summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/m68k/include/asm/flat.h13
-rw-r--r--arch/m68k/include/asm/processor.h15
-rw-r--r--arch/parisc/Kconfig1
-rw-r--r--arch/parisc/include/asm/hash.h146
-rw-r--r--arch/parisc/kernel/firmware.c6
-rw-r--r--arch/parisc/lib/iomap.c64
-rw-r--r--arch/um/Kconfig.common5
-rw-r--r--arch/um/include/asm/irqflags.h18
-rw-r--r--arch/um/kernel/Makefile5
-rw-r--r--arch/um/kernel/initrd.c2
-rw-r--r--arch/um/kernel/um_arch.c8
-rw-r--r--arch/um/os-Linux/Makefile3
-rw-r--r--arch/um/os-Linux/signal.c5
-rw-r--r--arch/x86/um/vdso/Makefile3
14 files changed, 221 insertions, 73 deletions
diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h
index f9454b89a51b..00c392b0cabd 100644
--- a/arch/m68k/include/asm/flat.h
+++ b/arch/m68k/include/asm/flat.h
@@ -1,5 +1,5 @@
/*
- * include/asm-m68knommu/flat.h -- uClinux flat-format executables
+ * flat.h -- uClinux flat-format executables
*/
#ifndef __M68KNOMMU_FLAT_H__
@@ -8,8 +8,9 @@
#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) get_unaligned(rp)
-#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val,rp)
+#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)
#define flat_get_relocate_addr(rel) (rel)
static inline int flat_set_persistent(unsigned long relval,
@@ -18,4 +19,10 @@ static inline int flat_set_persistent(unsigned long relval,
return 0;
}
+#define FLAT_PLAT_INIT(regs) \
+ do { \
+ if (current->mm) \
+ (regs)->d5 = current->mm->start_data; \
+ } while (0)
+
#endif /* __M68KNOMMU_FLAT_H__ */
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index a6ce2ec8d693..c84a2183b3f0 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -110,7 +110,6 @@ struct thread_struct {
#define setframeformat(_regs) do { } while (0)
#endif
-#ifdef CONFIG_MMU
/*
* Do necessary setup to start up a newly executed thread.
*/
@@ -123,26 +122,14 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc,
wrusp(usp);
}
+#ifdef CONFIG_MMU
extern int handle_kernel_fault(struct pt_regs *regs);
-
#else
-
-#define start_thread(_regs, _pc, _usp) \
-do { \
- (_regs)->pc = (_pc); \
- setframeformat(_regs); \
- if (current->mm) \
- (_regs)->d5 = current->mm->start_data; \
- (_regs)->sr &= ~0x2000; \
- wrusp(_usp); \
-} while(0)
-
static inline int handle_kernel_fault(struct pt_regs *regs)
{
/* Any fault in kernel is fatal on non-mmu */
return 0;
}
-
#endif
/* Forward declaration, a strange C thing */
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index dc117385ce2e..cd8778103165 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -31,6 +31,7 @@ config PARISC
select TTY # Needed for pdc_cons.c
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HASH
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_UNSTABLE_SCHED_CLOCK if (SMP || !64BIT)
diff --git a/arch/parisc/include/asm/hash.h b/arch/parisc/include/asm/hash.h
new file mode 100644
index 000000000000..dbe93311aa26
--- /dev/null
+++ b/arch/parisc/include/asm/hash.h
@@ -0,0 +1,146 @@
+#ifndef _ASM_HASH_H
+#define _ASM_HASH_H
+
+/*
+ * HP-PA only implements integer multiply in the FPU. However, for
+ * integer multiplies by constant, it has a number of shift-and-add
+ * (but no shift-and-subtract, sigh!) instructions that a compiler
+ * can synthesize a code sequence with.
+ *
+ * Unfortunately, GCC isn't very efficient at using them. For example
+ * it uses three instructions for "x *= 21" when only two are needed.
+ * But we can find a sequence manually.
+ */
+
+#define HAVE_ARCH__HASH_32 1
+
+/*
+ * This is a multiply by GOLDEN_RATIO_32 = 0x61C88647 optimized for the
+ * PA7100 pairing rules. This is an in-order 2-way superscalar processor.
+ * Only one instruction in a pair may be a shift (by more than 3 bits),
+ * but other than that, simple ALU ops (including shift-and-add by up
+ * to 3 bits) may be paired arbitrarily.
+ *
+ * PA8xxx processors also dual-issue ALU instructions, although with
+ * fewer constraints, so this schedule is good for them, too.
+ *
+ * This 6-step sequence was found by Yevgen Voronenko's implementation
+ * of the Hcub algorithm at http://spiral.ece.cmu.edu/mcm/gen.html.
+ */
+static inline u32 __attribute_const__ __hash_32(u32 x)
+{
+ u32 a, b, c;
+
+ /*
+ * Phase 1: Compute a = (x << 19) + x,
+ * b = (x << 9) + a, c = (x << 23) + b.
+ */
+ a = x << 19; /* Two shifts can't be paired */
+ b = x << 9; a += x;
+ c = x << 23; b += a;
+ c += b;
+ /* Phase 2: Return (b<<11) + (c<<6) + (a<<3) - c */
+ b <<= 11;
+ a += c << 3; b -= c;
+ return (a << 3) + b;
+}
+
+#if BITS_PER_LONG == 64
+
+#define HAVE_ARCH_HASH_64 1
+
+/*
+ * Finding a good shift-and-add chain for GOLDEN_RATIO_64 is tricky,
+ * because available software for the purpose chokes on constants this
+ * large. (It's mostly designed for compiling FIR filter coefficients
+ * into FPGAs.)
+ *
+ * However, Jason Thong pointed out a work-around. The Hcub software
+ * (http://spiral.ece.cmu.edu/mcm/gen.html) is designed for *multiple*
+ * constant multiplication, and is good at finding shift-and-add chains
+ * which share common terms.
+ *
+ * Looking at 0x0x61C8864680B583EB in binary:
+ * 0110000111001000100001100100011010000000101101011000001111101011
+ * \______________/ \__________/ \_______/ \________/
+ * \____________________________/ \____________________/
+ * you can see the non-zero bits are divided into several well-separated
+ * blocks. Hcub can find algorithms for those terms separately, which
+ * can then be shifted and added together.
+ *
+ * Dividing the input into 2, 3 or 4 blocks, Hcub can find solutions
+ * with 10, 9 or 8 adds, respectively, making a total of 11 for the
+ * whole number.
+ *
+ * Using just two large blocks, 0xC3910C8D << 31 in the high bits,
+ * and 0xB583EB in the low bits, produces as good an algorithm as any,
+ * and with one more small shift than alternatives.
+ *
+ * The high bits are a larger number and more work to compute, as well
+ * as needing one extra cycle to shift left 31 bits before the final
+ * addition, so they are the critical path for scheduling. The low bits
+ * can fit into the scheduling slots left over.
+ */
+
+
+/*
+ * This _ASSIGN(dst, src) macro performs "dst = src", but prevents GCC
+ * from inferring anything about the value assigned to "dest".
+ *
+ * This prevents it from mis-optimizing certain sequences.
+ * In particular, gcc is annoyingly eager to combine consecutive shifts.
+ * Given "x <<= 19; y += x; z += x << 1;", GCC will turn this into
+ * "y += x << 19; z += x << 20;" even though the latter sequence needs
+ * an additional instruction and temporary register.
+ *
+ * Because no actual assembly code is generated, this construct is
+ * usefully portable across all GCC platforms, and so can be test-compiled
+ * on non-PA systems.
+ *
+ * In two places, additional unused input dependencies are added. This
+ * forces GCC's scheduling so it does not rearrange instructions too much.
+ * Because the PA-8xxx is out of order, I'm not sure how much this matters,
+ * but why make it more difficult for the processor than necessary?
+ */
+#define _ASSIGN(dst, src, ...) asm("" : "=r" (dst) : "0" (src), ##__VA_ARGS__)
+
+/*
+ * Multiply by GOLDEN_RATIO_64 = 0x0x61C8864680B583EB using a heavily
+ * optimized shift-and-add sequence.
+ *
+ * Without the final shift, the multiply proper is 19 instructions,
+ * 10 cycles and uses only 4 temporaries. Whew!
+ *
+ * You are not expected to understand this.
+ */
+static __always_inline u32 __attribute_const__
+hash_64(u64 a, unsigned int bits)
+{
+ u64 b, c, d;
+
+ /*
+ * Encourage GCC to move a dynamic shift to %sar early,
+ * thereby freeing up an additional temporary register.
+ */
+ if (!__builtin_constant_p(bits))
+ asm("" : "=q" (bits) : "0" (64 - bits));
+ else
+ bits = 64 - bits;
+
+ _ASSIGN(b, a*5); c = a << 13;
+ b = (b << 2) + a; _ASSIGN(d, a << 17);
+ a = b + (a << 1); c += d;
+ d = a << 10; _ASSIGN(a, a << 19);
+ d = a - d; _ASSIGN(a, a << 4, "X" (d));
+ c += b; a += b;
+ d -= c; c += a << 1;
+ a += c << 3; _ASSIGN(b, b << (7+31), "X" (c), "X" (d));
+ a <<= 31; b += d;
+ a += b;
+ return a >> bits;
+}
+#undef _ASSIGN /* We're a widely-used header file, so don't litter! */
+
+#endif /* BITS_PER_LONG == 64 */
+
+#endif /* _ASM_HASH_H */
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 22395901d47b..e5d71905cad5 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -1354,9 +1354,9 @@ int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *mem_addr)
retval = mem_pdc_call(PDC_PAT_IO, PDC_PAT_IO_PCI_CONFIG_READ,
__pa(pdc_result), pci_addr, pci_size);
switch(pci_size) {
- case 1: *(u8 *) mem_addr = (u8) pdc_result[0];
- case 2: *(u16 *)mem_addr = (u16) pdc_result[0];
- case 4: *(u32 *)mem_addr = (u32) pdc_result[0];
+ case 1: *(u8 *) mem_addr = (u8) pdc_result[0]; break;
+ case 2: *(u16 *)mem_addr = (u16) pdc_result[0]; break;
+ case 4: *(u32 *)mem_addr = (u32) pdc_result[0]; break;
}
spin_unlock_irqrestore(&pdc_lock, flags);
diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c
index fb8e10a4fb39..eaffbb90aa14 100644
--- a/arch/parisc/lib/iomap.c
+++ b/arch/parisc/lib/iomap.c
@@ -125,22 +125,22 @@ static void ioport_write32r(void __iomem *addr, const void *s, unsigned long n)
}
static const struct iomap_ops ioport_ops = {
- ioport_read8,
- ioport_read16,
- ioport_read16,
- ioport_read32,
- ioport_read32,
- ioport_write8,
- ioport_write16,
- ioport_write16,
- ioport_write32,
- ioport_write32,
- ioport_read8r,
- ioport_read16r,
- ioport_read32r,
- ioport_write8r,
- ioport_write16r,
- ioport_write32r,
+ .read8 = ioport_read8,
+ .read16 = ioport_read16,
+ .read16be = ioport_read16,
+ .read32 = ioport_read32,
+ .read32be = ioport_read32,
+ .write8 = ioport_write8,
+ .write16 = ioport_write16,
+ .write16be = ioport_write16,
+ .write32 = ioport_write32,
+ .write32be = ioport_write32,
+ .read8r = ioport_read8r,
+ .read16r = ioport_read16r,
+ .read32r = ioport_read32r,
+ .write8r = ioport_write8r,
+ .write16r = ioport_write16r,
+ .write32r = ioport_write32r,
};
/* Legacy I/O memory ops */
@@ -244,22 +244,22 @@ static void iomem_write32r(void __iomem *addr, const void *s, unsigned long n)
}
static const struct iomap_ops iomem_ops = {
- iomem_read8,
- iomem_read16,
- iomem_read16be,
- iomem_read32,
- iomem_read32be,
- iomem_write8,
- iomem_write16,
- iomem_write16be,
- iomem_write32,
- iomem_write32be,
- iomem_read8r,
- iomem_read16r,
- iomem_read32r,
- iomem_write8r,
- iomem_write16r,
- iomem_write32r,
+ .read8 = iomem_read8,
+ .read16 = iomem_read16,
+ .read16be = iomem_read16be,
+ .read32 = iomem_read32,
+ .read32be = iomem_read32be,
+ .write8 = iomem_write8,
+ .write16 = iomem_write16,
+ .write16be = iomem_write16be,
+ .write32 = iomem_write32,
+ .write32be = iomem_write32be,
+ .read8r = iomem_read8r,
+ .read16r = iomem_read16r,
+ .read32r = iomem_read32r,
+ .write8r = iomem_write8r,
+ .write16r = iomem_write16r,
+ .write32r = iomem_write32r,
};
static const struct iomap_ops *iomap_ops[8] = {
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index 58650d098fb4..fd443852103c 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -1,10 +1,12 @@
config UML
bool
default y
+ select ARCH_HAS_KCOV
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_UID16
select HAVE_FUTEX_CMPXCHG if FUTEX
+ select HAVE_DEBUG_KMEMLEAK
select GENERIC_IRQ_SHOW
select GENERIC_CPU_DEVICES
select GENERIC_IO
@@ -31,10 +33,9 @@ config PCI
config PCMCIA
bool
-# Yet to do!
config TRACE_IRQFLAGS_SUPPORT
bool
- default n
+ default y
config LOCKDEP_SUPPORT
bool
diff --git a/arch/um/include/asm/irqflags.h b/arch/um/include/asm/irqflags.h
index c780d8a16773..3bb221e1d5a4 100644
--- a/arch/um/include/asm/irqflags.h
+++ b/arch/um/include/asm/irqflags.h
@@ -6,37 +6,33 @@ extern int set_signals(int enable);
extern void block_signals(void);
extern void unblock_signals(void);
+#define arch_local_save_flags arch_local_save_flags
static inline unsigned long arch_local_save_flags(void)
{
return get_signals();
}
+#define arch_local_irq_restore arch_local_irq_restore
static inline void arch_local_irq_restore(unsigned long flags)
{
set_signals(flags);
}
+#define arch_local_irq_enable arch_local_irq_enable
static inline void arch_local_irq_enable(void)
{
unblock_signals();
}
+#define arch_local_irq_disable arch_local_irq_disable
static inline void arch_local_irq_disable(void)
{
block_signals();
}
-static inline unsigned long arch_local_irq_save(void)
-{
- unsigned long flags;
- flags = arch_local_save_flags();
- arch_local_irq_disable();
- return flags;
-}
+#define ARCH_IRQ_DISABLED 0
+#define ARCh_IRQ_ENABLED (SIGIO|SIGVTALRM)
-static inline bool arch_irqs_disabled(void)
-{
- return arch_local_save_flags() == 0;
-}
+#include <asm-generic/irqflags.h>
#endif
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index a6a5e42caaef..2f36d515762e 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -3,6 +3,11 @@
# Licensed under the GPL
#
+# Don't instrument UML-specific code; without this, we may crash when
+# accessing the instrumentation buffer for the first time from the
+# kernel.
+KCOV_INSTRUMENT := n
+
CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START) \
-DELF_ARCH=$(LDS_ELF_ARCH) \
-DELF_FORMAT=$(LDS_ELF_FORMAT) \
diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c
index 55cead809b18..48bae81f8dca 100644
--- a/arch/um/kernel/initrd.c
+++ b/arch/um/kernel/initrd.c
@@ -37,8 +37,6 @@ static int __init read_initrd(void)
}
area = alloc_bootmem(size);
- if (area == NULL)
- return 0;
if (load_initrd(initrd, area, size) == -1)
return 0;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 16630e75f056..e8175a8aa22c 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -319,9 +319,6 @@ int __init linux_main(int argc, char **argv)
start_vm = VMALLOC_START;
- setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
- mem_total_pages(physmem_size, iomem_size, highmem);
-
virtmem_size = physmem_size;
stack = (unsigned long) argv;
stack &= ~(1024 * 1024 - 1);
@@ -334,7 +331,6 @@ int __init linux_main(int argc, char **argv)
printf("Kernel virtual memory size shrunk to %lu bytes\n",
virtmem_size);
- stack_protections((unsigned long) &init_thread_info);
os_flush_stdout();
return start_uml();
@@ -342,6 +338,10 @@ int __init linux_main(int argc, char **argv)
void __init setup_arch(char **cmdline_p)
{
+ stack_protections((unsigned long) &init_thread_info);
+ setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
+ mem_total_pages(physmem_size, iomem_size, highmem);
+
paging_init();
strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile
index 08ff5094fcdd..ada473bf6f46 100644
--- a/arch/um/os-Linux/Makefile
+++ b/arch/um/os-Linux/Makefile
@@ -3,6 +3,9 @@
# Licensed under the GPL
#
+# Don't instrument UML-specific code
+KCOV_INSTRUMENT := n
+
obj-y = aio.o execvp.o file.o helper.o irq.o main.o mem.o process.o \
registers.o sigio.o signal.o start_up.o time.o tty.o \
umid.o user_syms.o util.o drivers/ skas/
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 8acaf4e384c0..a86d7cc2c2d8 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -15,6 +15,7 @@
#include <kern_util.h>
#include <os.h>
#include <sysdep/mcontext.h>
+#include <um_malloc.h>
void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
[SIGTRAP] = relay_signal,
@@ -32,7 +33,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
struct uml_pt_regs *r;
int save_errno = errno;
- r = malloc(sizeof(struct uml_pt_regs));
+ r = uml_kmalloc(sizeof(struct uml_pt_regs), UM_GFP_ATOMIC);
if (!r)
panic("out of memory");
@@ -91,7 +92,7 @@ static void timer_real_alarm_handler(mcontext_t *mc)
{
struct uml_pt_regs *regs;
- regs = malloc(sizeof(struct uml_pt_regs));
+ regs = uml_kmalloc(sizeof(struct uml_pt_regs), UM_GFP_ATOMIC);
if (!regs)
panic("out of memory");
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 6c803ca49b5d..d72dec406ccb 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -2,6 +2,9 @@
# Building vDSO images for x86.
#
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT := n
+
VDSO64-y := y
vdso-install-$(VDSO64-y) += vdso.so
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-19 17:15:02 +0000