752bea4abb
a system with 256 GB of RAM, when NUMA is disabled crashes the following way: Your BIOS doesn't leave a aperture memory hole Please enable the IOMMU option in the BIOS setup This costs you 64 MB of RAM Cannot allocate aperture memory hole (ffff8101c0000000,65536K) Kernel panic - not syncing: Not enough memory for aperture Pid: 0, comm: swapper Not tainted 2.6.25-rc4-x86-latest.git #33 Call Trace: [<ffffffff84037c62>] panic+0xb2/0x190 [<ffffffff840381fc>] ? release_console_sem+0x7c/0x250 [<ffffffff847b1628>] ? __alloc_bootmem_nopanic+0x48/0x90 [<ffffffff847b0ac9>] ? free_bootmem+0x29/0x50 [<ffffffff847ac1f7>] gart_iommu_hole_init+0x5e7/0x680 [<ffffffff847b255b>] ? alloc_large_system_hash+0x16b/0x310 [<ffffffff84506a2f>] ? _etext+0x0/0x1 [<ffffffff847a2e8c>] pci_iommu_alloc+0x1c/0x40 [<ffffffff847ac795>] mem_init+0x45/0x1a0 [<ffffffff8479ff35>] start_kernel+0x295/0x380 [<ffffffff8479f1c2>] _sinittext+0x1c2/0x230 the root cause is : memmap PMD is too big, [ffffe200e0600000-ffffe200e07fffff] PMD ->ffff81383c000000 on node 0 almost near 4G..., and vmemmap_alloc_block will use up the ram under 4G. solution will be: 1. make memmap allocation get memory above 4G... 2. reserve some dma32 range early before we try to set up memmap for all. and release that before pci_iommu_alloc, so gart or swiotlb could get some range under 4g limit for sure. the patch is using method 2. because method1 may need more code to handle SPARSEMEM and SPASEMEM_VMEMMAP will get Your BIOS doesn't leave a aperture memory hole Please enable the IOMMU option in the BIOS setup This costs you 64 MB of RAM Mapping aperture over 65536 KB of RAM @ 4000000 Memory: 264245736k/268959744k available (8484k kernel code, 4187464k reserved, 4004k data, 724k init) Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
67 lines
1.8 KiB
C
67 lines
1.8 KiB
C
#ifndef __x8664_PCI_H
|
|
#define __x8664_PCI_H
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#ifdef CONFIG_CALGARY_IOMMU
|
|
static inline void *pci_iommu(struct pci_bus *bus)
|
|
{
|
|
struct pci_sysdata *sd = bus->sysdata;
|
|
return sd->iommu;
|
|
}
|
|
|
|
static inline void set_pci_iommu(struct pci_bus *bus, void *val)
|
|
{
|
|
struct pci_sysdata *sd = bus->sysdata;
|
|
sd->iommu = val;
|
|
}
|
|
#endif /* CONFIG_CALGARY_IOMMU */
|
|
|
|
extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
|
|
int reg, int len, u32 *value);
|
|
extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
|
|
int reg, int len, u32 value);
|
|
|
|
extern void dma32_reserve_bootmem(void);
|
|
extern void pci_iommu_alloc(void);
|
|
|
|
/* The PCI address space does equal the physical memory
|
|
* address space. The networking and block device layers use
|
|
* this boolean for bounce buffer decisions
|
|
*
|
|
* On AMD64 it mostly equals, but we set it to zero if a hardware
|
|
* IOMMU (gart) of sotware IOMMU (swiotlb) is available.
|
|
*/
|
|
#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
|
|
|
|
#if defined(CONFIG_GART_IOMMU) || defined(CONFIG_CALGARY_IOMMU)
|
|
|
|
#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \
|
|
dma_addr_t ADDR_NAME;
|
|
#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \
|
|
__u32 LEN_NAME;
|
|
#define pci_unmap_addr(PTR, ADDR_NAME) \
|
|
((PTR)->ADDR_NAME)
|
|
#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
|
|
(((PTR)->ADDR_NAME) = (VAL))
|
|
#define pci_unmap_len(PTR, LEN_NAME) \
|
|
((PTR)->LEN_NAME)
|
|
#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
|
|
(((PTR)->LEN_NAME) = (VAL))
|
|
|
|
#else
|
|
/* No IOMMU */
|
|
|
|
#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
|
|
#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
|
|
#define pci_unmap_addr(PTR, ADDR_NAME) (0)
|
|
#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0)
|
|
#define pci_unmap_len(PTR, LEN_NAME) (0)
|
|
#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0)
|
|
|
|
#endif
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* __x8664_PCI_H */
|