include/linux/string.h index 96f5a5fd0377..a467e617eeb0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -137,6 +137,7 @@ extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); +extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); @@ -202,17 +203,6 @@ void __read_overflow2(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) -__FORTIFY_INLINE char *strcpy(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __builtin_strcpy(p, q); - if (strscpy(p, q, p_size < q_size ? p_size : q_size) < 0) - fortify_panic(__func__); - return p; -} - __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -391,6 +381,18 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) fortify_panic(__func__); return __real_kmemdup(p, size, gfp); } + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strcpy(p, q); + memcpy(p, q, strlen(q) + 1); + return p; +} + #endif #endif /* _LINUX_STRING_H_ */ diff --git a/include/net/9p/client.h b/include/net/9p/client.h index b582339ccef5..7af9d769b97d 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -157,6 +157,18 @@ struct p9_client { enum p9_trans_status status; void *trans; + union { + struct { + int rfd; + int wfd; + } fd; + struct { + u16 port; + bool privport; + + } tcp; + } trans_opts; + struct p9_idpool *fidpool; struct list_head fidlist; @@ -213,6 +225,7 @@ struct p9_dirent { struct iov_iter; +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name); diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index 5122b5e40f78..1625fb842ac4 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -62,6 +62,7 @@ struct p9_trans_module { int (*cancelled)(struct p9_client *, struct p9_req_t *req); int (*zc_request)(struct p9_client *, struct p9_req_t *, struct iov_iter *, struct iov_iter *, int , int, int); + int (*show_options)(struct seq_file *, struct p9_client *); }; void v9fs_register_trans(struct p9_trans_module *m); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c0b6dfec5f87..6cd63c18708a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -927,6 +927,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_CMMA_MIGRATION 145 #define KVM_CAP_PPC_FWNMI 146 #define KVM_CAP_PPC_SMT_POSSIBLE 147 +#define KVM_CAP_HYPERV_SYNIC2 148 +#define KVM_CAP_HYPERV_VP_INDEX 149 #ifdef KVM_CAP_IRQ_ROUTING @@ -1351,7 +1353,7 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_X86_SMM */ #define KVM_SMI _IO(KVMIO, 0xb7) /* Available with KVM_CAP_S390_CMMA_MIGRATION */ -#define KVM_S390_GET_CMMA_BITS _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log) +#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9bbd33497d3d..e833ed914358 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -377,10 +377,22 @@ static void bpf_evict_inode(struct inode *inode) bpf_any_put(inode->i_private, type); } +/* + * Display the mount options in /proc/mounts. + */ +static int bpf_show_options(struct seq_file *m, struct dentry *root) +{ + umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; + + if (mode != S_IRWXUGO) + seq_printf(m, ",mode=%o", mode); + return 0; +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, - .show_options = generic_show_options, + .show_options = bpf_show_options, .evict_inode = bpf_evict_inode, }; @@ -434,8 +446,6 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; int ret; - save_mount_options(sb, data); - ret = bpf_parse_options(data, &opts); if (ret) return ret; diff --git a/kernel/kmod.c b/kernel/kmod.c index ff68198fe83b..6d016c5d97c8 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -68,6 +68,7 @@ static DECLARE_RWSEM(umhelper_sem); */ #define MAX_KMOD_CONCURRENT 50 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT); +static DECLARE_WAIT_QUEUE_HEAD(kmod_wq); /* modprobe_path is set via /proc/sys. @@ -140,7 +141,6 @@ int __request_module(bool wait, const char *fmt, ...) va_list args; char module_name[MODULE_NAME_LEN]; int ret; - static int kmod_loop_msg; /* * We don't allow synchronous module loading from async. Module @@ -164,14 +164,11 @@ int __request_module(bool wait, const char *fmt, ...) return ret; if (atomic_dec_if_positive(&kmod_concurrent_max) < 0) { - /* We may be blaming an innocent here, but unlikely */ - if (kmod_loop_msg < 5) { - printk(KERN_ERR - "request_module: runaway loop modprobe %s\n", - module_name); - kmod_loop_msg++; - } - return -ENOMEM; + pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...", + atomic_read(&kmod_concurrent_max), + MAX_KMOD_CONCURRENT, module_name); + wait_event_interruptible(kmod_wq, + atomic_dec_if_positive(&kmod_concurrent_max) >= 0); } trace_module_request(module_name, wait, _RET_IP_); @@ -179,6 +176,7 @@ int __request_module(bool wait, const char *fmt, ...) ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); atomic_inc(&kmod_concurrent_max); + wake_up(&kmod_wq); return ret; } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 076a2e31951c..29a397067ffa 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -610,6 +610,11 @@ static int sugov_start(struct cpufreq_policy *policy) sg_cpu->sg_policy = sg_policy; sg_cpu->flags = SCHED_CPUFREQ_RT; sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + } + + for_each_cpu(cpu, policy->cpus) { + struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, policy_is_shared(policy) ? sugov_update_shared : diff --git a/kernel/watchdog.c b/kernel/watchdog.c index cabe3e9fb620..06d3389bca0d 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -9,7 +9,7 @@ * to those contributors as well. */ -#define pr_fmt(fmt) "NMI watchdog: " fmt +#define pr_fmt(fmt) "watchdog: " fmt #include <linux/mm.h> #include <linux/cpu.h> diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b0d01c6d4e03..98fe715522e8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1223,6 +1223,34 @@ config STACKTRACE It is also used by various kernel debugging features that require stack trace generation. +config WARN_ALL_UNSEEDED_RANDOM + bool "Warn for all uses of unseeded randomness" + default n + help + Some parts of the kernel contain bugs relating to their use of + cryptographically secure random numbers before it's actually possible + to generate those numbers securely. This setting ensures that these + flaws don't go unnoticed, by enabling a message, should this ever + occur. This will allow people with obscure setups to know when things + are going wrong, so that they might contact developers about fixing + it. + + Unfortunately, on some models of some architectures getting + a fully seeded CRNG is extremely difficult, and so this can + result in dmesg getting spammed for a surprisingly long + time. This is really bad from a security perspective, and + so architecture maintainers really need to do what they can + to get the CRNG seeded sooner after the system is booted. + However, since users can not do anything actionble to + address this, by default the kernel will issue only a single + warning for the first use of unseeded randomness. + + Say Y here if you want to receive warnings for all uses of + unseeded randomness. This will be of use primarily for + those developers interersted in improving the security of + Linux kernels running on their architecture (or + subarchitecture). + config DEBUG_KOBJECT bool "kobject debugging" depends on DEBUG_KERNEL @@ -1847,6 +1875,33 @@ config BUG_ON_DATA_CORRUPTION If unsure, say N. +config TEST_KMOD + tristate "kmod stress tester" + default n + depends on m + depends on BLOCK && (64BIT || LBDAF) # for XFS, BTRFS + depends on NETDEVICES && NET_CORE && INET # for TUN + select TEST_LKM + select XFS_FS + select TUN + select BTRFS_FS + help + Test the kernel's module loading mechanism: kmod. kmod implements + support to load modules using the Linux kernel's usermode helper. + This test provides a series of tests against kmod. + + Although technically you can either build test_kmod as a module or + into the kernel we disallow building it into the kernel since + it stress tests request_module() and this will very likely cause + some issues by taking over precious threads available from other + module load requests, ultimately this could be fatal. + + To run tests run: + + tools/testing/selftests/kmod/kmod.sh --help + + If unsure, say N. + source "samples/Kconfig" source "lib/Kconfig.kgdb" diff --git a/lib/Makefile b/lib/Makefile index 85e91e51a9fe..40c18372b301 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -61,6 +61,7 @@ obj-$(CONFIG_TEST_PRINTF) += test_printf.o obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o obj-$(CONFIG_TEST_UUID) += test_uuid.o obj-$(CONFIG_TEST_PARMAN) += test_parman.o +obj-$(CONFIG_TEST_KMOD) += test_kmod.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index fd70c0e0e673..62ab629f51ca 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -153,8 +153,10 @@ static __init void test_atomic64(void) long long v0 = 0xaaa31337c001d00dLL; long long v1 = 0xdeadbeefdeafcafeLL; long long v2 = 0xfaceabadf00df001LL; + long long v3 = 0x8000000000000000LL; long long onestwos = 0x1111111122222222LL; long long one = 1LL; + int r_int; atomic64_t v = ATOMIC64_INIT(v0); long long r = v0; @@ -240,6 +242,11 @@ static __init void test_atomic64(void) BUG_ON(!atomic64_inc_not_zero(&v)); r += one; BUG_ON(v.counter != r); + + /* Confirm the return value fits in an int, even if the value doesn't */ + INIT(v3); + r_int = atomic64_inc_not_zero(&v); + BUG_ON(!r_int); } static __init int test_atomics_init(void) diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 09ac73c177fd..7d315fdb9f13 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -107,9 +107,12 @@ static inline bool fail_stacktrace(struct fault_attr *attr) bool should_fail(struct fault_attr *attr, ssize_t size) { - if (in_task() && current->fail_nth) { - if (--current->fail_nth == 0) + if (in_task()) { + unsigned int fail_nth = READ_ONCE(current->fail_nth); + + if (fail_nth && !WRITE_ONCE(current->fail_nth, fail_nth - 1)) goto fail; + return false; } diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 42466c167257..707ca5d677c6 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -234,7 +234,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, INIT_LIST_HEAD(&tbl->walkers); - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); + tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); diff --git a/lib/test_kmod.c b/lib/test_kmod.c new file mode 100644 index 000000000000..6c1d678bcf8b --- /dev/null +++ b/lib/test_kmod.c @@ -0,0 +1,1246 @@ +/* + * kmod stress test driver + * + * Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org> + * + * 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; or, when distributed separately from the Linux kernel or + * when incorporated into other software packages, subject to the following + * license: + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of copyleft-next (version 0.3.1 or later) as published + * at http://copyleft-next.org/. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +/* + * This driver provides an interface to trigger and test the kernel's + * module loader through a series of configurations and a few triggers. + * To test this driver use the following script as root: + * + * tools/testing/selftests/kmod/kmod.sh --help + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kmod.h> +#include <linux/printk.h> +#include <linux/kthread.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> +#include <linux/device.h> + +#define TEST_START_NUM_THREADS 50 +#define TEST_START_DRIVER "test_module" +#define TEST_START_TEST_FS "xfs" +#define TEST_START_TEST_CASE TEST_KMOD_DRIVER + + +static bool force_init_test = false; +module_param(force_init_test, bool_enable_only, 0644); +MODULE_PARM_DESC(force_init_test, + "Force kicking a test immediately after driver loads"); + +/* + * For device allocation / registration + */ +static DEFINE_MUTEX(reg_dev_mutex); +static LIST_HEAD(reg_test_devs); + +/* + * num_test_devs actually represents the *next* ID of the next + * device we will allow to create. + */ +static int num_test_devs; + +/** + * enum kmod_test_case - linker table test case + * + * If you add a test case, please be sure to review if you need to se + * @need_mod_put for your tests case. + * + * @TEST_KMOD_DRIVER: stress tests request_module() + * @TEST_KMOD_FS_TYPE: stress tests get_fs_type() + */ +enum kmod_test_case { + __TEST_KMOD_INVALID = 0, + + TEST_KMOD_DRIVER, + TEST_KMOD_FS_TYPE, + + __TEST_KMOD_MAX, +}; + +struct test_config { + char *test_driver; + char *test_fs; + unsigned int num_threads; + enum kmod_test_case test_case; + int test_result; +}; + +struct kmod_test_device; + +/** + * kmod_test_device_info - thread info + * + * @ret_sync: return value if request_module() is used, sync request for + * @TEST_KMOD_DRIVER + * @fs_sync: return value of get_fs_type() for @TEST_KMOD_FS_TYPE + * @thread_idx: thread ID + * @test_dev: test device test is being performed under + * @need_mod_put: Some tests (get_fs_type() is one) requires putting the module + * (module_put(fs_sync->owner)) when done, otherwise you will not be able + * to unload the respective modules and re-test. We use this to keep + * accounting of when we need this and to help out in case we need to + * error out and deal with module_put() on error. + */ +struct kmod_test_device_info { + int ret_sync; + struct file_system_type *fs_sync; + struct task_struct *task_sync; + unsigned int thread_idx; + struct kmod_test_device *test_dev; + bool need_mod_put; +}; + +/** + * kmod_test_device - test device to help test kmod + * + * @dev_idx: unique ID for test device + * @config: configuration for the test + * @misc_dev: we use a misc device under the hood + * @dev: pointer to misc_dev's own struct device + * @config_mutex: protects configuration of test + * @trigger_mutex: the test trigger can only be fired once at a time + * @thread_lock: protects @done count, and the @info per each thread + * @done: number of threads which have completed or failed + * @test_is_oom: when we run out of memory, use this to halt moving forward + * @kthreads_done: completion used to signal when all work is done + * @list: needed to be part of the reg_test_devs + * @info: array of info for each thread + */ +struct kmod_test_device { + int dev_idx; + struct test_config config; + struct miscdevice misc_dev; + struct device *dev; + struct mutex config_mutex; + struct mutex trigger_mutex; + struct mutex thread_mutex; + + unsigned int done; + + bool test_is_oom; + struct completion kthreads_done; + struct list_head list; + + struct kmod_test_device_info *info; +}; + +static const char *test_case_str(enum kmod_test_case test_case) +{ + switch (test_case) { + case TEST_KMOD_DRIVER: + return "TEST_KMOD_DRIVER"; + case TEST_KMOD_FS_TYPE: + return "TEST_KMOD_FS_TYPE"; + default: + return "invalid"; + } +} + +static struct miscdevice *dev_to_misc_dev(struct device *dev) +{ + return dev_get_drvdata(dev); +} + +static struct kmod_test_device *misc_dev_to_test_dev(struct miscdevice *misc_dev) +{ + return container_of(misc_dev, struct kmod_test_device, misc_dev); +} + +static struct kmod_test_device *dev_to_test_dev(struct device *dev) +{ + struct miscdevice *misc_dev; + + misc_dev = dev_to_misc_dev(dev); + + return misc_dev_to_test_dev(misc_dev); +} + +/* Must run with thread_mutex held */ +static void kmod_test_done_check(struct kmod_test_device *test_dev, + unsigned int idx) +{ + struct test_config *config = &test_dev->config; + + test_dev->done++; + dev_dbg(test_dev->dev, "Done thread count: %u\n", test_dev->done); + + if (test_dev->done == config->num_threads) { + dev_info(test_dev->dev, "Done: %u threads have all run now\n", + test_dev->done); + dev_info(test_dev->dev, "Last thread to run: %u\n", idx); + complete(&test_dev->kthreads_done); + } +} + +static void test_kmod_put_module(struct kmod_test_device_info *info) +{ + struct kmod_test_device *test_dev = info->test_dev; + struct test_config *config = &test_dev->config; + + if (!info->need_mod_put) + return; + + switch (config->test_case) { + case TEST_KMOD_DRIVER: + break; + case TEST_KMOD_FS_TYPE: + if (info && info->fs_sync && info->fs_sync->owner) + module_put(info->fs_sync->owner); + break; + default: + BUG(); + } + + info->need_mod_put = true; +} + +static int run_request(void *data) +{ + struct kmod_test_device_info *info = data; + struct kmod_test_device *test_dev = info->test_dev; + struct test_config *config = &test_dev->config; + + switch (config->test_case) { + case TEST_KMOD_DRIVER: + info->ret_sync = request_module("%s", config->test_driver); + break; + case TEST_KMOD_FS_TYPE: + info->fs_sync = get_fs_type(config->test_fs); + info->need_mod_put = true; + break; + default: + /* __trigger_config_run() already checked for test sanity */ + BUG(); + return -EINVAL; + } + + dev_dbg(test_dev->dev, "Ran thread %u\n", info->thread_idx); + + test_kmod_put_module(info); + + mutex_lock(&test_dev->thread_mutex); + info->task_sync = NULL; + kmod_test_done_check(test_dev, info->thread_idx); + mutex_unlock(&test_dev->thread_mutex); + + return 0; +} + +static int tally_work_test(struct kmod_test_device_info *info) +{ + struct kmod_test_device *test_dev = info->test_dev; + struct test_config *config = &test_dev->config; + int err_ret = 0; + + switch (config->test_case) { + case TEST_KMOD_DRIVER: + /* + * Only capture errors, if one is found that's + * enough, for now. + */ + if (info->ret_sync != 0) + err_ret = info->ret_sync; + dev_info(test_dev->dev, + "Sync thread %d return status: %d\n", + info->thread_idx, info->ret_sync); + break; + case TEST_KMOD_FS_TYPE: + /* For now we make this simple */ + if (!info->fs_sync) + err_ret = -EINVAL; + dev_info(test_dev->dev, "Sync thread %u fs: %s\n", + info->thread_idx, info->fs_sync ? config->test_fs : + "NULL"); + break; + default: + BUG(); + } + + return err_ret; +} + +/* + * XXX: add result option to display if all errors did not match. + * For now we just keep any error code if one was found. + * + * If this ran it means *all* tasks were created fine and we + * are now just collecting results. + * + * Only propagate errors, do not override with a subsequent sucess case. + */ +static void tally_up_work(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + struct kmod_test_device_info *info; + unsigned int idx; + int err_ret = 0; + int ret = 0; + + mutex_lock(&test_dev->thread_mutex); + + dev_info(test_dev->dev, "Results:\n"); + + for (idx=0; idx < config->num_threads; idx++) { + info = &test_dev->info[idx]; + ret = tally_work_test(info); + if (ret) + err_ret = ret; + } + + /* + * Note: request_module() returns 256 for a module not found even + * though modprobe itself returns 1. + */ + config->test_result = err_ret; + + mutex_unlock(&test_dev->thread_mutex); +} + +static int try_one_request(struct kmod_test_device *test_dev, unsigned int idx) +{ + struct kmod_test_device_info *info = &test_dev->info[idx]; + int fail_ret = -ENOMEM; + + mutex_lock(&test_dev->thread_mutex); + + info->thread_idx = idx; + info->test_dev = test_dev; + info->task_sync = kthread_run(run_request, info, "%s-%u", + KBUILD_MODNAME, idx); + + if (!info->task_sync || IS_ERR(info->task_sync)) { + test_dev->test_is_oom = true; + dev_err(test_dev->dev, "Setting up thread %u failed\n", idx); + info->task_sync = NULL; + goto err_out; + } else + dev_dbg(test_dev->dev, "Kicked off thread %u\n", idx); + + mutex_unlock(&test_dev->thread_mutex); + + return 0; + +err_out: + info->ret_sync = fail_ret; + mutex_unlock(&test_dev->thread_mutex); + + return fail_ret; +} + +static void test_dev_kmod_stop_tests(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + struct kmod_test_device_info *info; + unsigned int i; + + dev_info(test_dev->dev, "Ending request_module() tests\n"); + + mutex_lock(&test_dev->thread_mutex); + + for (i=0; i < config->num_threads; i++) { + info = &test_dev->info[i]; + if (info->task_sync && !IS_ERR(info->task_sync)) { + dev_info(test_dev->dev, + "Stopping still-running thread %i\n", i); + kthread_stop(info->task_sync); + } + + /* + * info->task_sync is well protected, it can only be + * NULL or a pointer to a struct. If its NULL we either + * never ran, or we did and we completed the work. Completed + * tasks *always* put the module for us. This is a sanity + * check -- just in case. + */ + if (info->task_sync && info->need_mod_put) + test_kmod_put_module(info); + } + + mutex_unlock(&test_dev->thread_mutex); +} + +/* + * Only wait *iff* we did not run into any errors during all of our thread + * set up. If run into any issues we stop threads and just bail out with + * an error to the trigger. This also means we don't need any tally work + * for any threads which fail. + */ +static int try_requests(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + unsigned int idx; + int ret; + bool any_error = false; + + for (idx=0; idx < config->num_threads; idx++) { + if (test_dev->test_is_oom) { + any_error = true; + break; + } + + ret = try_one_request(test_dev, idx); + if (ret) { + any_error = true; + break; + } + } + + if (!any_error) { + test_dev->test_is_oom = false; + dev_info(test_dev->dev, + "No errors were found while initializing threads\n"); + wait_for_completion(&test_dev->kthreads_done); + tally_up_work(test_dev); + } else { + test_dev->test_is_oom = true; + dev_info(test_dev->dev, + "At least one thread failed to start, stop all work\n"); + test_dev_kmod_stop_tests(test_dev); + return -ENOMEM; + } + + return 0; +} + +static int run_test_driver(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + + dev_info(test_dev->dev, "Test case: %s (%u)\n", + test_case_str(config->test_case), + config->test_case); + dev_info(test_dev->dev, "Test driver to load: %s\n", + config->test_driver); + dev_info(test_dev->dev, "Number of threads to run: %u\n", + config->num_threads); + dev_info(test_dev->dev, "Thread IDs will range from 0 - %u\n", + config->num_threads - 1); + + return try_requests(test_dev); +} + +static int run_test_fs_type(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + + dev_info(test_dev->dev, "Test case: %s (%u)\n", + test_case_str(config->test_case), + config->test_case); + dev_info(test_dev->dev, "Test filesystem to load: %s\n", + config->test_fs); + dev_info(test_dev->dev, "Number of threads to run: %u\n", + config->num_threads); + dev_info(test_dev->dev, "Thread IDs will range from 0 - %u\n", + config->num_threads - 1); + + return try_requests(test_dev); +} + +static ssize_t config_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + int len = 0; + + mutex_lock(&test_dev->config_mutex); + + len += snprintf(buf, PAGE_SIZE, + "Custom trigger configuration for: %s\n", + dev_name(dev)); + + len += snprintf(buf+len, PAGE_SIZE - len, + "Number of threads:\t%u\n", + config->num_threads); + + len += snprintf(buf+len, PAGE_SIZE - len, + "Test_case:\t%s (%u)\n", + test_case_str(config->test_case), + config->test_case); + + if (config->test_driver) + len += snprintf(buf+len, PAGE_SIZE - len, + "driver:\t%s\n", + config->test_driver); + else + len += snprintf(buf+len, PAGE_SIZE - len, + "driver:\tEMTPY\n"); + + if (config->test_fs) + len += snprintf(buf+len, PAGE_SIZE - len, + "fs:\t%s\n", + config->test_fs); + else + len += snprintf(buf+len, PAGE_SIZE - len, + "fs:\tEMTPY\n"); + + mutex_unlock(&test_dev->config_mutex); + + return len; +} +static DEVICE_ATTR_RO(config); + +/* + * This ensures we don't allow kicking threads through if our configuration + * is faulty. + */ +static int __trigger_config_run(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + + test_dev->done = 0; + + switch (config->test_case) { + case TEST_KMOD_DRIVER: + return run_test_driver(test_dev); + case TEST_KMOD_FS_TYPE: + return run_test_fs_type(test_dev); + default: + dev_warn(test_dev->dev, + "Invalid test case requested: %u\n", + config->test_case); + return -EINVAL; + } +} + +static int trigger_config_run(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + int ret; + + mutex_lock(&test_dev->trigger_mutex); + mutex_lock(&test_dev->config_mutex); + + ret = __trigger_config_run(test_dev); + if (ret < 0) + goto out; + dev_info(test_dev->dev, "General test result: %d\n", + config->test_result); + + /* + * We must return 0 after a trigger even unless something went + * wrong with the setup of the test. If the test setup went fine + * then userspace must just check the result of config->test_result. + * One issue with relying on the return from a call in the kernel + * is if the kernel returns a possitive value using this trigger + * will not return the value to userspace, it would be lost. + * + * By not relying on capturing the return value of tests we are using + * through the trigger it also us to run tests with set -e and only + * fail when something went wrong with the driver upon trigger + * requests. + */ + ret = 0; + +out: + mutex_unlock(&test_dev->config_mutex); + mutex_unlock(&test_dev->trigger_mutex); + + return ret; +} + +static ssize_t +trigger_config_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + int ret; + + if (test_dev->test_is_oom) + return -ENOMEM; + + /* For all intents and purposes we don't care what userspace + * sent this trigger, we care only that we were triggered. + * We treat the return value only for caputuring issues with + * the test setup. At this point all the test variables should + * have been allocated so typically this should never fail. + */ + ret = trigger_config_run(test_dev); + if (unlikely(ret < 0)) + goto out; + + /* + * Note: any return > 0 will be treated as success + * and the error value will not be available to userspace. + * Do not rely on trying to send to userspace a test value + * return value as possitive return errors will be lost. + */ + if (WARN_ON(ret > 0)) + return -EINVAL; + + ret = count; +out: + return ret; +} +static DEVICE_ATTR_WO(trigger_config); + +/* + * XXX: move to kstrncpy() once merged. + * + * Users should use kfree_const() when freeing these. + */ +static int __kstrncpy(char **dst, const char *name, size_t count, gfp_t gfp) +{ + *dst = kstrndup(name, count, gfp); + if (!*dst) + return -ENOSPC; + return count; +} + +static int config_copy_test_driver_name(struct test_config *config, + const char *name, + size_t count) +{ + return __kstrncpy(&config->test_driver, name, count, GFP_KERNEL); +} + + +static int config_copy_test_fs(struct test_config *config, const char *name, + size_t count) +{ + return __kstrncpy(&config->test_fs, name, count, GFP_KERNEL); +} + +static void __kmod_config_free(struct test_config *config) +{ + if (!config) + return; + + kfree_const(config->test_driver); + config->test_driver = NULL; + + kfree_const(config->test_fs); + config->test_driver = NULL; +} + +static void kmod_config_free(struct kmod_test_device *test_dev) +{ + struct test_config *config; + + if (!test_dev) + return; + + config = &test_dev->config; + + mutex_lock(&test_dev->config_mutex); + __kmod_config_free(config); + mutex_unlock(&test_dev->config_mutex); +} + +static ssize_t config_test_driver_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + int copied; + + mutex_lock(&test_dev->config_mutex); + + kfree_const(config->test_driver); + config->test_driver = NULL; + + copied = config_copy_test_driver_name(config, buf, count); + mutex_unlock(&test_dev->config_mutex); + + return copied; +} + +/* + * As per sysfs_kf_seq_show() the buf is max PAGE_SIZE. + */ +static ssize_t config_test_show_str(struct mutex *config_mutex, + char *dst, + char *src) +{ + int len; + + mutex_lock(config_mutex); + len = snprintf(dst, PAGE_SIZE, "%s\n", src); + mutex_unlock(config_mutex); + + return len; +} + +static ssize_t config_test_driver_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return config_test_show_str(&test_dev->config_mutex, buf, + config->test_driver); +} +static DEVICE_ATTR(config_test_driver, 0644, config_test_driver_show, + config_test_driver_store); + +static ssize_t config_test_fs_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + int copied; + + mutex_lock(&test_dev->config_mutex); + + kfree_const(config->test_fs); + config->test_fs = NULL; + + copied = config_copy_test_fs(config, buf, count); + mutex_unlock(&test_dev->config_mutex); + + return copied; +} + +static ssize_t config_test_fs_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return config_test_show_str(&test_dev->config_mutex, buf, + config->test_fs); +} +static DEVICE_ATTR(config_test_fs, 0644, config_test_fs_show, + config_test_fs_store); + +static int trigger_config_run_type(struct kmod_test_device *test_dev, + enum kmod_test_case test_case, + const char *test_str) +{ + int copied = 0; + struct test_config *config = &test_dev->config; + + mutex_lock(&test_dev->config_mutex); + + switch (test_case) { + case TEST_KMOD_DRIVER: + kfree_const(config->test_driver); + config->test_driver = NULL; + copied = config_copy_test_driver_name(config, test_str, + strlen(test_str)); + break; + case TEST_KMOD_FS_TYPE: + break; + kfree_const(config->test_fs); + config->test_driver = NULL; + copied = config_copy_test_fs(config, test_str, + strlen(test_str)); + default: + mutex_unlock(&test_dev->config_mutex); + return -EINVAL; + } + + config->test_case = test_case; + + mutex_unlock(&test_dev->config_mutex); + + if (copied <= 0 || copied != strlen(test_str)) { + test_dev->test_is_oom = true; + return -ENOMEM; + } + + test_dev->test_is_oom = false; + + return trigger_config_run(test_dev); +} + +static void free_test_dev_info(struct kmod_test_device *test_dev) +{ + vfree(test_dev->info); + test_dev->info = NULL; +} + +static int kmod_config_sync_info(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + + free_test_dev_info(test_dev); + test_dev->info = vzalloc(config->num_threads * + sizeof(struct kmod_test_device_info)); + if (!test_dev->info) { + dev_err(test_dev->dev, "Cannot alloc test_dev info\n"); + return -ENOMEM; + } + + return 0; +} + +/* + * Old kernels may not have this, if you want to port this code to + * test it on older kernels. + */ +#ifdef get_kmod_umh_limit +static unsigned int kmod_init_test_thread_limit(void) +{ + return get_kmod_umh_limit(); +} +#else +static unsigned int kmod_init_test_thread_limit(void) +{ + return TEST_START_NUM_THREADS; +} +#endif + +static int __kmod_config_init(struct kmod_test_device *test_dev) +{ + struct test_config *config = &test_dev->config; + int ret = -ENOMEM, copied; + + __kmod_config_free(config); + + copied = config_copy_test_driver_name(config, TEST_START_DRIVER, + strlen(TEST_START_DRIVER)); + if (copied != strlen(TEST_START_DRIVER)) + goto err_out; + + copied = config_copy_test_fs(config, TEST_START_TEST_FS, + strlen(TEST_START_TEST_FS)); + if (copied != strlen(TEST_START_TEST_FS)) + goto err_out; + + config->num_threads = kmod_init_test_thread_limit(); + config->test_result = 0; + config->test_case = TEST_START_TEST_CASE; + + ret = kmod_config_sync_info(test_dev); + if (ret) + goto err_out; + + test_dev->test_is_oom = false; + + return 0; + +err_out: + test_dev->test_is_oom = true; + WARN_ON(test_dev->test_is_oom); + + __kmod_config_free(config); + + return ret; +} + +static ssize_t reset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + int ret; + + mutex_lock(&test_dev->trigger_mutex); + mutex_lock(&test_dev->config_mutex); + + ret = __kmod_config_init(test_dev); + if (ret < 0) { + ret = -ENOMEM; + dev_err(dev, "could not alloc settings for config trigger: %d\n", + ret); + goto out; + } + + dev_info(dev, "reset\n"); + ret = count; + +out: + mutex_unlock(&test_dev->config_mutex); + mutex_unlock(&test_dev->trigger_mutex); + + return ret; +} +static DEVICE_ATTR_WO(reset); + +static int test_dev_config_update_uint_sync(struct kmod_test_device *test_dev, + const char *buf, size_t size, + unsigned int *config, + int (*test_sync)(struct kmod_test_device *test_dev)) +{ + int ret; + long new; + unsigned int old_val; + + ret = kstrtol(buf, 10, &new); + if (ret) + return ret; + + if (new > UINT_MAX) + return -EINVAL; + + mutex_lock(&test_dev->config_mutex); + + old_val = *config; + *(unsigned int *)config = new; + + ret = test_sync(test_dev); + if (ret) { + *(unsigned int *)config = old_val; + + ret = test_sync(test_dev); + WARN_ON(ret); + + mutex_unlock(&test_dev->config_mutex); + return -EINVAL; + } + + mutex_unlock(&test_dev->config_mutex); + /* Always return full write size even if we didn't consume all */ + return size; +} + +static int test_dev_config_update_uint_range(struct kmod_test_device *test_dev, + const char *buf, size_t size, + unsigned int *config, + unsigned int min, + unsigned int max) +{ + int ret; + long new; + + ret = kstrtol(buf, 10, &new); + if (ret) + return ret; + + if (new < min || new > max || new > UINT_MAX) + return -EINVAL; + + mutex_lock(&test_dev->config_mutex); + *config = new; + mutex_unlock(&test_dev->config_mutex); + + /* Always return full write size even if we didn't consume all */ + return size; +} + +static int test_dev_config_update_int(struct kmod_test_device *test_dev, + const char *buf, size_t size, + int *config) +{ + int ret; + long new; + + ret = kstrtol(buf, 10, &new); + if (ret) + return ret; + + if (new > INT_MAX || new < INT_MIN) + return -EINVAL; + + mutex_lock(&test_dev->config_mutex); + *config = new; + mutex_unlock(&test_dev->config_mutex); + /* Always return full write size even if we didn't consume all */ + return size; +} + +static ssize_t test_dev_config_show_int(struct kmod_test_device *test_dev, + char *buf, + int config) +{ + int val; + + mutex_lock(&test_dev->config_mutex); + val = config; + mutex_unlock(&test_dev->config_mutex); + + return snprintf(buf, PAGE_SIZE, "%d\n", val); +} + +static ssize_t test_dev_config_show_uint(struct kmod_test_device *test_dev, + char *buf, + unsigned int config) +{ + unsigned int val; + + mutex_lock(&test_dev->config_mutex); + val = config; + mutex_unlock(&test_dev->config_mutex); + + return snprintf(buf, PAGE_SIZE, "%u\n", val); +} + +static ssize_t test_result_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return test_dev_config_update_int(test_dev, buf, count, + &config->test_result); +} + +static ssize_t config_num_threads_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return test_dev_config_update_uint_sync(test_dev, buf, count, + &config->num_threads, + kmod_config_sync_info); +} + +static ssize_t config_num_threads_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return test_dev_config_show_int(test_dev, buf, config->num_threads); +} +static DEVICE_ATTR(config_num_threads, 0644, config_num_threads_show, + config_num_threads_store); + +static ssize_t config_test_case_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return test_dev_config_update_uint_range(test_dev, buf, count, + &config->test_case, + __TEST_KMOD_INVALID + 1, + __TEST_KMOD_MAX - 1); +} + +static ssize_t config_test_case_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return test_dev_config_show_uint(test_dev, buf, config->test_case); +} +static DEVICE_ATTR(config_test_case, 0644, config_test_case_show, + config_test_case_store); + +static ssize_t test_result_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kmod_test_device *test_dev = dev_to_test_dev(dev); + struct test_config *config = &test_dev->config; + + return test_dev_config_show_int(test_dev, buf, config->test_result); +} +static DEVICE_ATTR(test_result, 0644, test_result_show, test_result_store); + +#define TEST_KMOD_DEV_ATTR(name) &dev_attr_##name.attr + +static struct attribute *test_dev_attrs[] = { + TEST_KMOD_DEV_ATTR(trigger_config), + TEST_KMOD_DEV_ATTR(config), + TEST_KMOD_DEV_ATTR(reset), + + TEST_KMOD_DEV_ATTR(config_test_driver), + TEST_KMOD_DEV_ATTR(config_test_fs), + TEST_KMOD_DEV_ATTR(config_num_threads), + TEST_KMOD_DEV_ATTR(config_test_case), + TEST_KMOD_DEV_ATTR(test_result), + + NULL, +}; + +ATTRIBUTE_GROUPS(test_dev); + +static int kmod_config_init(struct kmod_test_device *test_dev) +{ + int ret; + + mutex_lock(&test_dev->config_mutex); + ret = __kmod_config_init(test_dev); + mutex_unlock(&test_dev->config_mutex); + + return ret; +} + +static struct kmod_test_device *alloc_test_dev_kmod(int idx) +{ + int ret; + struct kmod_test_device *test_dev; + struct miscdevice *misc_dev; + + test_dev = vzalloc(sizeof(struct kmod_test_device)); + if (!test_dev) { + pr_err("Cannot alloc test_dev\n"); + goto err_out; + } + + mutex_init(&test_dev->config_mutex); + mutex_init(&test_dev->trigger_mutex); + mutex_init(&test_dev->thread_mutex); + + init_completion(&test_dev->kthreads_done); + + ret = kmod_config_init(test_dev); + if (ret < 0) { + pr_err("Cannot alloc kmod_config_init()\n"); + goto err_out_free; + } + + test_dev->dev_idx = idx; + misc_dev = &test_dev->misc_dev; + + misc_dev->minor = MISC_DYNAMIC_MINOR; + misc_dev->name = kasprintf(GFP_KERNEL, "test_kmod%d", idx); + if (!misc_dev->name) { + pr_err("Cannot alloc misc_dev->name\n"); + goto err_out_free_config; + } + misc_dev->groups = test_dev_groups; + + return test_dev; + +err_out_free_config: + free_test_dev_info(test_dev); + kmod_config_free(test_dev); +err_out_free: + vfree(test_dev); + test_dev = NULL; +err_out: + return NULL; +} + +static void free_test_dev_kmod(struct kmod_test_device *test_dev) +{ + if (test_dev) { + kfree_const(test_dev->misc_dev.name); + test_dev->misc_dev.name = NULL; + free_test_dev_info(test_dev); + kmod_config_free(test_dev); + vfree(test_dev); + test_dev = NULL; + } +} + +static struct kmod_test_device *register_test_dev_kmod(void) +{ + struct kmod_test_device *test_dev = NULL; + int ret; + + mutex_unlock(®_dev_mutex); + + /* int should suffice for number of devices, test for wrap */ + if (unlikely(num_test_devs + 1) < 0) { + pr_err("reached limit of number of test devices\n"); + goto out; + } + + test_dev = alloc_test_dev_kmod(num_test_devs); + if (!test_dev) + goto out; + + ret = misc_register(&test_dev->misc_dev); + if (ret) { + pr_err("could not register misc device: %d\n", ret); + free_test_dev_kmod(test_dev); + goto out; + } + + test_dev->dev = test_dev->misc_dev.this_device; + list_add_tail(&test_dev->list, ®_test_devs); + dev_info(test_dev->dev, "interface ready\n"); + + num_test_devs++; + +out: + mutex_unlock(®_dev_mutex); + + return test_dev; + +} + +static int __init test_kmod_init(void) +{ + struct kmod_test_device *test_dev; + int ret; + + test_dev = register_test_dev_kmod(); + if (!test_dev) { + pr_err("Cannot add first test kmod device\n"); + return -ENODEV; + } + + /* + * With some work we might be able to gracefully enable + * testing with this driver built-in, for now this seems + * rather risky. For those willing to try have at it, + * and enable the below. Good luck! If that works, try + * lowering the init level for more fun. + */ + if (force_init_test) { + ret = trigger_config_run_type(test_dev, + TEST_KMOD_DRIVER, "tun"); + if (WARN_ON(ret)) + return ret; + ret = trigger_config_run_type(test_dev, + TEST_KMOD_FS_TYPE, "btrfs"); + if (WARN_ON(ret)) + return ret; + } + + return 0; +} +late_initcall(test_kmod_init); + +static +void unregister_test_dev_kmod(struct kmod_test_device *test_dev) +{ + mutex_lock(&test_dev->trigger_mutex); + mutex_lock(&test_dev->config_mutex); + + test_dev_kmod_stop_tests(test_dev); + + dev_info(test_dev->dev, "removing interface\n"); + misc_deregister(&test_dev->misc_dev); + kfree(&test_dev->misc_dev.name); + + mutex_unlock(&test_dev->config_mutex); + mutex_unlock(&test_dev->trigger_mutex); + + free_test_dev_kmod(test_dev); +} + +static void __exit test_kmod_exit(void) +{ + struct kmod_test_device *test_dev, *tmp; + + mutex_lock(®_dev_mutex); + list_for_each_entry_safe(test_dev, tmp, ®_test_devs, list) { + list_del(&test_dev->list); + unregister_test_dev_kmod(test_dev); + } + mutex_unlock(®_dev_mutex); +} +module_exit(test_kmod_exit); + +MODULE_AUTHOR("Luis R. Rodriguez <mcgrof@kernel.org>"); +MODULE_LICENSE("GPL"); diff --git a/mm/mmap.c b/mm/mmap.c index 7fa6759322d1..f19efcf75418 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2231,7 +2231,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; - if (address >= TASK_SIZE) + if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; diff --git a/mm/util.c b/mm/util.c index ee250e2cde34..7b07ec852e01 100644 --- a/mm/util.c +++ b/mm/util.c @@ -83,6 +83,8 @@ EXPORT_SYMBOL(kstrdup_const); * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Note: Use kmemdup_nul() instead if the size is known exactly. */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { @@ -121,6 +123,28 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp) EXPORT_SYMBOL(kmemdup); /** + * kmemdup_nul - Create a NUL-terminated string from unterminated data + * @s: The data to stringify + * @len: The size of the data + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + */ +char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) +{ + char *buf; + + if (!s) + return NULL; + + buf = kmalloc_track_caller(len + 1, gfp); + if (buf) { + memcpy(buf, s, len); + buf[len] = '\0'; + } + return buf; +} +EXPORT_SYMBOL(kmemdup_nul); + +/** * memdup_user - duplicate memory region from user space * * @src: source address in user space diff --git a/net/9p/client.c b/net/9p/client.c index 1218fb3b52da..4674235b0d9b 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -37,6 +37,7 @@ #include <linux/uio.h> #include <net/9p/9p.h> #include <linux/parser.h> +#include <linux/seq_file.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include "protocol.h" @@ -77,6 +78,30 @@ inline int p9_is_proto_dotu(struct p9_client *clnt) } EXPORT_SYMBOL(p9_is_proto_dotu); +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->msize != 8192) + seq_printf(m, ",msize=%u", clnt->msize); + seq_printf(m, "trans=%s", clnt->trans_mod->name); + + switch (clnt->proto_version) { + case p9_proto_legacy: + seq_puts(m, ",noextend"); + break; + case p9_proto_2000u: + seq_puts(m, ",version=9p2000.u"); + break; + case p9_proto_2000L: + /* Default */ + break; + } + + if (clnt->trans_mod->show_options) + return clnt->trans_mod->show_options(m, clnt); + return 0; +} +EXPORT_SYMBOL(p9_show_client_options); + /* * Some error codes are taken directly from the server replies, * make sure they are valid. diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index dca3cdd1a014..ddfa86648f95 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -41,6 +41,7 @@ #include <linux/file.h> #include <linux/parser.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> @@ -51,6 +52,9 @@ #define MAX_SOCK_BUF (64*1024) #define MAXPOLLWADDR 2 +static struct p9_trans_module p9_tcp_trans; +static struct p9_trans_module p9_fd_trans; + /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) @@ -63,7 +67,7 @@ struct p9_fd_opts { int rfd; int wfd; u16 port; - int privport; + bool privport; }; /* @@ -720,6 +724,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) return 0; } +static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->trans_mod == &p9_tcp_trans) { + if (clnt->trans_opts.tcp.port != P9_PORT) + seq_printf(m, "port=%u", clnt->trans_opts.tcp.port); + } else if (clnt->trans_mod == &p9_fd_trans) { + if (clnt->trans_opts.fd.rfd != ~0) + seq_printf(m, "rfd=%u", clnt->trans_opts.fd.rfd); + if (clnt->trans_opts.fd.wfd != ~0) + seq_printf(m, "wfd=%u", clnt->trans_opts.fd.wfd); + } + return 0; +} + /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount @@ -738,7 +756,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -776,7 +794,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->wfd = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -942,6 +960,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) csocket = NULL; + client->trans_opts.tcp.port = opts.port; + client->trans_opts.tcp.privport = opts.privport; sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); @@ -1020,6 +1040,8 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) struct p9_fd_opts opts; parse_opts(args, &opts); + client->trans_opts.fd.rfd = opts.rfd; + client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); @@ -1044,6 +1066,7 @@ static struct p9_trans_module p9_tcp_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1056,6 +1079,7 @@ static struct p9_trans_module p9_unix_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1068,6 +1092,7 @@ static struct p9_trans_module p9_fd_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 553ed4ecb6a0..6d8e3031978f 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -43,6 +43,7 @@ #include <linux/parser.h> #include <linux/semaphore.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> @@ -70,6 +71,8 @@ * @dm_mr: DMA Memory Region pointer * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events + * @privport: Whether a privileged port may be used + * @port: The port to use * @sq_depth: The depth of the Send Queue * @sq_sem: Semaphore for the SQ * @rq_depth: The depth of the Receive Queue. @@ -95,6 +98,8 @@ struct p9_trans_rdma { struct ib_qp *qp; struct ib_cq *cq; long timeout; + bool privport; + u16 port; int sq_depth; struct semaphore sq_sem; int rq_depth; @@ -133,10 +138,10 @@ struct p9_rdma_context { */ struct p9_rdma_opts { short port; + bool privport; int sq_depth; int rq_depth; long timeout; - int privport; }; /* @@ -159,6 +164,23 @@ static match_table_t tokens = { {Opt_err, NULL}, }; +static int p9_rdma_show_options(struct seq_file *m, struct p9_client *clnt) +{ + struct p9_trans_rdma *rdma = clnt->trans; + + if (rdma->port != P9_PORT) + seq_printf(m, ",port=%u", rdma->port); + if (rdma->sq_depth != P9_RDMA_SQ_DEPTH) + seq_printf(m, ",sq=%u", rdma->sq_depth); + if (rdma->rq_depth != P9_RDMA_RQ_DEPTH) + seq_printf(m, ",rq=%u", rdma->rq_depth); + if (rdma->timeout != P9_RDMA_TIMEOUT) + seq_printf(m, ",timeout=%lu", rdma->timeout); + if (rdma->privport) + seq_puts(m, ",privport"); + return 0; +} + /** * parse_opts - parse mount options into rdma options structure * @params: options string passed from mount @@ -177,7 +199,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->sq_depth = P9_RDMA_SQ_DEPTH; opts->rq_depth = P9_RDMA_RQ_DEPTH; opts->timeout = P9_RDMA_TIMEOUT; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -218,7 +240,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->timeout = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -560,6 +582,8 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts) if (!rdma) return NULL; + rdma->port = opts->port; + rdma->privport = opts->privport; rdma->sq_depth = opts->sq_depth; rdma->rq_depth = opts->rq_depth; rdma->timeout = opts->timeout; @@ -733,6 +757,7 @@ static struct p9_trans_module p9_rdma_trans = { .request = rdma_request, .cancel = rdma_cancel, .cancelled = rdma_cancelled, + .show_options = p9_rdma_show_options, }; /** diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 3d265c5cb6d0..5c036d2f401e 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -599,7 +599,11 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) { struct ceph_client *client; struct ceph_entity_addr *myaddr = NULL; - int err = -ENOMEM; + int err; + + err = wait_for_random_bytes(); + if (err < 0) + return ERR_PTR(err); client = kzalloc(sizeof(*client), GFP_KERNEL); if (client == NULL) diff --git a/net/compat.c b/net/compat.c index aba929e5250f..6ded6c821d7a 100644 --- a/net/compat.c +++ b/net/compat.c @@ -37,21 +37,16 @@ int get_compat_msghdr(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - compat_uptr_t uaddr, uiov, tmp3; - compat_size_t nr_segs; + struct compat_msghdr msg; ssize_t err; - if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || - __get_user(uaddr, &umsg->msg_name) || - __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || - __get_user(uiov, &umsg->msg_iov) || - __get_user(nr_segs, &umsg->msg_iovlen) || - __get_user(tmp3, &umsg->msg_control) || - __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || - __get_user(kmsg->msg_flags, &umsg->msg_flags)) + if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - if (!uaddr) + kmsg->msg_flags = msg.msg_flags; + kmsg->msg_namelen = msg.msg_namelen; + + if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -59,14 +54,16 @@ int get_compat_msghdr(struct msghdr *kmsg, if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); - kmsg->msg_control = compat_ptr(tmp3); + + kmsg->msg_control = compat_ptr(msg.msg_control); + kmsg->msg_controllen = msg.msg_controllen; if (save_addr) - *save_addr = compat_ptr(uaddr); + *save_addr = compat_ptr(msg.msg_name); - if (uaddr && kmsg->msg_namelen) { + if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(compat_ptr(uaddr), + err = move_addr_to_kernel(compat_ptr(msg.msg_name), kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -77,13 +74,13 @@ int get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (nr_segs > UIO_MAXIOV) + if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; return compat_import_iovec(save_addr ? READ : WRITE, - compat_ptr(uiov), nr_segs, + compat_ptr(msg.msg_iov), msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); } @@ -316,15 +313,15 @@ struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); - compat_uptr_t ptr; - u16 len; - - if (!access_ok(VERIFY_READ, fprog32, sizeof(*fprog32)) || - !access_ok(VERIFY_WRITE, kfprog, sizeof(struct sock_fprog)) || - __get_user(len, &fprog32->len) || - __get_user(ptr, &fprog32->filter) || - __put_user(len, &kfprog->len) || - __put_user(compat_ptr(ptr), &kfprog->filter)) + struct compat_sock_fprog f32; + struct sock_fprog f; + + if (copy_from_user(&f32, fprog32, sizeof(*fprog32))) + return NULL; + memset(&f, 0, sizeof(f)); + f.len = f32.len; + f.filter = compat_ptr(f32.filter); + if (copy_to_user(kfprog, &f, sizeof(struct sock_fprog))) return NULL; return kfprog; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e31fc11a8000..d0713627deb6 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -347,8 +347,7 @@ out_entries: static void neigh_get_hash_rnd(u32 *x) { - get_random_bytes(x, sizeof(*x)); - *x |= 1; + *x = get_random_u32() | 1; } static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c816cd53f7fc..0383e66f59bc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2979,8 +2979,7 @@ static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); - get_random_bytes(&net->ipv4.dev_addr_genid, - sizeof(net->ipv4.dev_addr_genid)); + atomic_set(&net->ipv4.dev_addr_genid, get_random_int()); return 0; } diff --git a/net/socket.c b/net/socket.c index 59e902b9df09..bf2122691fba 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1910,22 +1910,18 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - struct sockaddr __user *uaddr; - struct iovec __user *uiov; - size_t nr_segs; + struct user_msghdr msg; ssize_t err; - if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || - __get_user(uaddr, &umsg->msg_name) || - __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || - __get_user(uiov, &umsg->msg_iov) || - __get_user(nr_segs, &umsg->msg_iovlen) || - __get_user(kmsg->msg_control, &umsg->msg_control) || - __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || - __get_user(kmsg->msg_flags, &umsg->msg_flags)) + if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - if (!uaddr) + kmsg->msg_control = msg.msg_control; + kmsg->msg_controllen = msg.msg_controllen; + kmsg->msg_flags = msg.msg_flags; + + kmsg->msg_namelen = msg.msg_namelen; + if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -1935,11 +1931,11 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) - *save_addr = uaddr; + *save_addr = msg.msg_name; - if (uaddr && kmsg->msg_namelen) { + if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(uaddr, kmsg->msg_namelen, + err = move_addr_to_kernel(msg.msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; @@ -1949,12 +1945,13 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (nr_segs > UIO_MAXIOV) + if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; - return import_iovec(save_addr ? READ : WRITE, uiov, nr_segs, + return import_iovec(save_addr ? READ : WRITE, + msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); } diff --git a/security/keys/compat_dh.c b/security/keys/compat_dh.c index a6a659b6bcb6..aa6b34cafe5f 100644 --- a/security/keys/compat_dh.c +++ b/security/keys/compat_dh.c @@ -33,6 +33,8 @@ long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params, kdfcopy.hashname = compat_ptr(compat_kdfcopy.hashname); kdfcopy.otherinfo = compat_ptr(compat_kdfcopy.otherinfo); kdfcopy.otherinfolen = compat_kdfcopy.otherinfolen; + memcpy(kdfcopy.__spare, compat_kdfcopy.__spare, + sizeof(kdfcopy.__spare)); return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy); } diff --git a/security/keys/dh.c b/security/keys/dh.c index 4755d4b4f945..d1ea9f325f94 100644 --- a/security/keys/dh.c +++ b/security/keys/dh.c @@ -266,6 +266,11 @@ long __keyctl_dh_compute(struct keyctl_dh_params __user *params, if (kdfcopy) { char *hashname; + if (memchr_inv(kdfcopy->__spare, 0, sizeof(kdfcopy->__spare))) { + ret = -EINVAL; + goto out1; + } + if (buflen > KEYCTL_KDF_MAX_OUTPUT_LEN || kdfcopy->otherinfolen > KEYCTL_KDF_MAX_OI_LEN) { ret = -EMSGSIZE; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index b3d5bed75029..22995cb3bd44 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -238,10 +238,8 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) { if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP)) return false; - /* check architectures that return -EINVAL from dma_mmap_coherent() */ - /* FIXME: this should be some global flag */ -#if defined(CONFIG_C6X) || defined(CONFIG_FRV) || defined(CONFIG_MN10300) ||\ - defined(CONFIG_PARISC) || defined(CONFIG_XTENSA) + /* architecture supports dma_mmap_coherent()? */ +#if defined(CONFIG_ARCH_NO_COHERENT_DMA_MMAP) || !defined(CONFIG_HAS_DMA) if (!substream->ops->mmap && substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV) return false; @@ -3502,7 +3500,7 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, } #endif /* CONFIG_GENERIC_ALLOCATOR */ #ifndef CONFIG_X86 /* for avoiding warnings arch/x86/mm/pat.c */ - if (!substream->ops->page && + if (IS_ENABLED(CONFIG_HAS_DMA) && !substream->ops->page && substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV) return dma_mmap_coherent(substream->dma_buffer.dev.dev, area, diff --git a/sound/drivers/opl4/opl4_lib.c b/sound/drivers/opl4/opl4_lib.c index bc345d564f8d..db76a5bf2bd2 100644 --- a/sound/drivers/opl4/opl4_lib.c +++ b/sound/drivers/opl4/opl4_lib.c @@ -29,7 +29,7 @@ MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>"); MODULE_DESCRIPTION("OPL4 driver"); MODULE_LICENSE("GPL"); -static void inline snd_opl4_wait(struct snd_opl4 *opl4) +static inline void snd_opl4_wait(struct snd_opl4 *opl4) { int timeout = 10; while ((inb(opl4->fm_port) & OPL4_STATUS_BUSY) && --timeout > 0) diff --git a/sound/isa/msnd/msnd_midi.c b/sound/isa/msnd/msnd_midi.c index 912b5a9ccbab..013d8d1170fe 100644 --- a/sound/isa/msnd/msnd_midi.c +++ b/sound/isa/msnd/msnd_midi.c @@ -120,24 +120,24 @@ void snd_msndmidi_input_read(void *mpuv) unsigned long flags; struct snd_msndmidi *mpu = mpuv; void *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF; + u16 head, tail, size; spin_lock_irqsave(&mpu->input_lock, flags); - while (readw(mpu->dev->MIDQ + JQS_wTail) != - readw(mpu->dev->MIDQ + JQS_wHead)) { - u16 wTmp, val; - val = readw(pwMIDQData + 2 * readw(mpu->dev->MIDQ + JQS_wHead)); - - if (test_bit(MSNDMIDI_MODE_BIT_INPUT_TRIGGER, - &mpu->mode)) - snd_rawmidi_receive(mpu->substream_input, - (unsigned char *)&val, 1); - - wTmp = readw(mpu->dev->MIDQ + JQS_wHead) + 1; - if (wTmp > readw(mpu->dev->MIDQ + JQS_wSize)) - writew(0, mpu->dev->MIDQ + JQS_wHead); - else - writew(wTmp, mpu->dev->MIDQ + JQS_wHead); + head = readw(mpu->dev->MIDQ + JQS_wHead); + tail = readw(mpu->dev->MIDQ + JQS_wTail); + size = readw(mpu->dev->MIDQ + JQS_wSize); + if (head > size || tail > size) + goto out; + while (head != tail) { + unsigned char val = readw(pwMIDQData + 2 * head); + + if (test_bit(MSNDMIDI_MODE_BIT_INPUT_TRIGGER, &mpu->mode)) + snd_rawmidi_receive(mpu->substream_input, &val, 1); + if (++head > size) + head = 0; + writew(head, mpu->dev->MIDQ + JQS_wHead); } + out: spin_unlock_irqrestore(&mpu->input_lock, flags); } EXPORT_SYMBOL(snd_msndmidi_input_read); diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c index ad4897337df5..fc4fb1904aef 100644 --- a/sound/isa/msnd/msnd_pinnacle.c +++ b/sound/isa/msnd/msnd_pinnacle.c @@ -170,23 +170,24 @@ static irqreturn_t snd_msnd_interrupt(int irq, void *dev_id) { struct snd_msnd *chip = dev_id; void *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF; + u16 head, tail, size; /* Send ack to DSP */ /* inb(chip->io + HP_RXL); */ /* Evaluate queued DSP messages */ - while (readw(chip->DSPQ + JQS_wTail) != readw(chip->DSPQ + JQS_wHead)) { - u16 wTmp; - - snd_msnd_eval_dsp_msg(chip, - readw(pwDSPQData + 2 * readw(chip->DSPQ + JQS_wHead))); - - wTmp = readw(chip->DSPQ + JQS_wHead) + 1; - if (wTmp > readw(chip->DSPQ + JQS_wSize)) - writew(0, chip->DSPQ + JQS_wHead); - else - writew(wTmp, chip->DSPQ + JQS_wHead); + head = readw(chip->DSPQ + JQS_wHead); + tail = readw(chip->DSPQ + JQS_wTail); + size = readw(chip->DSPQ + JQS_wSize); + if (head > size || tail > size) + goto out; + while (head != tail) { + snd_msnd_eval_dsp_msg(chip, readw(pwDSPQData + 2 * head)); + if (++head > size) + head = 0; + writew(head, chip->DSPQ + JQS_wHead); } + out: /* Send ack to DSP */ inb(chip->io + HP_RXL); return IRQ_HANDLED; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 76c85f08bea6..d549f35f39d3 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -53,9 +53,11 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); #define is_skylake(codec) ((codec)->core.vendor_id == 0x80862809) #define is_broxton(codec) ((codec)->core.vendor_id == 0x8086280a) #define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b) +#define is_geminilake(codec) (((codec)->core.vendor_id == 0x8086280d) || \ + ((codec)->core.vendor_id == 0x80862800)) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ || is_skylake(codec) || is_broxton(codec) \ - || is_kabylake(codec)) + || is_kabylake(codec)) || is_geminilake(codec) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) @@ -3790,6 +3792,7 @@ HDA_CODEC_ENTRY(0x80862809, "Skylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280a, "Broxton HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), +HDA_CODEC_ENTRY(0x80862800, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cd6987b5c6d9..45d58fc1df39 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -379,6 +379,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) break; case 0x10ec0899: case 0x10ec0900: + case 0x10ec1168: case 0x10ec1220: alc_update_coef_idx(codec, 0x7, 1<<1, 0); break; @@ -5179,6 +5180,7 @@ enum { ALC233_FIXUP_ASUS_MIC_NO_PRESENCE, ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, ALC233_FIXUP_LENOVO_MULTI_CODECS, + ALC294_FIXUP_LENOVO_MIC_LOCATION, }; static const struct hda_fixup alc269_fixups[] = { @@ -5962,6 +5964,18 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, }, + [ALC294_FIXUP_LENOVO_MIC_LOCATION] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* Change the mic location from front to right, otherwise there are + two front mics with the same name, pulseaudio can't handle them. + This is just a temporary workaround, after applying this fixup, + there will be one "Front Mic" and one "Mic" in this machine. + */ + { 0x1a, 0x04a19040 }, + { } + }, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6143,6 +6157,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), + SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), @@ -7801,6 +7816,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662), HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882), HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882), + HDA_CODEC_ENTRY(0x10ec1168, "ALC1220", patch_alc882), HDA_CODEC_ENTRY(0x10ec1220, "ALC1220", patch_alc882), {} /* terminator */ }; diff --git a/tools/testing/selftests/kmod/Makefile b/tools/testing/selftests/kmod/Makefile new file mode 100644 index 000000000000..fa2ccc5fb3de --- /dev/null +++ b/tools/testing/selftests/kmod/Makefile @@ -0,0 +1,11 @@ +# Makefile for kmod loading selftests + +# No binaries, but make sure arg-less "make" doesn't trigger "run_tests" +all: + +TEST_PROGS := kmod.sh + +include ../lib.mk + +# Nothing to clean up. +clean: diff --git a/tools/testing/selftests/kmod/config b/tools/testing/selftests/kmod/config new file mode 100644 index 000000000000..259f4fd6b5e2 --- /dev/null +++ b/tools/testing/selftests/kmod/config @@ -0,0 +1,7 @@ +CONFIG_TEST_KMOD=m +CONFIG_TEST_LKM=m +CONFIG_XFS_FS=m + +# For the module parameter force_init_test is used +CONFIG_TUN=m +CONFIG_BTRFS_FS=m diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh new file mode 100644 index 000000000000..8cecae9a8bca --- /dev/null +++ b/tools/testing/selftests/kmod/kmod.sh @@ -0,0 +1,615 @@ +#!/bin/bash +# +# Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org> +# +# 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; or, when distributed separately from the Linux kernel or +# when incorporated into other software packages, subject to the following +# license: +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of copyleft-next (version 0.3.1 or later) as published +# at http://copyleft-next.org/. + +# This is a stress test script for kmod, the kernel module loader. It uses +# test_kmod which exposes a series of knobs for the API for us so we can +# tweak each test in userspace rather than in kernelspace. +# +# The way kmod works is it uses the kernel's usermode helper API to eventually +# call /sbin/modprobe. It has a limit of the number of concurrent calls +# possible. The kernel interface to load modules is request_module(), however +# mount uses get_fs_type(). Both behave slightly differently, but the +# differences are important enough to test each call separately. For this +# reason test_kmod starts by providing tests for both calls. +# +# The test driver test_kmod assumes a series of defaults which you can +# override by exporting to your environment prior running this script. +# For instance this script assumes you do not have xfs loaded upon boot. +# If this is false, export DEFAULT_KMOD_FS="ext4" prior to running this +# script if the filesyste module you don't have loaded upon bootup +# is ext4 instead. Refer to allow_user_defaults() for a list of user +# override variables possible. +# +# You'll want at least 4 GiB of RAM to expect to run these tests +# without running out of memory on them. For other requirements refer +# to test_reqs() + +set -e + +TEST_NAME="kmod" +TEST_DRIVER="test_${TEST_NAME}" +TEST_DIR=$(dirname $0) + +# This represents +# +# TEST_ID:TEST_COUNT:ENABLED +# +# TEST_ID: is the test id number +# TEST_COUNT: number of times we should run the test +# ENABLED: 1 if enabled, 0 otherwise +# +# Once these are enabled please leave them as-is. Write your own test, +# we have tons of space. +ALL_TESTS="0001:3:1" +ALL_TESTS="$ALL_TESTS 0002:3:1" +ALL_TESTS="$ALL_TESTS 0003:1:1" +ALL_TESTS="$ALL_TESTS 0004:1:1" +ALL_TESTS="$ALL_TESTS 0005:10:1" +ALL_TESTS="$ALL_TESTS 0006:10:1" +ALL_TESTS="$ALL_TESTS 0007:5:1" +ALL_TESTS="$ALL_TESTS 0008:150:1" +ALL_TESTS="$ALL_TESTS 0009:150:1" + +test_modprobe() +{ + if [ ! -d $DIR ]; then + echo "$0: $DIR not present" >&2 + echo "You must have the following enabled in your kernel:" >&2 + cat $TEST_DIR/config >&2 + exit 1 + fi +} + +function allow_user_defaults() +{ + if [ -z $DEFAULT_KMOD_DRIVER ]; then + DEFAULT_KMOD_DRIVER="test_module" + fi + + if [ -z $DEFAULT_KMOD_FS ]; then + DEFAULT_KMOD_FS="xfs" + fi + + if [ -z $PROC_DIR ]; then + PROC_DIR="/proc/sys/kernel/" + fi + + if [ -z $MODPROBE_LIMIT ]; then + MODPROBE_LIMIT=50 + fi + + if [ -z $DIR ]; then + DIR="/sys/devices/virtual/misc/${TEST_DRIVER}0/" + fi + + if [ -z $DEFAULT_NUM_TESTS ]; then + DEFAULT_NUM_TESTS=150 + fi + + MODPROBE_LIMIT_FILE="${PROC_DIR}/kmod-limit" +} + +test_reqs() +{ + if ! which modprobe 2> /dev/null > /dev/null; then + echo "$0: You need modprobe installed" >&2 + exit 1 + fi + + if ! which kmod 2> /dev/null > /dev/null; then + echo "$0: You need kmod installed" >&2 + exit 1 + fi + + # kmod 19 has a bad bug where it returns 0 when modprobe + # gets called *even* if the module was not loaded due to + # some bad heuristics. For details see: + # + # A work around is possible in-kernel but its rather + # complex. + KMOD_VERSION=$(kmod --version | awk '{print $3}') + if [[ $KMOD_VERSION -le 19 ]]; then + echo "$0: You need at least kmod 20" >&2 + echo "kmod <= 19 is buggy, for details see:" >&2 + echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 + exit 1 + fi + + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit 0 + fi +} + +function load_req_mod() +{ + trap "test_modprobe" EXIT + + if [ ! -d $DIR ]; then + # Alanis: "Oh isn't it ironic?" + modprobe $TEST_DRIVER + fi +} + +test_finish() +{ + echo "Test completed" +} + +errno_name_to_val() +{ + case "$1" in + # kmod calls modprobe and upon of a module not found + # modprobe returns just 1... However in the kernel we + # *sometimes* see 256... + MODULE_NOT_FOUND) + echo 256;; + SUCCESS) + echo 0;; + -EPERM) + echo -1;; + -ENOENT) + echo -2;; + -EINVAL) + echo -22;; + -ERR_ANY) + echo -123456;; + *) + echo invalid;; + esac +} + +errno_val_to_name() + case "$1" in + 256) + echo MODULE_NOT_FOUND;; + 0) + echo SUCCESS;; + -1) + echo -EPERM;; + -2) + echo -ENOENT;; + -22) + echo -EINVAL;; + -123456) + echo -ERR_ANY;; + *) + echo invalid;; + esac + +config_set_test_case_driver() +{ + if ! echo -n 1 >$DIR/config_test_case; then + echo "$0: Unable to set to test case to driver" >&2 + exit 1 + fi +} + +config_set_test_case_fs() +{ + if ! echo -n 2 >$DIR/config_test_case; then + echo "$0: Unable to set to test case to fs" >&2 + exit 1 + fi +} + +config_num_threads() +{ + if ! echo -n $1 >$DIR/config_num_threads; then + echo "$0: Unable to set to number of threads" >&2 + exit 1 + fi +} + +config_get_modprobe_limit() +{ + if [[ -f ${MODPROBE_LIMIT_FILE} ]] ; then + MODPROBE_LIMIT=$(cat $MODPROBE_LIMIT_FILE) + fi + echo $MODPROBE_LIMIT +} + +config_num_thread_limit_extra() +{ + MODPROBE_LIMIT=$(config_get_modprobe_limit) + let EXTRA_LIMIT=$MODPROBE_LIMIT+$1 + config_num_threads $EXTRA_LIMIT +} + +# For special characters use printf directly, +# refer to kmod_test_0001 +config_set_driver() +{ + if ! echo -n $1 >$DIR/config_test_driver; then + echo "$0: Unable to set driver" >&2 + exit 1 + fi +} + +config_set_fs() +{ + if ! echo -n $1 >$DIR/config_test_fs; then + echo "$0: Unable to set driver" >&2 + exit 1 + fi +} + +config_get_driver() +{ + cat $DIR/config_test_driver +} + +config_get_test_result() +{ + cat $DIR/test_result +} + +config_reset() +{ + if ! echo -n "1" >"$DIR"/reset; then + echo "$0: reset shuld have worked" >&2 + exit 1 + fi +} + +config_show_config() +{ + echo "----------------------------------------------------" + cat "$DIR"/config + echo "----------------------------------------------------" +} + +config_trigger() +{ + if ! echo -n "1" >"$DIR"/trigger_config 2>/dev/null; then + echo "$1: FAIL - loading should have worked" + config_show_config + exit 1 + fi + echo "$1: OK! - loading kmod test" +} + +config_trigger_want_fail() +{ + if echo "1" > $DIR/trigger_config 2>/dev/null; then + echo "$1: FAIL - test case was expected to fail" + config_show_config + exit 1 + fi + echo "$1: OK! - kmod test case failed as expected" +} + +config_expect_result() +{ + RC=$(config_get_test_result) + RC_NAME=$(errno_val_to_name $RC) + + ERRNO_NAME=$2 + ERRNO=$(errno_name_to_val $ERRNO_NAME) + + if [[ $ERRNO_NAME = "-ERR_ANY" ]]; then + if [[ $RC -ge 0 ]]; then + echo "$1: FAIL, test expects $ERRNO_NAME - got $RC_NAME ($RC)" >&2 + config_show_config + exit 1 + fi + elif [[ $RC != $ERRNO ]]; then + echo "$1: FAIL, test expects $ERRNO_NAME ($ERRNO) - got $RC_NAME ($RC)" >&2 + config_show_config + exit 1 + fi + echo "$1: OK! - Return value: $RC ($RC_NAME), expected $ERRNO_NAME" +} + +kmod_defaults_driver() +{ + config_reset + modprobe -r $DEFAULT_KMOD_DRIVER + config_set_driver $DEFAULT_KMOD_DRIVER +} + +kmod_defaults_fs() +{ + config_reset + modprobe -r $DEFAULT_KMOD_FS + config_set_fs $DEFAULT_KMOD_FS + config_set_test_case_fs +} + +kmod_test_0001_driver() +{ + NAME='\000' + + kmod_defaults_driver + config_num_threads 1 + printf '\000' >"$DIR"/config_test_driver + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} MODULE_NOT_FOUND +} + +kmod_test_0001_fs() +{ + NAME='\000' + + kmod_defaults_fs + config_num_threads 1 + printf '\000' >"$DIR"/config_test_fs + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} -EINVAL +} + +kmod_test_0001() +{ + kmod_test_0001_driver + kmod_test_0001_fs +} + +kmod_test_0002_driver() +{ + NAME="nope-$DEFAULT_KMOD_DRIVER" + + kmod_defaults_driver + config_set_driver $NAME + config_num_threads 1 + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} MODULE_NOT_FOUND +} + +kmod_test_0002_fs() +{ + NAME="nope-$DEFAULT_KMOD_FS" + + kmod_defaults_fs + config_set_fs $NAME + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} -EINVAL +} + +kmod_test_0002() +{ + kmod_test_0002_driver + kmod_test_0002_fs +} + +kmod_test_0003() +{ + kmod_defaults_fs + config_num_threads 1 + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0004() +{ + kmod_defaults_fs + config_num_threads 2 + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0005() +{ + kmod_defaults_driver + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0006() +{ + kmod_defaults_fs + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0007() +{ + kmod_test_0005 + kmod_test_0006 +} + +kmod_test_0008() +{ + kmod_defaults_driver + MODPROBE_LIMIT=$(config_get_modprobe_limit) + let EXTRA=$MODPROBE_LIMIT/6 + config_num_thread_limit_extra $EXTRA + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0009() +{ + kmod_defaults_fs + MODPROBE_LIMIT=$(config_get_modprobe_limit) + let EXTRA=$MODPROBE_LIMIT/4 + config_num_thread_limit_extra $EXTRA + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +list_tests() +{ + echo "Test ID list:" + echo + echo "TEST_ID x NUM_TEST" + echo "TEST_ID: Test ID" + echo "NUM_TESTS: Number of recommended times to run the test" + echo + echo "0001 x $(get_test_count 0001) - Simple test - 1 thread for empty string" + echo "0002 x $(get_test_count 0002) - Simple test - 1 thread for modules/filesystems that do not exist" + echo "0003 x $(get_test_count 0003) - Simple test - 1 thread for get_fs_type() only" + echo "0004 x $(get_test_count 0004) - Simple test - 2 threads for get_fs_type() only" + echo "0005 x $(get_test_count 0005) - multithreaded tests with default setup - request_module() only" + echo "0006 x $(get_test_count 0006) - multithreaded tests with default setup - get_fs_type() only" + echo "0007 x $(get_test_count 0007) - multithreaded tests with default setup test request_module() and get_fs_type()" + echo "0008 x $(get_test_count 0008) - multithreaded - push kmod_concurrent over max_modprobes for request_module()" + echo "0009 x $(get_test_count 0009) - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()" +} + +usage() +{ + NUM_TESTS=$(grep -o ' ' <<<"$ALL_TESTS" | grep -c .) + let NUM_TESTS=$NUM_TESTS+1 + MAX_TEST=$(printf "%04d\n" $NUM_TESTS) + echo "Usage: $0 [ -t <4-number-digit> ] | [ -w <4-number-digit> ] |" + echo " [ -s <4-number-digit> ] | [ -c <4-number-digit> <test- count>" + echo " [ all ] [ -h | --help ] [ -l ]" + echo "" + echo "Valid tests: 0001-$MAX_TEST" + echo "" + echo " all Runs all tests (default)" + echo " -t Run test ID the number amount of times is recommended" + echo " -w Watch test ID run until it runs into an error" + echo " -c Run test ID once" + echo " -s Run test ID x test-count number of times" + echo " -l List all test ID list" + echo " -h|--help Help" + echo + echo "If an error every occurs execution will immediately terminate." + echo "If you are adding a new test try using -w <test-ID> first to" + echo "make sure the test passes a series of tests." + echo + echo Example uses: + echo + echo "${TEST_NAME}.sh -- executes all tests" + echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recomended" + echo "${TEST_NAME}.sh -w 0008 -- Watch test ID 0008 run until an error occurs" + echo "${TEST_NAME}.sh -s 0008 -- Run test ID 0008 once" + echo "${TEST_NAME}.sh -c 0008 3 -- Run test ID 0008 three times" + echo + list_tests + exit 1 +} + +function test_num() +{ + re='^[0-9]+$' + if ! [[ $1 =~ $re ]]; then + usage + fi +} + +function get_test_count() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + LAST_TWO=${TEST_DATA#*:*} + echo ${LAST_TWO%:*} +} + +function get_test_enabled() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + echo ${TEST_DATA#*:*:} +} + +function run_all_tests() +{ + for i in $ALL_TESTS ; do + TEST_ID=${i%:*:*} + ENABLED=$(get_test_enabled $TEST_ID) + TEST_COUNT=$(get_test_count $TEST_ID) + if [[ $ENABLED -eq "1" ]]; then + test_case $TEST_ID $TEST_COUNT + fi + done +} + +function watch_log() +{ + if [ $# -ne 3 ]; then + clear + fi + date + echo "Running test: $2 - run #$1" +} + +function watch_case() +{ + i=0 + while [ 1 ]; do + + if [ $# -eq 1 ]; then + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 + ${TEST_NAME}_test_$1 + else + watch_log $i all + run_all_tests + fi + let i=$i+1 + done +} + +function test_case() +{ + NUM_TESTS=$DEFAULT_NUM_TESTS + if [ $# -eq 2 ]; then + NUM_TESTS=$2 + fi + + i=0 + while [ $i -lt $NUM_TESTS ]; do + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 noclear + RUN_TEST=${TEST_NAME}_test_$1 + $RUN_TEST + let i=$i+1 + done +} + +function parse_args() +{ + if [ $# -eq 0 ]; then + run_all_tests + else + if [[ "$1" = "all" ]]; then + run_all_tests + elif [[ "$1" = "-w" ]]; then + shift + watch_case $@ + elif [[ "$1" = "-t" ]]; then + shift + test_num $1 + test_case $1 $(get_test_count $1) + elif [[ "$1" = "-c" ]]; then + shift + test_num $1 + test_num $2 + test_case $1 $2 + elif [[ "$1" = "-s" ]]; then + shift + test_case $1 1 + elif [[ "$1" = "-l" ]]; then + list_tests + elif [[ "$1" = "-h" || "$1" = "--help" ]]; then + usage + else + usage + fi + fi +} + +test_reqs +allow_user_defaults +load_req_mod + +trap "test_finish" EXIT + +parse_args $@ + +exit 0 diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 13f5198ba0ee..1c12b5855e4f 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -18,6 +18,7 @@ LIST_DEVS=FALSE DEBUGFS=${DEBUGFS-/sys/kernel/debug} +DB_BITMASK=0x7FFF PERF_RUN_ORDER=32 MAX_MW_SIZE=0 RUN_DMA_TESTS= @@ -38,6 +39,7 @@ function show_help() echo "be highly recommended." echo echo "Options:" + echo " -b BITMASK doorbell clear bitmask for ntb_tool" echo " -C don't cleanup ntb modules on exit" echo " -d run dma tests" echo " -h show this help message" @@ -52,8 +54,9 @@ function show_help() function parse_args() { OPTIND=0 - while getopts "Cdhlm:r:p:w:" opt; do + while getopts "b:Cdhlm:r:p:w:" opt; do case "$opt" in + b) DB_BITMASK=${OPTARG} ;; C) DONT_CLEANUP=1 ;; d) RUN_DMA_TESTS=1 ;; h) show_help; exit 0 ;; @@ -85,6 +88,10 @@ set -e function _modprobe() { modprobe "$@" + + if [[ "$REMOTE_HOST" != "" ]]; then + ssh "$REMOTE_HOST" modprobe "$@" + fi } function split_remote() @@ -154,7 +161,7 @@ function doorbell_test() echo "Running db tests on: $(basename $LOC) / $(basename $REM)" - write_file "c 0xFFFFFFFF" "$REM/db" + write_file "c $DB_BITMASK" "$REM/db" for ((i=1; i <= 8; i++)); do let DB=$(read_file "$REM/db") || true diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 9120edf3c94b..f2ac53ab8243 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -825,7 +825,7 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm, if (ret < 0) goto unlock_fail; - kvm->buses[bus_idx]->ioeventfd_count++; + kvm_get_bus(kvm, bus_idx)->ioeventfd_count++; list_add_tail(&p->list, &kvm->ioeventfds); mutex_unlock(&kvm->slots_lock); @@ -848,6 +848,7 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, { struct _ioeventfd *p, *tmp; struct eventfd_ctx *eventfd; + struct kvm_io_bus *bus; int ret = -ENOENT; eventfd = eventfd_ctx_fdget(args->fd); @@ -870,8 +871,9 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); - if (kvm->buses[bus_idx]) - kvm->buses[bus_idx]->ioeventfd_count--; + bus = kvm_get_bus(kvm, bus_idx); + if (bus) + bus->ioeventfd_count--; ioeventfd_release(p); ret = 0; break; diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 31e40c9e81df..b1286c4e0712 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -230,7 +230,7 @@ int kvm_set_irq_routing(struct kvm *kvm, } mutex_lock(&kvm->irq_lock); - old = kvm->irq_routing; + old = rcu_dereference_protected(kvm->irq_routing, 1); rcu_assign_pointer(kvm->irq_routing, new); kvm_irq_routing_update(kvm); kvm_arch_irq_routing_update(kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 19f0ecb9b93e..82987d457b8b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -130,6 +130,12 @@ EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; +#define KVM_EVENT_CREATE_VM 0 +#define KVM_EVENT_DESTROY_VM 1 +static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); +static unsigned long long kvm_createvm_count; +static unsigned long long kvm_active_vms; + bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) @@ -187,12 +193,23 @@ static void ack_flush(void *_completed) { } +static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +{ + if (unlikely(!cpus)) + cpus = cpu_online_mask; + + if (cpumask_empty(cpus)) + return false; + + smp_call_function_many(cpus, ack_flush, NULL, wait); + return true; +} + bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { int i, cpu, me; cpumask_var_t cpus; - bool called = true; - bool wait = req & KVM_REQUEST_WAIT; + bool called; struct kvm_vcpu *vcpu; zalloc_cpumask_var(&cpus, GFP_ATOMIC); @@ -207,14 +224,9 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) if (cpus != NULL && cpu != -1 && cpu != me && kvm_request_needs_ipi(vcpu, req)) - cpumask_set_cpu(cpu, cpus); + __cpumask_set_cpu(cpu, cpus); } - if (unlikely(cpus == NULL)) - smp_call_function_many(cpu_online_mask, ack_flush, NULL, wait); - else if (!cpumask_empty(cpus)) - smp_call_function_many(cpus, ack_flush, NULL, wait); - else - called = false; + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); free_cpumask_var(cpus); return called; @@ -293,7 +305,12 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) { - put_pid(vcpu->pid); + /* + * no need for rcu_read_lock as VCPU_RUN is the only place that + * will change the vcpu->pid pointer and on uninit all file + * descriptors are already gone. + */ + put_pid(rcu_dereference_protected(vcpu->pid, 1)); kvm_arch_vcpu_uninit(vcpu); free_page((unsigned long)vcpu->run); } @@ -674,8 +691,8 @@ static struct kvm *kvm_create_vm(unsigned long type) if (init_srcu_struct(&kvm->irq_srcu)) goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { - kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), - GFP_KERNEL); + rcu_assign_pointer(kvm->buses[i], + kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL)); if (!kvm->buses[i]) goto out_err; } @@ -700,9 +717,10 @@ out_err_no_srcu: hardware_disable_all(); out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) - kfree(kvm->buses[i]); + kfree(rcu_access_pointer(kvm->buses[i])); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, kvm->memslots[i]); + kvm_free_memslots(kvm, + rcu_dereference_protected(kvm->memslots[i], 1)); kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); @@ -728,6 +746,7 @@ static void kvm_destroy_vm(struct kvm *kvm) int i; struct mm_struct *mm = kvm->mm; + kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); spin_lock(&kvm_lock); @@ -735,8 +754,11 @@ static void kvm_destroy_vm(struct kvm *kvm) spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { - if (kvm->buses[i]) - kvm_io_bus_destroy(kvm->buses[i]); + struct kvm_io_bus *bus; + + bus = rcu_dereference_protected(kvm->buses[i], 1); + if (bus) + kvm_io_bus_destroy(bus); kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); @@ -748,7 +770,8 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, kvm->memslots[i]); + kvm_free_memslots(kvm, + rcu_dereference_protected(kvm->memslots[i], 1)); cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); @@ -2551,13 +2574,14 @@ static long kvm_vcpu_ioctl(struct file *filp, if (r) return r; switch (ioctl) { - case KVM_RUN: + case KVM_RUN: { + struct pid *oldpid; r = -EINVAL; if (arg) goto out; - if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) { + oldpid = rcu_access_pointer(vcpu->pid); + if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) { /* The thread running this VCPU changed. */ - struct pid *oldpid = vcpu->pid; struct pid *newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); @@ -2568,6 +2592,7 @@ static long kvm_vcpu_ioctl(struct file *filp, r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; + } case KVM_GET_REGS: { struct kvm_regs *kvm_regs; @@ -3202,6 +3227,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) fput(file); return -ENOMEM; } + kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); fd_install(r, file); return r; @@ -3563,7 +3589,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, { struct kvm_io_bus *new_bus, *bus; - bus = kvm->buses[bus_idx]; + bus = kvm_get_bus(kvm, bus_idx); if (!bus) return -ENOMEM; @@ -3592,7 +3618,7 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, int i; struct kvm_io_bus *new_bus, *bus; - bus = kvm->buses[bus_idx]; + bus = kvm_get_bus(kvm, bus_idx); if (!bus) return; @@ -3854,6 +3880,67 @@ static const struct file_operations *stat_fops[] = { [KVM_STAT_VM] = &vm_stat_fops, }; +static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) +{ + struct kobj_uevent_env *env; + char *tmp, *pathbuf = NULL; + unsigned long long created, active; + + if (!kvm_dev.this_device || !kvm) + return; + + spin_lock(&kvm_lock); + if (type == KVM_EVENT_CREATE_VM) { + kvm_createvm_count++; + kvm_active_vms++; + } else if (type == KVM_EVENT_DESTROY_VM) { + kvm_active_vms--; + } + created = kvm_createvm_count; + active = kvm_active_vms; + spin_unlock(&kvm_lock); + + env = kzalloc(sizeof(*env), GFP_KERNEL); + if (!env) + return; + + add_uevent_var(env, "CREATED=%llu", created); + add_uevent_var(env, "COUNT=%llu", active); + + if (type == KVM_EVENT_CREATE_VM) + add_uevent_var(env, "EVENT=create"); + else if (type == KVM_EVENT_DESTROY_VM) + add_uevent_var(env, "EVENT=destroy"); + + if (kvm->debugfs_dentry) { + char p[ITOA_MAX_LEN]; + + snprintf(p, sizeof(p), "%s", kvm->debugfs_dentry->d_name.name); + tmp = strchrnul(p + 1, '-'); + *tmp = '\0'; + add_uevent_var(env, "PID=%s", p); + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (pathbuf) { + /* sizeof counts the final '\0' */ + int len = sizeof("STATS_PATH=") - 1; + const char *pvar = "STATS_PATH="; + + tmp = dentry_path_raw(kvm->debugfs_dentry, + pathbuf + len, + PATH_MAX - len); + if (!IS_ERR(tmp)) { + memcpy(tmp - len, pvar, len); + env->envp[env->envp_idx++] = tmp - len; + } + } + } + /* no need for checks, since we are adding at most only 5 keys */ + env->envp[env->envp_idx++] = NULL; + kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp); + kfree(env); + kfree(pathbuf); +} + static int kvm_init_debug(void) { int r = -EEXIST; |